From 247cd9e34ac47280bf1d6119410f830a75bd9be7 Mon Sep 17 00:00:00 2001 From: Jeffrey Barrick Date: Wed, 10 Jul 2024 10:39:58 -0500 Subject: [PATCH] Fixed assignment of promoter regions #374 --- src/c/breseq/reference_sequence.cpp | 52 +++---------------- .../expected.gd | 4 +- .../expected.gd | 2 +- .../expected.gd | 6 +-- tests/gdtools_annotate_1/expected.gd | 4 +- tests/gdtools_annotate_2/expected.gd | 4 +- tests/gdtools_annotate_3/expected.json | 8 +-- tests/gdtools_compare_1/expected.gd | 6 +-- tests/gdtools_compare_5/expected.tsv | 14 ++--- tests/gdtools_compare_8/expected.csv | 14 ++--- tests/gdtools_convert_1/expected.json | 8 +-- tests/gdtools_convert_2/expected.json | 8 +-- tests/lambda_contig_ref/expected.gd | 4 +- tests/lambda_mixed_pop/expected.gd | 4 +- .../lambda_mixed_pop_bad_contigs/expected.gd | 4 +- .../expected.gd | 4 +- .../expected.gd | 4 +- tests/lambda_mult_ref_read/expected.gd | 4 +- .../expected.gd | 8 +-- tests/lambda_polymorphism/expected.gd | 8 +-- .../expected.gd | 4 +- .../expected.gd | 24 ++++----- .../expected.gd | 6 +-- .../expected.gd | 4 +- .../expected.gd | 8 +-- .../expected.gd | 28 +++++----- 26 files changed, 103 insertions(+), 141 deletions(-) diff --git a/src/c/breseq/reference_sequence.cpp b/src/c/breseq/reference_sequence.cpp index b3513f41..363bbb98 100644 --- a/src/c/breseq/reference_sequence.cpp +++ b/src/c/breseq/reference_sequence.cpp @@ -3515,46 +3515,10 @@ void cReferenceSequences::annotate_1_mutation(cDiffEntry& mut, uint32_t start, u if (next_gene_loc) next_gene = (cGeneFeature)*(next_gene_loc->get_feature()); // -------------- Begin "genes_promoter" field - - - /* code for assigning only to closest one - if (mut.is_mutation()) { - // Decide on promoter mutations - int32_t prev_gene_distance(numeric_limits::max()), next_gene_distance(numeric_limits::max()); - if (prev_gene.name.size() > 0) { - int32_t start_coord = mut.get_reference_coordinate_start().get_position(); - for (cFeatureLocationList::iterator it = prev_gene.m_locations.begin(); it != prev_gene.m_locations.end(); it++) { - if (it->get_strand() == -1) { - int32_t dist = start - it->get_end_1(); - prev_gene_distance = min(dist, prev_gene_distance); - } - } - } - if (next_gene.name.size() > 0) { - int32_t start_coord = mut.get_reference_coordinate_start().get_position(); - for (cFeatureLocationList::iterator it = prev_gene.m_locations.begin(); it != prev_gene.m_locations.end(); it++) { - if (it->get_strand() == +1) { - int32_t dist = it->get_start_1() - end; - next_gene_distance = min(dist, next_gene_distance); - } - } - } - - - // ties go to prev_gene! - if ((prev_gene_distance <= promoter_distance) && (prev_gene_distance <= next_gene_distance)) { - mut["genes_promoter"] = prev_gene.name; - mut["locus_tags_promoter"] = prev_gene.get_locus_tag(); - - } else if (next_gene_distance <= promoter_distance) { - mut["genes_promoter"] = next_gene.name; - mut["locus_tags_promoter"] = next_gene.get_locus_tag(); - - } - } - */ // Code for assigning to multiple promoters + // * At most it will be the two closest genes on each side of the mutation + if (mut.is_mutation()) { int32_t prev_gene_distance(numeric_limits::max()), next_gene_distance(numeric_limits::max()); if (prev_gene.name.size() > 0) { @@ -3568,7 +3532,7 @@ void cReferenceSequences::annotate_1_mutation(cDiffEntry& mut, uint32_t start, u } if (next_gene.name.size() > 0) { int32_t start_coord = mut.get_reference_coordinate_start().get_position(); - for (cFeatureLocationList::iterator it = prev_gene.m_locations.begin(); it != prev_gene.m_locations.end(); it++) { + for (cFeatureLocationList::iterator it = next_gene.m_locations.begin(); it != next_gene.m_locations.end(); it++) { if (it->get_strand() == +1) { int32_t dist = it->get_start_1() - end; next_gene_distance = min(dist, next_gene_distance); @@ -3579,16 +3543,14 @@ void cReferenceSequences::annotate_1_mutation(cDiffEntry& mut, uint32_t start, u vector genes_promoter_list; vector locus_tags_promoter_list; - if ((prev_gene_distance <= promoter_distance)) { - + if (prev_gene_distance <= promoter_distance) { genes_promoter_list.push_back(prev_gene.name); locus_tags_promoter_list.push_back(prev_gene.get_locus_tag()); - - } else if (next_gene_distance <= promoter_distance) { - + } + + if (next_gene_distance <= promoter_distance) { genes_promoter_list.push_back(next_gene.name); locus_tags_promoter_list.push_back(next_gene.get_locus_tag()); - } mut["genes_promoter"] = join(genes_promoter_list, ","); diff --git a/tests/REL606_fragment_advanced_mobile_element/expected.gd b/tests/REL606_fragment_advanced_mobile_element/expected.gd index e290dff3..3048d7c8 100644 --- a/tests/REL606_fragment_advanced_mobile_element/expected.gd +++ b/tests/REL606_fragment_advanced_mobile_element/expected.gd @@ -11,7 +11,7 @@ MOB 1 35,36 REL606-5 1000 IS1 -1 3 gene_name=dkgB gene_position=coding (400-402/804 nt) gene_product=2,5-diketo-D-gluconate reductase B gene_strand=> genes_inactivated=dkgB locus_tag=ECB_00200 locus_tags_inactivated=ECB_00200 mutation_category=mobile_element_insertion position_end=1002 position_start=1000 ref_seq=CCA repeat_size=768 MOB 2 37,38 REL606-5 2000 IS1 1 7 gene_name=yafC gene_position=coding (310-316/915 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< genes_inactivated=yafC locus_tag=ECB_00201 locus_tags_inactivated=ECB_00201 mutation_category=mobile_element_insertion position_end=2006 position_start=2000 ref_seq=GCAGCAC repeat_size=768 MOB 3 25,39,40 REL606-5 3000 IS1 -1 -3 gene_name=yafD gene_position=coding (445-447/801 nt) gene_product=hypothetical protein gene_strand=> genes_inactivated=yafD locus_tag=ECB_00202 locus_tags_inactivated=ECB_00202 mutation_category=mobile_element_insertion position_end=3002 position_start=3000 ref_seq=CTG repeat_size=768 -MOB 4 26,41,42 REL606-5 4000 IS1 1 -7 gene_name=yafE/mltD gene_position=intergenic (+17/+25) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< genes_promoter=mltD locus_tag=ECB_00203/ECB_00204 locus_tags_promoter=ECB_00204 mutation_category=mobile_element_insertion position_end=4006 position_start=4000 ref_seq=GGGAATC repeat_size=768 +MOB 4 26,41,42 REL606-5 4000 IS1 1 -7 gene_name=yafE/mltD gene_position=intergenic (+17/+25) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< locus_tag=ECB_00203/ECB_00204 mutation_category=mobile_element_insertion position_end=4006 position_start=4000 ref_seq=GGGAATC repeat_size=768 MOB 5 43,44 REL606-5 5000 IS1 -1 6 del_start=3 gene_name=mltD gene_position=coding (385-390/1359 nt) gene_product=predicted membrane-bound lytic murein transglycosylase D gene_strand=< genes_inactivated=mltD locus_tag=ECB_00204 locus_tags_inactivated=ECB_00204 mutation_category=mobile_element_insertion position_end=5005 position_start=5000 ref_seq=AGGATC repeat_size=768 MOB 6 45,46 REL606-5 6000 IS1 1 4 gene_name=gloB gene_position=coding (214-217/756 nt) gene_product=predicted hydroxyacylglutathione hydrolase gene_strand=< genes_inactivated=gloB ins_end=TG locus_tag=ECB_00205 locus_tags_inactivated=ECB_00205 mutation_category=mobile_element_insertion position_end=6003 position_start=6000 ref_seq=CAAT repeat_size=768 MOB 7 47,48 REL606-5 7000 IS1 -1 3 del_end=3 gene_name=rnhA gene_position=coding (435-437/468 nt) gene_product=ribonuclease H gene_strand=< genes_overlapping=rnhA ins_end=CTT locus_tag=ECB_00207 locus_tags_overlapping=ECB_00207 mutation_category=mobile_element_insertion position_end=7002 position_start=7000 ref_seq=AGT repeat_size=768 @@ -29,7 +29,7 @@ MOB 18 63,73 REL606-5 26000 IS1 -1 2 gene_name=yafP gene_position=coding (219-22 MOB 19 32,53,74 REL606-5 27000 IS1 1 -3 del_end=6 gene_name=prfH gene_position=coding (298-300/501 nt) gene_product=peptide chain release factor 2 gene_strand=> genes_inactivated=prfH locus_tag=ECB_00231 locus_tags_inactivated=ECB_00231 mutation_category=mobile_element_insertion position_end=27002 position_start=27000 ref_seq=TCC repeat_size=768 MOB 20 33,64,75 REL606-5 28000 IS1 -1 -1 gene_name=pepD gene_position=coding (718/1458 nt) gene_product=aminoacyl-histidine dipeptidase (peptidase D) gene_strand=< genes_inactivated=pepD ins_start=AGGC locus_tag=ECB_00232 locus_tags_inactivated=ECB_00232 mutation_category=mobile_element_insertion position_end=28000 position_start=28000 ref_seq=C repeat_size=768 MOB 21 78,82 REL606-5 35000 IS1 -1 0 del_end=3 del_start=1 gene_name=proA gene_position=coding (496/1254 nt) gene_product=gamma-glutamyl phosphate reductase gene_strand=> genes_inactivated=proA ins_end=TA ins_start=T locus_tag=ECB_00240 locus_tags_inactivated=ECB_00240 mutation_category=mobile_element_insertion position_end=35000 position_start=35000 ref_seq=T repeat_size=768 -MOB 22 61,77 REL606-5 36000 IS1 1 7 del_end=2 del_start=2 gene_name=thrW/yagP gene_position=intergenic (+52/+69) gene_product=tRNA-Thr/predicted transcriptional regulator gene_strand=>/< genes_promoter=yagP ins_end=GC ins_start=ATGGC locus_tag=ECB_t00005/ECB_00241 locus_tags_promoter=ECB_00241 mutation_category=mobile_element_insertion position_end=36006 position_start=36000 ref_seq=CCGTATT repeat_size=768 +MOB 22 61,77 REL606-5 36000 IS1 1 7 del_end=2 del_start=2 gene_name=thrW/yagP gene_position=intergenic (+52/+69) gene_product=tRNA-Thr/predicted transcriptional regulator gene_strand=>/< ins_end=GC ins_start=ATGGC locus_tag=ECB_t00005/ECB_00241 mutation_category=mobile_element_insertion position_end=36006 position_start=36000 ref_seq=CCGTATT repeat_size=768 MOB 23 76,81 REL606-5 37000 IS1 -1 1 del_end=1 del_start=3 gene_name=yagQ gene_position=coding (421/957 nt) gene_product=hypothetical protein gene_strand=< genes_inactivated=yagQ ins_end=AGC ins_start=AGTC locus_tag=ECB_00242 locus_tags_inactivated=ECB_00242 mutation_category=mobile_element_insertion position_end=37000 position_start=37000 ref_seq=T repeat_size=768 MOB 24 79,80 REL606-5 38000 IS1 1 2 del_end=10 del_start=5 gene_name=yagR gene_position=coding (1628-1629/2199 nt) gene_product=predicted oxidoreductase with molybdenum-binding domain gene_strand=< genes_inactivated=yagR ins_end=CA ins_start=CG locus_tag=ECB_00243 locus_tags_inactivated=ECB_00243 mutation_category=mobile_element_insertion position_end=38001 position_start=38000 ref_seq=AA repeat_size=768 MC 25 . REL606-5 3000 3002 0 0 gene_name=yafD gene_position=coding (445-447/801 nt) gene_product=hypothetical protein gene_strand=> left_inside_cov=0 left_outside_cov=27 locus_tag=ECB_00202 right_inside_cov=0 right_outside_cov=14 diff --git a/tests/REL606_fragment_is_junction_only/expected.gd b/tests/REL606_fragment_is_junction_only/expected.gd index 7493e892..f8387b85 100644 --- a/tests/REL606_fragment_is_junction_only/expected.gd +++ b/tests/REL606_fragment_is_junction_only/expected.gd @@ -10,7 +10,7 @@ #=MAPPED-BASES 1407249 #=MAPPED-READS 39196 MOB 1 8,9 REL606-5 2345 IS150 1 3 gene_name=yafC/yafD gene_position=intergenic (-30/-209) gene_product=predicted DNA-binding transcriptional regulator/hypothetical protein gene_strand= genes_promoter=yafC locus_tag=ECB_00201/ECB_00202 locus_tags_promoter=ECB_00201 mutation_category=mobile_element_insertion position_end=2347 position_start=2345 ref_seq=ATT repeat_size=1443 -MOB 2 10,11 REL606-5 4000 IS150 -1 3 gene_name=yafE/mltD gene_position=intergenic (+17/+29) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< genes_promoter=mltD locus_tag=ECB_00203/ECB_00204 locus_tags_promoter=ECB_00204 mutation_category=mobile_element_insertion position_end=4002 position_start=4000 ref_seq=GGG repeat_size=1443 +MOB 2 10,11 REL606-5 4000 IS150 -1 3 gene_name=yafE/mltD gene_position=intergenic (+17/+29) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< locus_tag=ECB_00203/ECB_00204 mutation_category=mobile_element_insertion position_end=4002 position_start=4000 ref_seq=GGG repeat_size=1443 MOB 3 12,13 REL606-5 4400 IS150 1 3 gene_name=mltD gene_position=coding (988-990/1359 nt) gene_product=predicted membrane-bound lytic murein transglycosylase D gene_strand=< genes_inactivated=mltD locus_tag=ECB_00204 locus_tags_inactivated=ECB_00204 mutation_category=mobile_element_insertion position_end=4402 position_start=4400 ref_seq=CGT repeat_size=1443 MOB 4 15,16 REL606-5 38000 IS1 -1 6 gene_name=yagR gene_position=coding (1624-1629/2199 nt) gene_product=predicted oxidoreductase with molybdenum-binding domain gene_strand=< genes_inactivated=yagR locus_tag=ECB_00243 locus_tags_inactivated=ECB_00243 mutation_category=mobile_element_insertion position_end=38005 position_start=38000 ref_seq=AAACTG repeat_size=768 MOB 5 14,17 REL606-5 42000 IS1 1 6 gene_name=yagU gene_position=coding (317-322/615 nt) gene_product=conserved inner membrane protein gene_strand=> genes_inactivated=yagU locus_tag=ECB_00246 locus_tags_inactivated=ECB_00246 mutation_category=mobile_element_insertion position_end=42005 position_start=42000 ref_seq=ACATTA repeat_size=768 diff --git a/tests/REL606_tiled_reads_continuation/expected.gd b/tests/REL606_tiled_reads_continuation/expected.gd index 52600f41..cb4f19ce 100644 --- a/tests/REL606_tiled_reads_continuation/expected.gd +++ b/tests/REL606_tiled_reads_continuation/expected.gd @@ -16,12 +16,12 @@ MOB 4 50,51 REL606-5 2000 IS1 1 7 frequency=1 gene_name=yafC gene_position=codin INS 5 52 REL606-5 2129 CTT frequency=1 gene_name=yafC gene_position=coding (187/915 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< genes_overlapping=yafC locus_tag=ECB_00201 locus_tags_overlapping=ECB_00201 mutation_category=small_indel position_end=2129 position_start=2129 ref_seq=C MOB 6 35,53,54 REL606-5 3000 IS1 -1 -3 frequency=1 gene_name=yafD gene_position=coding (445-447/801 nt) gene_product=hypothetical protein gene_strand=> genes_inactivated=yafD locus_tag=ECB_00202 locus_tags_inactivated=ECB_00202 mutation_category=mobile_element_insertion position_end=3002 position_start=3000 ref_seq=CTG repeat_size=768 DEL 7 36,55 REL606-5 3249 3 frequency=1 gene_name=yafD gene_position=coding (694-696/801 nt) gene_product=hypothetical protein gene_strand=> genes_overlapping=yafD locus_tag=ECB_00202 locus_tags_overlapping=ECB_00202 mutation_category=small_indel position_end=3251 position_start=3249 ref_seq=GTT -MOB 8 37,56,57 REL606-5 4000 IS1 1 -7 frequency=1 gene_name=yafE/mltD gene_position=intergenic (+17/+25) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< genes_promoter=mltD locus_tag=ECB_00203/ECB_00204 locus_tags_promoter=ECB_00204 mutation_category=mobile_element_insertion position_end=4006 position_start=4000 ref_seq=GGGAATC repeat_size=768 +MOB 8 37,56,57 REL606-5 4000 IS1 1 -7 frequency=1 gene_name=yafE/mltD gene_position=intergenic (+17/+25) gene_product=predicted S-adenosyl-L-methionine-dependent methyltransferase/predicted membrane-bound lytic murein transglycosylase D gene_strand=>/< locus_tag=ECB_00203/ECB_00204 mutation_category=mobile_element_insertion position_end=4006 position_start=4000 ref_seq=GGGAATC repeat_size=768 MOB 9 58,59 REL606-5 5000 IS1 -1 6 del_start=3 frequency=1 gene_name=mltD gene_position=coding (385-390/1359 nt) gene_product=predicted membrane-bound lytic murein transglycosylase D gene_strand=< genes_inactivated=mltD locus_tag=ECB_00204 locus_tags_inactivated=ECB_00204 mutation_category=mobile_element_insertion position_end=5005 position_start=5000 ref_seq=AGGATC repeat_size=768 MOB 10 60,61 REL606-5 6000 IS1 1 4 frequency=1 gene_name=gloB gene_position=coding (214-217/756 nt) gene_product=predicted hydroxyacylglutathione hydrolase gene_strand=< genes_inactivated=gloB ins_end=TG locus_tag=ECB_00205 locus_tags_inactivated=ECB_00205 mutation_category=mobile_element_insertion position_end=6003 position_start=6000 ref_seq=CAAT repeat_size=768 MOB 11 62,63 REL606-5 7000 IS1 -1 3 del_end=3 frequency=1 gene_name=rnhA gene_position=coding (435-437/468 nt) gene_product=ribonuclease H gene_strand=< genes_overlapping=rnhA ins_end=CTT locus_tag=ECB_00207 locus_tags_overlapping=ECB_00207 mutation_category=mobile_element_insertion position_end=7002 position_start=7000 ref_seq=AGT repeat_size=768 MOB 12 64,65 REL606-5 8000 IS1 1 3 frequency=1 gene_name=dnaQ gene_position=coding (500-502/732 nt) gene_product=DNA polymerase III subunit epsilon gene_strand=> genes_inactivated=dnaQ ins_start=ATGGC locus_tag=ECB_00208 locus_tags_inactivated=ECB_00208 mutation_category=mobile_element_insertion position_end=8002 position_start=8000 ref_seq=ATG repeat_size=768 -DEL 13 66 REL606-5 8494 3 frequency=1 gene_name=aspV/yafT gene_position=intergenic (+53/-275) gene_product=tRNA-Asp/predicted aminopeptidase gene_strand=>/> genes_promoter=yafT locus_tag=ECB_t00004/ECB_00209 locus_tags_promoter=ECB_00209 mutation_category=small_indel position_end=8496 position_start=8494 ref_seq=TTT +DEL 13 66 REL606-5 8494 3 frequency=1 gene_name=aspV/yafT gene_position=intergenic (+53/-275) gene_product=tRNA-Asp/predicted aminopeptidase gene_strand=>/> locus_tag=ECB_t00004/ECB_00209 mutation_category=small_indel position_end=8496 position_start=8494 ref_seq=TTT INS 14 81 REL606-5 10708 GGG frequency=1 gene_name=ECB_00212 gene_position=coding (188/372 nt) gene_product=hypothetical protein gene_strand=> genes_overlapping=ECB_00212 locus_tag=ECB_00212 locus_tags_overlapping=ECB_00212 mutation_category=small_indel position_end=10708 position_start=10708 ref_seq=G MOB 15 38,72,78 REL606-5 15000 IS1 -1 -3 del_end=3 del_start=1 frequency=1 gene_name=fadE gene_position=coding (1383-1385/2445 nt) gene_product=acyl-CoA dehydrogenase gene_strand=< genes_inactivated=fadE ins_end=TA ins_start=T locus_tag=ECB_00216 locus_tags_inactivated=ECB_00216 mutation_category=mobile_element_insertion position_end=15002 position_start=15000 ref_seq=GAC repeat_size=768 MOB 16 39,71,76 REL606-5 16000 IS1 1 -7 del_end=2 del_start=2 frequency=1 gene_name=fadE gene_position=coding (379-385/2445 nt) gene_product=acyl-CoA dehydrogenase gene_strand=< genes_inactivated=fadE ins_end=GC ins_start=ATGGC locus_tag=ECB_00216 locus_tags_inactivated=ECB_00216 mutation_category=mobile_element_insertion position_end=16006 position_start=16000 ref_seq=CGAGAAA repeat_size=768 @@ -37,7 +37,7 @@ MOB 25 43,69,91 REL606-5 27000 IS1 1 -3 del_end=6 frequency=1 gene_name=prfH gen MOB 26 80,92 REL606-5 28000 IS1 -1 -1 frequency=1 gene_name=pepD gene_position=coding (718/1458 nt) gene_product=aminoacyl-histidine dipeptidase (peptidase D) gene_strand=< genes_inactivated=pepD ins_start=AGGC locus_tag=ECB_00232 locus_tags_inactivated=ECB_00232 mutation_category=mobile_element_insertion position_end=28000 position_start=28000 ref_seq=C repeat_size=768 DEL 27 32,33 REL606-5 34577 2 frequency=1 gene_name=proA gene_position=coding (73-74/1254 nt) gene_product=gamma-glutamyl phosphate reductase gene_strand=> genes_inactivated=proA locus_tag=ECB_00240 locus_tags_inactivated=ECB_00240 mutation_category=small_indel position_end=34578 position_start=34577 ref_seq=AA repeat_length=1 repeat_new_copies=5 repeat_ref_copies=7 repeat_seq=A MOB 28 95,99 REL606-5 35000 IS1 -1 0 del_end=3 del_start=1 frequency=1 gene_name=proA gene_position=coding (496/1254 nt) gene_product=gamma-glutamyl phosphate reductase gene_strand=> genes_inactivated=proA ins_end=TA ins_start=T locus_tag=ECB_00240 locus_tags_inactivated=ECB_00240 mutation_category=mobile_element_insertion position_end=35000 position_start=35000 ref_seq=T repeat_size=768 -MOB 29 77,94 REL606-5 36000 IS1 1 7 del_end=2 del_start=2 frequency=1 gene_name=thrW/yagP gene_position=intergenic (+52/+69) gene_product=tRNA-Thr/predicted transcriptional regulator gene_strand=>/< genes_promoter=yagP ins_end=GC ins_start=ATGGC locus_tag=ECB_t00005/ECB_00241 locus_tags_promoter=ECB_00241 mutation_category=mobile_element_insertion position_end=36006 position_start=36000 ref_seq=CCGTATT repeat_size=768 +MOB 29 77,94 REL606-5 36000 IS1 1 7 del_end=2 del_start=2 frequency=1 gene_name=thrW/yagP gene_position=intergenic (+52/+69) gene_product=tRNA-Thr/predicted transcriptional regulator gene_strand=>/< ins_end=GC ins_start=ATGGC locus_tag=ECB_t00005/ECB_00241 mutation_category=mobile_element_insertion position_end=36006 position_start=36000 ref_seq=CCGTATT repeat_size=768 MOB 30 93,98 REL606-5 37000 IS1 -1 1 del_end=1 del_start=3 frequency=1 gene_name=yagQ gene_position=coding (421/957 nt) gene_product=hypothetical protein gene_strand=< genes_inactivated=yagQ ins_end=AGC ins_start=AGTC locus_tag=ECB_00242 locus_tags_inactivated=ECB_00242 mutation_category=mobile_element_insertion position_end=37000 position_start=37000 ref_seq=T repeat_size=768 MOB 31 96,97 REL606-5 38000 IS1 1 2 del_end=10 del_start=5 frequency=1 gene_name=yagR gene_position=coding (1628-1629/2199 nt) gene_product=predicted oxidoreductase with molybdenum-binding domain gene_strand=< genes_inactivated=yagR ins_end=CA ins_start=CG locus_tag=ECB_00243 locus_tags_inactivated=ECB_00243 mutation_category=mobile_element_insertion position_end=38001 position_start=38000 ref_seq=AA repeat_size=768 RA 32 . REL606-5 34577 0 A . consensus_score=358.9 frequency=1 gene_name=proA gene_position=coding (73/1254 nt) gene_product=gamma-glutamyl phosphate reductase gene_strand=> locus_tag=ECB_00240 major_base=. major_cov=30/30 major_frequency=1.00000000e+00 minor_base=N minor_cov=0/0 new_cov=30/30 polymorphism_frequency=1.00000000e+00 polymorphism_reject=FREQUENCY_CUTOFF,VARIANT_STRAND_COVERAGE,INDEL_HOMOPOLYMER polymorphism_score=NA prediction=consensus ref_cov=0/0 total_cov=30/30 diff --git a/tests/gdtools_annotate_1/expected.gd b/tests/gdtools_annotate_1/expected.gd index 97383f90..e4e084af 100644 --- a/tests/gdtools_annotate_1/expected.gd +++ b/tests/gdtools_annotate_1/expected.gd @@ -15,7 +15,7 @@ SNP 12 . NC_001416-4 7356 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_s SNP 13 . NC_001416-4 7361 A aa_new_seq=E aa_position=66 aa_ref_seq=A codon_new_seq=GAA codon_number=66 codon_position=2 codon_ref_seq=GCA frequency=0.0550 gene_name=Rz gene_position=197 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7361 position_start=7361 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 14 . NC_001416-4 7384 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=0.0870 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7384 position_start=7384 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 15 . NC_001416-4 7389 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=0.1100 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=7389 position_start=7389 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 16 . NC_001416-4 7629 C frequency=0.2390 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic +SNP 16 . NC_001416-4 7629 C frequency=0.2390 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic SNP 17 . NC_001416-4 7796 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=0.2630 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7796 position_start=7796 ref_seq=G snp_type=synonymous transl_table=11 SNP 18 . NC_001416-4 7807 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=0.2100 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=7807 position_start=7807 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 19 . NC_001416-4 7811 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=0.2090 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7811 position_start=7811 ref_seq=C snp_type=synonymous transl_table=11 @@ -44,7 +44,7 @@ SNP 41 . NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 42 . NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 43 . NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 44 . NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 45 . NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 45 . NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 46 . NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 47 . NC_001416-4 9172 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic SUB 48 . NC_001416-4 9176 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=9177 position_start=9176 ref_seq=GT diff --git a/tests/gdtools_annotate_2/expected.gd b/tests/gdtools_annotate_2/expected.gd index 2c87829c..00c0138b 100644 --- a/tests/gdtools_annotate_2/expected.gd +++ b/tests/gdtools_annotate_2/expected.gd @@ -15,7 +15,7 @@ SNP 12 . NC_001416-4 7356 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_s SNP 13 . NC_001416-4 7361 A aa_new_seq=E aa_position=66 aa_ref_seq=A codon_new_seq=GAA codon_number=66 codon_position=2 codon_ref_seq=GCA frequency=0.0550 gene_name=Rz gene_position=197 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz html_gene_name=Rz → html_gene_product=cell lysis protein html_mutation=C→A html_mutation_annotation=A66E (GCA→GAA)  html_position=7,361 html_seq_id=NC_001416‑4 locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7361 position_start=7361 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 14 . NC_001416-4 7384 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=0.0870 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz html_gene_name=Rz → html_gene_product=cell lysis protein html_mutation=G→A html_mutation_annotation=D74N (GAT→AAT)  html_position=7,384 html_seq_id=NC_001416‑4 locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7384 position_start=7384 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 15 . NC_001416-4 7389 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=0.1100 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 html_gene_name=Rz →
Rz1 → html_gene_product=cell lysis protein
Rz1 protein html_mutation=T→G html_mutation_annotation=A75A (GCT→GCG) 
L2R (CTA→CGA)  html_position=7,389 html_seq_id=NC_001416‑4 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=7389 position_start=7389 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 16 . NC_001416-4 7629 C frequency=0.2390 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor html_gene_name=Rz → / ← bor html_gene_product=cell lysis protein/Bor protein precursor html_mutation=T→C html_mutation_annotation=intergenic (+3/+29) html_position=7,629 html_seq_id=NC_001416‑4 locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic +SNP 16 . NC_001416-4 7629 C frequency=0.2390 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< html_gene_name=Rz → / ← bor html_gene_product=cell lysis protein/Bor protein precursor html_mutation=T→C html_mutation_annotation=intergenic (+3/+29) html_position=7,629 html_seq_id=NC_001416‑4 locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic SNP 17 . NC_001416-4 7796 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=0.2630 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor html_gene_name=bor ← html_gene_product=Bor protein precursor html_mutation=G→A html_mutation_annotation=V52V (GTC→GTT)  html_position=7,796 html_seq_id=NC_001416‑4 locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7796 position_start=7796 ref_seq=G snp_type=synonymous transl_table=11 SNP 18 . NC_001416-4 7807 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=0.2100 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor html_gene_name=bor ← html_gene_product=Bor protein precursor html_mutation=T→C html_mutation_annotation=K49E (AAG→GAG)  html_position=7,807 html_seq_id=NC_001416‑4 locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=7807 position_start=7807 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 19 . NC_001416-4 7811 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=0.2090 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor html_gene_name=bor ← html_gene_product=Bor protein precursor html_mutation=C→T html_mutation_annotation=G47G (GGG→GGA)  html_position=7,811 html_seq_id=NC_001416‑4 locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7811 position_start=7811 ref_seq=C snp_type=synonymous transl_table=11 @@ -44,7 +44,7 @@ SNP 41 . NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 42 . NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 html_gene_name=lambdap78 ← html_gene_product=putative envelope protein html_mutation=T→C html_mutation_annotation=T23A (ACG→GCG)  html_position=8,708 html_seq_id=NC_001416‑4 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 43 . NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 html_gene_name=lambdap78 ← html_gene_product=putative envelope protein html_mutation=C→T html_mutation_annotation=R16K (AGG→AAG)  html_position=8,728 html_seq_id=NC_001416‑4 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 44 . NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 html_gene_name=lambdap78 ← html_gene_product=putative envelope protein html_mutation=C→A html_mutation_annotation=M1M (GTG→TTG) † html_position=8,774 html_seq_id=NC_001416‑4 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 45 . NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 html_gene_name=lambdap78 ← / → lambdap79 html_gene_product=putative envelope protein/hypothetical protein html_mutation=T→C html_mutation_annotation=intergenic (‑94/‑69) html_position=8,868 html_seq_id=NC_001416‑4 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 45 . NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 html_gene_name=lambdap78 ← / → lambdap79 html_gene_product=putative envelope protein/hypothetical protein html_mutation=T→C html_mutation_annotation=intergenic (‑94/‑69) html_position=8,868 html_seq_id=NC_001416‑4 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 46 . NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 html_gene_name=lambdap79 → html_gene_product=hypothetical protein html_mutation=A→G html_mutation_annotation=R47R (AGA→AGG)  html_position=9,077 html_seq_id=NC_001416‑4 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 47 . NC_001416-4 9172 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– html_gene_name=lambdap79 → / – html_gene_product=hypothetical protein/– html_mutation=T→C html_mutation_annotation=intergenic (+29/–) html_position=9,172 html_seq_id=NC_001416‑4 locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic SUB 48 . NC_001416-4 9176 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– html_gene_name=lambdap79 → / – html_gene_product=hypothetical protein/– html_mutation=2 bp→AC html_mutation_annotation=intergenic (+33/–) html_position=9,176 html_seq_id=NC_001416‑4 locus_tag=lambdap79/– mutation_category=small_indel position_end=9177 position_start=9176 ref_seq=GT diff --git a/tests/gdtools_annotate_3/expected.json b/tests/gdtools_annotate_3/expected.json index 3a8964db..7a7747f0 100644 --- a/tests/gdtools_annotate_3/expected.json +++ b/tests/gdtools_annotate_3/expected.json @@ -16,12 +16,12 @@ "gene_strand": "–/>", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "", + "genes_promoter": "nu1", "id": "1", "locus_tag": "–/lambdap01", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "", + "locus_tags_promoter": "lambdap01", "mutation_category": "small_indel", "position": "139", "position_end": "139", @@ -828,12 +828,12 @@ "gene_strand": "", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "lambdap78", + "genes_promoter": "lambdap78,lambdap79", "id": "25", "locus_tag": "lambdap78/lambdap79", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "lambdap78", + "locus_tags_promoter": "lambdap78,lambdap79", "mutation_category": "snp_intergenic", "new_seq": "C", "position": "8868", diff --git a/tests/gdtools_compare_1/expected.gd b/tests/gdtools_compare_1/expected.gd index d399a3d4..c8002c23 100644 --- a/tests/gdtools_compare_1/expected.gd +++ b/tests/gdtools_compare_1/expected.gd @@ -1,5 +1,5 @@ #=GENOME_DIFF 1.0 -DEL 63 . NC_001416-0 139 1 frequency=1 frequency_gd=? frequency_gd_1=1 frequency_gd_2=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 63 . NC_001416-0 139 1 frequency=1 frequency_gd=? frequency_gd_1=1 frequency_gd_2=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 1 . NC_001416-1 4566 G frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=0 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=4566 position_start=4566 ref_seq=C SNP 2 . NC_001416-2 1261 G aa_new_seq=E|NA aa_position=338|NA aa_ref_seq=K|NA codon_new_seq=GAA|NA codon_number=338|NA codon_position=1|NA codon_ref_seq=AAA|NA frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=orf-401|orf206b gene_position=1012|noncoding (107/621 nt) gene_product=Tail fiber protein| gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90_made_noncoding locus_tags_overlapping=lambdap27,lambdap90_made_noncoding mutation_category=snp_nonsynonymous|noncoding position_end=1261 position_start=1261 ref_seq=A snp_type=nonsynonymous|noncoding transl_table=11|NA INS 3 . NC_001416-2 1435 C frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=0 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=1435 position_start=1435 ref_seq=C @@ -16,7 +16,7 @@ SNP 12 . NC_001416-4 7356 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_s SNP 13 . NC_001416-4 7361 A aa_new_seq=E aa_position=66 aa_ref_seq=A codon_new_seq=GAA codon_number=66 codon_position=2 codon_ref_seq=GCA frequency=0.0550 frequency_gd=0.0550 frequency_gd_1=0.0550 frequency_gd_2=0.0550 gene_name=Rz gene_position=197 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7361 position_start=7361 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 14 . NC_001416-4 7384 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=0.0870 frequency_gd=0.0870 frequency_gd_1=0.0870 frequency_gd_2=0.0870 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7384 position_start=7384 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 15 . NC_001416-4 7389 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=0.1100 frequency_gd=0.1100 frequency_gd_1=0.1100 frequency_gd_2=0.1100 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=7389 position_start=7389 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 16 . NC_001416-4 7629 C frequency=0.2390 frequency_gd=0.2390 frequency_gd_1=0.2390 frequency_gd_2=0 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic +SNP 16 . NC_001416-4 7629 C frequency=0.2390 frequency_gd=0.2390 frequency_gd_1=0.2390 frequency_gd_2=0 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic SNP 17 . NC_001416-4 7796 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=0.2630 frequency_gd=0.2630 frequency_gd_1=0.2630 frequency_gd_2=0 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7796 position_start=7796 ref_seq=G snp_type=synonymous transl_table=11 SNP 18 . NC_001416-4 7807 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=0.2100 frequency_gd=0.2100 frequency_gd_1=0.2100 frequency_gd_2=0 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=7807 position_start=7807 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 19 . NC_001416-4 7811 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=0.2090 frequency_gd=0.2090 frequency_gd_1=0.2090 frequency_gd_2=0 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7811 position_start=7811 ref_seq=C snp_type=synonymous transl_table=11 @@ -47,7 +47,7 @@ SNP 41 . NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 42 . NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 frequency_gd=1 frequency_gd_1=0 frequency_gd_2=0 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 43 . NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 frequency_gd=1 frequency_gd_1=0 frequency_gd_2=0 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 44 . NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 45 . NC_001416-4 8868 C frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 45 . NC_001416-4 8868 C frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 46 . NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 47 . NC_001416-4 9172 C frequency=1 frequency_gd=1 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic INS 66 . NC_001416-4 9176 AC frequency=1 frequency_gd=0 frequency_gd_1=1 frequency_gd_2=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– insert_position=0 locus_tag=lambdap79/– mutation_category=small_indel position_end=9176 position_start=9176 ref_seq=G diff --git a/tests/gdtools_compare_5/expected.tsv b/tests/gdtools_compare_5/expected.tsv index ad86e7fc..1cdaab5a 100644 --- a/tests/gdtools_compare_5/expected.tsv +++ b/tests/gdtools_compare_5/expected.tsv @@ -14,7 +14,7 @@ L 64 L CTG 64 3 CTC 0.0660 Rz 192 cell lysis protein > Rz lambdap76 lambda E 66 A GAA 66 2 GCA 0.0550 Rz 197 cell lysis protein > Rz lambdap76 lambdap76 snp_nonsynonymous 0 0 A 7361 7361 7361 0 0 C NC_001416-4 nonsynonymous -1 gd 11 SNP N 74 D AAT 74 1 GAT 0.0870 Rz 220 cell lysis protein > Rz lambdap76 lambdap76 snp_nonsynonymous 0 0 A 7384 7384 7384 0 0 G NC_001416-4 nonsynonymous -1 gd 11 SNP A|R 75|2 A|L GCG|CGA 75|2 3|2 GCT|CTA 0.1100 Rz|Rz1 225|5 cell lysis protein|Rz1 protein >|> Rz,Rz1 lambdap76|lambdap91 lambdap76,lambdap91 snp_synonymous|nonsynonymous 0 0 G 7389 7389 7389 0 0 T NC_001416-4 synonymous|nonsynonymous -1 gd 11|11 SNP - 0.2390 Rz/bor intergenic (+3/+29) cell lysis protein/Bor protein precursor >/< bor lambdap76/lambdap77 lambdap77 snp_intergenic 0 0 C 7629 7629 7629 0 0 T NC_001416-4 intergenic -1 gd SNP + 0.2390 Rz/bor intergenic (+3/+29) cell lysis protein/Bor protein precursor >/< lambdap76/lambdap77 snp_intergenic 0 0 C 7629 7629 7629 0 0 T NC_001416-4 intergenic -1 gd SNP V 52 V GTT 52 3 GTC 0.2630 bor 156 Bor protein precursor < bor lambdap77 lambdap77 snp_synonymous 0 0 A 7796 7796 7796 0 0 G NC_001416-4 synonymous -1 gd 11 SNP E 49 K GAG 49 1 AAG 0.2100 bor 145 Bor protein precursor < bor lambdap77 lambdap77 snp_nonsynonymous 0 0 C 7807 7807 7807 0 0 T NC_001416-4 nonsynonymous -1 gd 11 SNP G 47 G GGA 47 3 GGG 0.2090 bor 141 Bor protein precursor < bor lambdap77 lambdap77 snp_synonymous 0 0 T 7811 7811 7811 0 0 C NC_001416-4 synonymous -1 gd 11 SNP @@ -43,7 +43,7 @@ N 60 D AAC 60 1 GAC 1 lambdap78 178 putative envelope protein < lambdap78 l A 23 T GCG 23 1 ACG 1 lambdap78 67 putative envelope protein < lambdap78 lambdap78 lambdap78 snp_nonsynonymous 0 0 C 8708 8708 8708 0 0 T NC_001416-4 nonsynonymous -1 gd 11 SNP K 16 R AAG 16 2 AGG 1 lambdap78 47 putative envelope protein < lambdap78 lambdap78 lambdap78 snp_nonsynonymous 0 0 T 8728 8728 8728 0 0 C NC_001416-4 nonsynonymous -1 gd 11 SNP M 1 M TTG 1 1 GTG 1 lambdap78 1 putative envelope protein < lambdap78 lambdap78 lambdap78 snp_synonymous 0 0 A 8774 8774 8774 0 0 C NC_001416-4 synonymous -1 gd 11 SNP - 1 lambdap78/lambdap79 intergenic (-94/-69) putative envelope protein/hypothetical protein lambdap78 lambdap78/lambdap79 lambdap78 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP + 1 lambdap78/lambdap79 intergenic (-94/-69) putative envelope protein/hypothetical protein lambdap78,lambdap79 lambdap78/lambdap79 lambdap78,lambdap79 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP R 47 R AGG 47 3 AGA 1 lambdap79 141 hypothetical protein > lambdap79 lambdap79 lambdap79 snp_synonymous 0 0 G 9077 9077 9077 0 0 A NC_001416-4 synonymous -1 gd 11 SNP 1 lambdap79/– intergenic (+29/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 C 9172 9172 9172 0 0 T NC_001416-4 intergenic -1 gd SNP 1 lambdap79/– intergenic (+33/–) hypothetical protein/– >/– lambdap79/– small_indel 0 0 AC 9176 9177 9176 0 0 GT NC_001416-4 2 -1 gd SUB @@ -58,7 +58,7 @@ R 47 R AGG 47 3 AGA 1 lambdap79 141 hypothetical protein > lambdap79 lambda 0.0880 lambdap79/– intergenic (+485/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 A 9628 9628 9628 0 0 C NC_001416-4 intergenic -1 gd SNP 0.1120 lambdap79/– intergenic (+486/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 G 9629 9629 9629 0 0 C NC_001416-4 intergenic -1 gd SNP 0.1120 lambdap79/– intergenic (+488/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 T 9631 9631 9631 0 0 C NC_001416-4 intergenic -1 gd SNP - 1 –/nu1 intergenic (–/-52) –/DNA packaging protein –/> –/lambdap01 small_indel 0 0 139 139 139 0 0 G NC_001416-0 1 -1 gd DEL + 1 –/nu1 intergenic (–/-52) –/DNA packaging protein –/> nu1 –/lambdap01 lambdap01 small_indel 0 0 139 139 139 0 0 G NC_001416-0 1 -1 gd DEL 1 L/K intergenic (+139/-10) tail component/tail component >/> K 0 lambdap18/lambdap19 lambdap19 small_indel 0 0 G 4566 4566 4566 0 0 C NC_001416-1 -1 gd INS E|NA 338|NA K|NA GAA|NA 338|NA 1|NA AAA|NA 1 orf-401|orf206b 1012|noncoding (107/621 nt) Tail fiber protein| >|< orf-401,orf206b lambdap27|lambdap90_made_noncoding lambdap27,lambdap90_made_noncoding snp_nonsynonymous|noncoding 0 0 G 1261 1261 1261 0 0 A NC_001416-2 nonsynonymous|noncoding -1 gd 11|NA SNP 1 orf-401 coding (1186/1206 nt) Tail fiber protein > orf-401 0 lambdap27 lambdap27 small_indel 0 0 C 1435 1435 1435 0 0 C NC_001416-2 -1 gd INS @@ -71,7 +71,7 @@ L 64 L CTG 64 3 CTC 0.0660 Rz 192 cell lysis protein > Rz lambdap76 lambda E 66 A GAA 66 2 GCA 0.0550 Rz 197 cell lysis protein > Rz lambdap76 lambdap76 snp_nonsynonymous 0 0 A 7361 7361 7361 0 0 C NC_001416-4 nonsynonymous -1 gd 11 SNP N 74 D AAT 74 1 GAT 0.0870 Rz 220 cell lysis protein > Rz lambdap76 lambdap76 snp_nonsynonymous 0 0 A 7384 7384 7384 0 0 G NC_001416-4 nonsynonymous -1 gd 11 SNP A|R 75|2 A|L GCG|CGA 75|2 3|2 GCT|CTA 0.1100 Rz|Rz1 225|5 cell lysis protein|Rz1 protein >|> Rz,Rz1 lambdap76|lambdap91 lambdap76,lambdap91 snp_synonymous|nonsynonymous 0 0 G 7389 7389 7389 0 0 T NC_001416-4 synonymous|nonsynonymous -1 gd 11|11 SNP - 0.2390 Rz/bor intergenic (+3/+29) cell lysis protein/Bor protein precursor >/< bor lambdap76/lambdap77 lambdap77 snp_intergenic 0 0 C 7629 7629 7629 0 0 T NC_001416-4 intergenic -1 gd SNP + 0.2390 Rz/bor intergenic (+3/+29) cell lysis protein/Bor protein precursor >/< lambdap76/lambdap77 snp_intergenic 0 0 C 7629 7629 7629 0 0 T NC_001416-4 intergenic -1 gd SNP V 52 V GTT 52 3 GTC 0.2630 bor 156 Bor protein precursor < bor lambdap77 lambdap77 snp_synonymous 0 0 A 7796 7796 7796 0 0 G NC_001416-4 synonymous -1 gd 11 SNP E 49 K GAG 49 1 AAG 0.2100 bor 145 Bor protein precursor < bor lambdap77 lambdap77 snp_nonsynonymous 0 0 C 7807 7807 7807 0 0 T NC_001416-4 nonsynonymous -1 gd 11 SNP G 47 G GGA 47 3 GGG 0.2090 bor 141 Bor protein precursor < bor lambdap77 lambdap77 snp_synonymous 0 0 T 7811 7811 7811 0 0 C NC_001416-4 synonymous -1 gd 11 SNP @@ -90,7 +90,7 @@ A 11 A GCA 11 3 GCC 0.0660 bor 33 Bor protein precursor < bor lambdap77 la 1 bor/lambdap78 intergenic (-233/+57) Bor protein precursor/putative envelope protein lambdap78 lambdap78/lambdap79 lambdap78 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP + 1 lambdap78/lambdap79 intergenic (-94/-69) putative envelope protein/hypothetical protein lambdap78,lambdap79 lambdap78/lambdap79 lambdap78,lambdap79 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP R 47 R AGG 47 3 AGA 1 lambdap79 141 hypothetical protein > lambdap79 lambdap79 lambdap79 snp_synonymous 0 0 G 9077 9077 9077 0 0 A NC_001416-4 synonymous -1 gd 11 SNP 1 lambdap79/– intergenic (+29/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 C 9172 9172 9172 0 0 T NC_001416-4 intergenic -1 gd SNP 1 lambdap79/– intergenic (+33/–) hypothetical protein/– >/– 0 lambdap79/– small_indel 0 0 AC 9176 9176 9176 0 0 G NC_001416-4 -1 gd INS @@ -105,7 +105,7 @@ R 47 R AGG 47 3 AGA 1 lambdap79 141 hypothetical protein > lambdap79 lambda 0.0880 lambdap79/– intergenic (+485/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 A 9628 9628 9628 0 0 C NC_001416-4 intergenic -1 gd SNP 0.1120 lambdap79/– intergenic (+486/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 G 9629 9629 9629 0 0 C NC_001416-4 intergenic -1 gd SNP 0.1120 lambdap79/– intergenic (+488/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 T 9631 9631 9631 0 0 C NC_001416-4 intergenic -1 gd SNP - 1 –/nu1 intergenic (–/-52) –/DNA packaging protein –/> –/lambdap01 small_indel 0 0 139 139 139 0 0 G NC_001416-0 1 -1 gd DEL + 1 –/nu1 intergenic (–/-52) –/DNA packaging protein –/> nu1 –/lambdap01 lambdap01 small_indel 0 0 139 139 139 0 0 G NC_001416-0 1 -1 gd DEL 1 L/K intergenic (+139/-10) tail component/tail component >/> K 0 lambdap18/lambdap19 lambdap19 small_indel 0 0 G 4566 4566 4566 0 0 C NC_001416-1 -1 gd INS E|NA 338|NA K|NA GAA|NA 338|NA 1|NA AAA|NA 1 orf-401|orf206b 1012|noncoding (107/621 nt) Tail fiber protein| >|< orf-401,orf206b lambdap27|lambdap90_made_noncoding lambdap27,lambdap90_made_noncoding snp_nonsynonymous|noncoding 0 0 G 1261 1261 1261 0 0 A NC_001416-2 nonsynonymous|noncoding -1 gd 11|NA SNP 1 orf-401 coding (1186/1206 nt) Tail fiber protein > orf-401 0 lambdap27 lambdap27 small_indel 0 0 C 1435 1435 1435 0 0 C NC_001416-2 -1 gd INS @@ -129,7 +129,7 @@ A 11 A GCA 11 3 GCC 0.0660 bor 33 Bor protein precursor < bor lambdap77 la 1 bor/lambdap78 intergenic (-233/+57) Bor protein precursor/putative envelope protein lambdap78 lambdap78/lambdap79 lambdap78 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP + 1 lambdap78/lambdap79 intergenic (-94/-69) putative envelope protein/hypothetical protein lambdap78,lambdap79 lambdap78/lambdap79 lambdap78,lambdap79 snp_intergenic 0 0 C 8868 8868 8868 0 0 T NC_001416-4 intergenic -1 gd SNP R 47 R AGG 47 3 AGA 1 lambdap79 141 hypothetical protein > lambdap79 lambdap79 lambdap79 snp_synonymous 0 0 G 9077 9077 9077 0 0 A NC_001416-4 synonymous -1 gd 11 SNP 1 lambdap79/– intergenic (+29/–) hypothetical protein/– >/– lambdap79/– snp_intergenic 0 0 C 9172 9172 9172 0 0 T NC_001416-4 intergenic -1 gd SNP 1 lambdap79/– intergenic (+33/–) hypothetical protein/– >/– 0 lambdap79/– small_indel 0 0 AC 9176 9176 9176 0 0 G NC_001416-4 -1 gd INS diff --git a/tests/gdtools_compare_8/expected.csv b/tests/gdtools_compare_8/expected.csv index 38a949b3..43cd34c7 100644 --- a/tests/gdtools_compare_8/expected.csv +++ b/tests/gdtools_compare_8/expected.csv @@ -14,7 +14,7 @@ "Rz →","cell lysis protein","C→A","A66E (GCA→GAA)","7361","NC_001416-4","E","66","A","","GAA","66","2","","GCA","0.0550","Rz","197","cell lysis protein",">","","Rz","","","lambdap76","","lambdap76","","","snp_nonsynonymous","","0","0","A","","7361","7361","7361","0","0","C","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "Rz →","cell lysis protein","G→A","D74N (GAT→AAT)","7384","NC_001416-4","N","74","D","","AAT","74","1","","GAT","0.0870","Rz","220","cell lysis protein",">","","Rz","","","lambdap76","","lambdap76","","","snp_nonsynonymous","","0","0","A","","7384","7384","7384","0","0","G","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "Rz →|Rz1 →","cell lysis protein|Rz1 protein","T→G","A75A (GCT→GCG)|L2R (CTA→CGA)","7389","NC_001416-4","A|R","75|2","A|L","","GCG|CGA","75|2","3|2","","GCT|CTA","0.1100","Rz|Rz1","225|5","cell lysis protein|Rz1 protein",">|>","","Rz,Rz1","","","lambdap76|lambdap91","","lambdap76,lambdap91","","","snp_synonymous|nonsynonymous","","0","0","G","","7389","7389","7389","0","0","T","NC_001416-4","","synonymous|nonsynonymous","-1","gd","11|11","","SNP" -"Rz → / ← bor","cell lysis protein/Bor protein precursor","T→C","intergenic (+3/+29)","7629","NC_001416-4","","","","","","","","","","0.2390","Rz/bor","intergenic (+3/+29)","cell lysis protein/Bor protein precursor",">/<","","","bor","","lambdap76/lambdap77","","","lambdap77","","snp_intergenic","","0","0","C","","7629","7629","7629","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" +"Rz → / ← bor","cell lysis protein/Bor protein precursor","T→C","intergenic (+3/+29)","7629","NC_001416-4","","","","","","","","","","0.2390","Rz/bor","intergenic (+3/+29)","cell lysis protein/Bor protein precursor",">/<","","","","","lambdap76/lambdap77","","","","","snp_intergenic","","0","0","C","","7629","7629","7629","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "bor ←","Bor protein precursor","G→A","V52V (GTC→GTT)","7796","NC_001416-4","V","52","V","","GTT","52","3","","GTC","0.2630","bor","156","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_synonymous","","0","0","A","","7796","7796","7796","0","0","G","NC_001416-4","","synonymous","-1","gd","11","","SNP" "bor ←","Bor protein precursor","T→C","K49E (AAG→GAG)","7807","NC_001416-4","E","49","K","","GAG","49","1","","AAG","0.2100","bor","145","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_nonsynonymous","","0","0","C","","7807","7807","7807","0","0","T","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "bor ←","Bor protein precursor","C→T","G47G (GGG→GGA)","7811","NC_001416-4","G","47","G","","GGA","47","3","","GGG","0.2090","bor","141","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_synonymous","","0","0","T","","7811","7811","7811","0","0","C","NC_001416-4","","synonymous","-1","gd","11","","SNP" @@ -43,7 +43,7 @@ "lambdap78 ←","putative envelope protein","T→C","T23A (ACG→GCG)","8708","NC_001416-4","A","23","T","","GCG","23","1","","ACG","1","lambdap78","67","putative envelope protein","<","","lambdap78","","","lambdap78","","lambdap78","","","snp_nonsynonymous","","0","0","C","","8708","8708","8708","0","0","T","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "lambdap78 ←","putative envelope protein","C→T","R16K (AGG→AAG)","8728","NC_001416-4","K","16","R","","AAG","16","2","","AGG","1","lambdap78","47","putative envelope protein","<","","lambdap78","","","lambdap78","","lambdap78","","","snp_nonsynonymous","","0","0","T","","8728","8728","8728","0","0","C","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "lambdap78 ←","putative envelope protein","C→A","M1M (GTG→TTG)†","8774","NC_001416-4","M","1","M","","TTG","1","1","","GTG","1","lambdap78","1","putative envelope protein","<","","lambdap78","","","lambdap78","","lambdap78","","","snp_synonymous","","0","0","A","","8774","8774","8774","0","0","C","NC_001416-4","","synonymous","-1","gd","11","","SNP" -"lambdap78 ← / → lambdap79","putative envelope protein/hypothetical protein","T→C","intergenic (-94/-69)","8868","NC_001416-4","","","","","","","","","","1","lambdap78/lambdap79","intergenic (-94/-69)","putative envelope protein/hypothetical protein","","","","lambdap78","","lambdap78/lambdap79","","","lambdap78","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" +"lambdap78 ← / → lambdap79","putative envelope protein/hypothetical protein","T→C","intergenic (-94/-69)","8868","NC_001416-4","","","","","","","","","","1","lambdap78/lambdap79","intergenic (-94/-69)","putative envelope protein/hypothetical protein","","","","lambdap78,lambdap79","","lambdap78/lambdap79","","","lambdap78,lambdap79","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 →","hypothetical protein","A→G","R47R (AGA→AGG)","9077","NC_001416-4","R","47","R","","AGG","47","3","","AGA","1","lambdap79","141","hypothetical protein",">","","lambdap79","","","lambdap79","","lambdap79","","","snp_synonymous","","0","0","G","","9077","9077","9077","0","0","A","NC_001416-4","","synonymous","-1","gd","11","","SNP" "lambdap79 → / –","hypothetical protein/–","T→C","intergenic (+29/–)","9172","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+29/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","C","","9172","9172","9172","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","2 bp →AC","intergenic (+33/–)","9176","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+33/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","small_indel","","0","0","AC","","9176","9177","9176","0","0","GT","NC_001416-4","2","","-1","gd","","","SUB" @@ -58,7 +58,7 @@ "lambdap79 → / –","hypothetical protein/–","C→A","intergenic (+485/–)","9628","NC_001416-4","","","","","","","","","","0.0880","lambdap79/–","intergenic (+485/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","A","","9628","9628","9628","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","C→G","intergenic (+486/–)","9629","NC_001416-4","","","","","","","","","","0.1120","lambdap79/–","intergenic (+486/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","G","","9629","9629","9629","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","C→T","intergenic (+488/–)","9631","NC_001416-4","","","","","","","","","","0.1120","lambdap79/–","intergenic (+488/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","T","","9631","9631","9631","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" -"– / → nu1","–/DNA packaging protein","Δ1 bp","intergenic (–/-52)","139","NC_001416-0","","","","","","","","","","1","–/nu1","intergenic (–/-52)","–/DNA packaging protein","–/>","","","","","–/lambdap01","","","","","small_indel","","0","0","","","139","139","139","0","0","G","NC_001416-0","1","","-1","gd","","","DEL" +"– / → nu1","–/DNA packaging protein","Δ1 bp","intergenic (–/-52)","139","NC_001416-0","","","","","","","","","","1","–/nu1","intergenic (–/-52)","–/DNA packaging protein","–/>","","","nu1","","–/lambdap01","","","lambdap01","","small_indel","","0","0","","","139","139","139","0","0","G","NC_001416-0","1","","-1","gd","","","DEL" "L → / → K","tail component/tail component","​+G","intergenic (+139/-10)","4566","NC_001416-1","","","","","","","","","","1","L/K","intergenic (+139/-10)","tail component/tail component",">/>","","","K","0","lambdap18/lambdap19","","","lambdap19","","small_indel","","0","0","G","","4566","4566","4566","0","0","C","NC_001416-1","","","-1","gd","","","INS" "orf-401 →|orf206b ←","Tail fiber protein|","A→G","K338E (AAA→GAA)|noncoding (107/621 nt)","1261","NC_001416-2","E|NA","338|NA","K|NA","","GAA|NA","338|NA","1|NA","","AAA|NA","1","orf-401|orf206b","1012|noncoding (107/621 nt)","Tail fiber protein|",">|<","","orf-401,orf206b","","","lambdap27|lambdap90_made_noncoding","","lambdap27,lambdap90_made_noncoding","","","snp_nonsynonymous|noncoding","","0","0","G","","1261","1261","1261","0","0","A","NC_001416-2","","nonsynonymous|noncoding","-1","gd","11|NA","","SNP" "orf-401 →","Tail fiber protein","​+C","coding (1186/1206 nt)","1435","NC_001416-2","","","","","","","","","","1","orf-401","coding (1186/1206 nt)","Tail fiber protein",">","","orf-401","","0","lambdap27","","lambdap27","","","small_indel","","0","0","C","","1435","1435","1435","0","0","C","NC_001416-2","","","-1","gd","","","INS" @@ -71,7 +71,7 @@ "Rz →","cell lysis protein","C→A","A66E (GCA→GAA)","7361","NC_001416-4","E","66","A","","GAA","66","2","","GCA","0.0550","Rz","197","cell lysis protein",">","","Rz","","","lambdap76","","lambdap76","","","snp_nonsynonymous","","0","0","A","","7361","7361","7361","0","0","C","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "Rz →","cell lysis protein","G→A","D74N (GAT→AAT)","7384","NC_001416-4","N","74","D","","AAT","74","1","","GAT","0.0870","Rz","220","cell lysis protein",">","","Rz","","","lambdap76","","lambdap76","","","snp_nonsynonymous","","0","0","A","","7384","7384","7384","0","0","G","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "Rz →|Rz1 →","cell lysis protein|Rz1 protein","T→G","A75A (GCT→GCG)|L2R (CTA→CGA)","7389","NC_001416-4","A|R","75|2","A|L","","GCG|CGA","75|2","3|2","","GCT|CTA","0.1100","Rz|Rz1","225|5","cell lysis protein|Rz1 protein",">|>","","Rz,Rz1","","","lambdap76|lambdap91","","lambdap76,lambdap91","","","snp_synonymous|nonsynonymous","","0","0","G","","7389","7389","7389","0","0","T","NC_001416-4","","synonymous|nonsynonymous","-1","gd","11|11","","SNP" -"Rz → / ← bor","cell lysis protein/Bor protein precursor","T→C","intergenic (+3/+29)","7629","NC_001416-4","","","","","","","","","","0.2390","Rz/bor","intergenic (+3/+29)","cell lysis protein/Bor protein precursor",">/<","","","bor","","lambdap76/lambdap77","","","lambdap77","","snp_intergenic","","0","0","C","","7629","7629","7629","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" +"Rz → / ← bor","cell lysis protein/Bor protein precursor","T→C","intergenic (+3/+29)","7629","NC_001416-4","","","","","","","","","","0.2390","Rz/bor","intergenic (+3/+29)","cell lysis protein/Bor protein precursor",">/<","","","","","lambdap76/lambdap77","","","","","snp_intergenic","","0","0","C","","7629","7629","7629","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "bor ←","Bor protein precursor","G→A","V52V (GTC→GTT)","7796","NC_001416-4","V","52","V","","GTT","52","3","","GTC","0.2630","bor","156","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_synonymous","","0","0","A","","7796","7796","7796","0","0","G","NC_001416-4","","synonymous","-1","gd","11","","SNP" "bor ←","Bor protein precursor","T→C","K49E (AAG→GAG)","7807","NC_001416-4","E","49","K","","GAG","49","1","","AAG","0.2100","bor","145","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_nonsynonymous","","0","0","C","","7807","7807","7807","0","0","T","NC_001416-4","","nonsynonymous","-1","gd","11","","SNP" "bor ←","Bor protein precursor","C→T","G47G (GGG→GGA)","7811","NC_001416-4","G","47","G","","GGA","47","3","","GGG","0.2090","bor","141","Bor protein precursor","<","","bor","","","lambdap77","","lambdap77","","","snp_synonymous","","0","0","T","","7811","7811","7811","0","0","C","NC_001416-4","","synonymous","-1","gd","11","","SNP" @@ -90,7 +90,7 @@ "bor ← / ← lambdap78","Bor protein precursor/putative envelope protein","C→T","intergenic (-233/+57)","8184","NC_001416-4","","","","","","","","","","1","bor/lambdap78","intergenic (-233/+57)","Bor protein precursor/putative envelope protein","","","","lambdap78","","lambdap78/lambdap79","","","lambdap78","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" +"lambdap78 ← / → lambdap79","putative envelope protein/hypothetical protein","T→C","intergenic (-94/-69)","8868","NC_001416-4","","","","","","","","","","1","lambdap78/lambdap79","intergenic (-94/-69)","putative envelope protein/hypothetical protein","","","","lambdap78,lambdap79","","lambdap78/lambdap79","","","lambdap78,lambdap79","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 →","hypothetical protein","A→G","R47R (AGA→AGG)","9077","NC_001416-4","R","47","R","","AGG","47","3","","AGA","1","lambdap79","141","hypothetical protein",">","","lambdap79","","","lambdap79","","lambdap79","","","snp_synonymous","","0","0","G","","9077","9077","9077","0","0","A","NC_001416-4","","synonymous","-1","gd","11","","SNP" "lambdap79 → / –","hypothetical protein/–","T→C","intergenic (+29/–)","9172","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+29/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","C","","9172","9172","9172","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","​+AC","intergenic (+33/–)","9176","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+33/–)","hypothetical protein/–",">/–","","","","0","lambdap79/–","","","","","small_indel","","0","0","AC","","9176","9176","9176","0","0","G","NC_001416-4","","","-1","gd","","","INS" @@ -105,7 +105,7 @@ "lambdap79 → / –","hypothetical protein/–","C→A","intergenic (+485/–)","9628","NC_001416-4","","","","","","","","","","0.0880","lambdap79/–","intergenic (+485/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","A","","9628","9628","9628","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","C→G","intergenic (+486/–)","9629","NC_001416-4","","","","","","","","","","0.1120","lambdap79/–","intergenic (+486/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","G","","9629","9629","9629","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","C→T","intergenic (+488/–)","9631","NC_001416-4","","","","","","","","","","0.1120","lambdap79/–","intergenic (+488/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","T","","9631","9631","9631","0","0","C","NC_001416-4","","intergenic","-1","gd","","","SNP" -"– / → nu1","–/DNA packaging protein","Δ1 bp","intergenic (–/-52)","139","NC_001416-0","","","","","","","","","","1","–/nu1","intergenic (–/-52)","–/DNA packaging protein","–/>","","","","","–/lambdap01","","","","","small_indel","","0","0","","","139","139","139","0","0","G","NC_001416-0","1","","-1","gd","","","DEL" +"– / → nu1","–/DNA packaging protein","Δ1 bp","intergenic (–/-52)","139","NC_001416-0","","","","","","","","","","1","–/nu1","intergenic (–/-52)","–/DNA packaging protein","–/>","","","nu1","","–/lambdap01","","","lambdap01","","small_indel","","0","0","","","139","139","139","0","0","G","NC_001416-0","1","","-1","gd","","","DEL" "L → / → K","tail component/tail component","​+G","intergenic (+139/-10)","4566","NC_001416-1","","","","","","","","","","1","L/K","intergenic (+139/-10)","tail component/tail component",">/>","","","K","0","lambdap18/lambdap19","","","lambdap19","","small_indel","","0","0","G","","4566","4566","4566","0","0","C","NC_001416-1","","","-1","gd","","","INS" "orf-401 →|orf206b ←","Tail fiber protein|","A→G","K338E (AAA→GAA)|noncoding (107/621 nt)","1261","NC_001416-2","E|NA","338|NA","K|NA","","GAA|NA","338|NA","1|NA","","AAA|NA","1","orf-401|orf206b","1012|noncoding (107/621 nt)","Tail fiber protein|",">|<","","orf-401,orf206b","","","lambdap27|lambdap90_made_noncoding","","lambdap27,lambdap90_made_noncoding","","","snp_nonsynonymous|noncoding","","0","0","G","","1261","1261","1261","0","0","A","NC_001416-2","","nonsynonymous|noncoding","-1","gd","11|NA","","SNP" "orf-401 →","Tail fiber protein","​+C","coding (1186/1206 nt)","1435","NC_001416-2","","","","","","","","","","1","orf-401","coding (1186/1206 nt)","Tail fiber protein",">","","orf-401","","0","lambdap27","","lambdap27","","","small_indel","","0","0","C","","1435","1435","1435","0","0","C","NC_001416-2","","","-1","gd","","","INS" @@ -129,7 +129,7 @@ "bor ← / ← lambdap78","Bor protein precursor/putative envelope protein","C→T","intergenic (-233/+57)","8184","NC_001416-4","","","","","","","","","","1","bor/lambdap78","intergenic (-233/+57)","Bor protein precursor/putative envelope protein","","","","lambdap78","","lambdap78/lambdap79","","","lambdap78","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" +"lambdap78 ← / → lambdap79","putative envelope protein/hypothetical protein","T→C","intergenic (-94/-69)","8868","NC_001416-4","","","","","","","","","","1","lambdap78/lambdap79","intergenic (-94/-69)","putative envelope protein/hypothetical protein","","","","lambdap78,lambdap79","","lambdap78/lambdap79","","","lambdap78,lambdap79","","snp_intergenic","","0","0","C","","8868","8868","8868","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 →","hypothetical protein","A→G","R47R (AGA→AGG)","9077","NC_001416-4","R","47","R","","AGG","47","3","","AGA","1","lambdap79","141","hypothetical protein",">","","lambdap79","","","lambdap79","","lambdap79","","","snp_synonymous","","0","0","G","","9077","9077","9077","0","0","A","NC_001416-4","","synonymous","-1","gd","11","","SNP" "lambdap79 → / –","hypothetical protein/–","T→C","intergenic (+29/–)","9172","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+29/–)","hypothetical protein/–",">/–","","","","","lambdap79/–","","","","","snp_intergenic","","0","0","C","","9172","9172","9172","0","0","T","NC_001416-4","","intergenic","-1","gd","","","SNP" "lambdap79 → / –","hypothetical protein/–","​+AC","intergenic (+33/–)","9176","NC_001416-4","","","","","","","","","","1","lambdap79/–","intergenic (+33/–)","hypothetical protein/–",">/–","","","","0","lambdap79/–","","","","","small_indel","","0","0","AC","","9176","9176","9176","0","0","G","NC_001416-4","","","-1","gd","","","INS" diff --git a/tests/gdtools_convert_1/expected.json b/tests/gdtools_convert_1/expected.json index a6f49bfc..46b95eef 100644 --- a/tests/gdtools_convert_1/expected.json +++ b/tests/gdtools_convert_1/expected.json @@ -555,12 +555,12 @@ "gene_strand": ">/<", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "bor", + "genes_promoter": "", "id": "17", "locus_tag": "lambdap76/lambdap77", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "lambdap77", + "locus_tags_promoter": "", "mutation_category": "snp_intergenic", "new_seq": "C", "position": "7629", @@ -1574,12 +1574,12 @@ "gene_strand": "", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "lambdap78", + "genes_promoter": "lambdap78,lambdap79", "id": "46", "locus_tag": "lambdap78/lambdap79", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "lambdap78", + "locus_tags_promoter": "lambdap78,lambdap79", "mutation_category": "snp_intergenic", "new_seq": "C", "position": "8868", diff --git a/tests/gdtools_convert_2/expected.json b/tests/gdtools_convert_2/expected.json index fc3e7b01..5b4fdd5a 100644 --- a/tests/gdtools_convert_2/expected.json +++ b/tests/gdtools_convert_2/expected.json @@ -119,12 +119,12 @@ "gene_strand": ">/<", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "mltD", + "genes_promoter": "", "id": "4", "locus_tag": "ECB_00203/ECB_00204", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "ECB_00204", + "locus_tags_promoter": "", "mutation_category": "mobile_element_insertion", "position": "4000", "position_end": "4006", @@ -776,14 +776,14 @@ "gene_strand": ">/<", "genes_inactivated": "", "genes_overlapping": "", - "genes_promoter": "yagP", + "genes_promoter": "", "id": "22", "ins_end": "GC", "ins_start": "ATGGC", "locus_tag": "ECB_t00005/ECB_00241", "locus_tags_inactivated": "", "locus_tags_overlapping": "", - "locus_tags_promoter": "ECB_00241", + "locus_tags_promoter": "", "mutation_category": "mobile_element_insertion", "position": "36000", "position_end": "36006", diff --git a/tests/lambda_contig_ref/expected.gd b/tests/lambda_contig_ref/expected.gd index dbd98d2d..c605646b 100644 --- a/tests/lambda_contig_ref/expected.gd +++ b/tests/lambda_contig_ref/expected.gd @@ -8,7 +8,7 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4939668 #=MAPPED-READS 142258 -DEL 1 29 NC_001416-0 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 29 NC_001416-0 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 30 NC_001416-1 4566 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=4566 position_start=4566 ref_seq=C SNP 3 31 NC_001416-2 1261 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=K|F codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=AAA|TTT gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=1261 position_start=1261 ref_seq=A snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 32 NC_001416-2 1435 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=1435 position_start=1435 ref_seq=C @@ -31,7 +31,7 @@ SNP 20 50 NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_ SNP 21 51 NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 22 52 NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 23 53 NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 24 54 NC_001416-4 8868 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 24 54 NC_001416-4 8868 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 25 55 NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 26 56 NC_001416-4 9172 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic SUB 27 57,58 NC_001416-4 9176 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=9177 position_start=9176 ref_seq=GT diff --git a/tests/lambda_mixed_pop/expected.gd b/tests/lambda_mixed_pop/expected.gd index 07e28f70..db3f4082 100644 --- a/tests/lambda_mixed_pop/expected.gd +++ b/tests/lambda_mixed_pop/expected.gd @@ -12,7 +12,7 @@ #=MAPPED-READS 142716 #=ORIGINAL-BASES 536 #=ORIGINAL-READS 100 -DEL 1 30 NC_001416.1 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 30 NC_001416.1 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 31 NC_001416.1 14266 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 32 NC_001416.1 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 33 NC_001416.1 20835 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -36,7 +36,7 @@ SNP 21 52 NC_001416.1 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new SNP 22 53 NC_001416.1 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 23 54 NC_001416.1 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 24 55 NC_001416.1 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 25 56 NC_001416.1 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 25 56 NC_001416.1 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 26 57 NC_001416.1 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 27 58 NC_001416.1 47973 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 28 59,60 NC_001416.1 47977 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_mixed_pop_bad_contigs/expected.gd b/tests/lambda_mixed_pop_bad_contigs/expected.gd index da6a3af5..6d39d612 100644 --- a/tests/lambda_mixed_pop_bad_contigs/expected.gd +++ b/tests/lambda_mixed_pop_bad_contigs/expected.gd @@ -11,7 +11,7 @@ #=MAPPED-BASES 4971007 #=MAPPED-READS 143162 DEL 1 64 AF322221 1 687 gene_name=GFP gene_position=coding (1-687/687 nt) gene_product=green fluorescent protein asFP499 gene_strand=> genes_inactivated=GFP mutation_category=large_deletion position_end=687 position_start=1 ref_seq=687-bp -DEL 2 32 NC_001416 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 2 32 NC_001416 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 3 33 NC_001416 14266 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 4 34 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 5 35 NC_001416 20835 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -35,7 +35,7 @@ SNP 22 54 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 23 55 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 24 56 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 25 57 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 26 58 NC_001416 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 26 58 NC_001416 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 27 59 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 28 60 NC_001416 47973 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 29 61,62 NC_001416 47977 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_mixed_pop_custom_bowtie2/expected.gd b/tests/lambda_mixed_pop_custom_bowtie2/expected.gd index 8037f47a..185c44f7 100644 --- a/tests/lambda_mixed_pop_custom_bowtie2/expected.gd +++ b/tests/lambda_mixed_pop_custom_bowtie2/expected.gd @@ -8,7 +8,7 @@ #=INPUT-READS 200010 #=MAPPED-BASES 5030671 #=MAPPED-READS 144678 -DEL 1 28 NC_001416 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 28 NC_001416 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 29 NC_001416 14266 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 30 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 31 NC_001416 20835 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -31,7 +31,7 @@ SNP 20 49 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 21 50 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 22 51 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 23 52 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 24 53 NC_001416 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 24 53 NC_001416 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 25 54 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 26 55 NC_001416 47973 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 27 56,57 NC_001416 47977 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_mixed_pop_names_with_spaces/expected.gd b/tests/lambda_mixed_pop_names_with_spaces/expected.gd index 9126da1f..34fab3fe 100644 --- a/tests/lambda_mixed_pop_names_with_spaces/expected.gd +++ b/tests/lambda_mixed_pop_names_with_spaces/expected.gd @@ -12,7 +12,7 @@ #=MAPPED-READS 142716 #=ORIGINAL-BASES 536 #=ORIGINAL-READS 100 -DEL 1 30 NC_001416.1 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 30 NC_001416.1 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 31 NC_001416.1 14266 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 32 NC_001416.1 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 33 NC_001416.1 20835 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -36,7 +36,7 @@ SNP 21 52 NC_001416.1 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new SNP 22 53 NC_001416.1 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 23 54 NC_001416.1 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 24 55 NC_001416.1 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 25 56 NC_001416.1 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 25 56 NC_001416.1 47669 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 26 57 NC_001416.1 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 27 58 NC_001416.1 47973 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 28 59,60 NC_001416.1 47977 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_mult_ref_read/expected.gd b/tests/lambda_mult_ref_read/expected.gd index eb83d565..e853651d 100644 --- a/tests/lambda_mult_ref_read/expected.gd +++ b/tests/lambda_mult_ref_read/expected.gd @@ -14,7 +14,7 @@ #=INPUT-READS 80004 #=MAPPED-BASES 1738646 #=MAPPED-READS 50026 -DEL 1 29 NC_001416-0 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 29 NC_001416-0 139 1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 30 NC_001416-1 4566 G gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=4566 position_start=4566 ref_seq=C SNP 3 31 NC_001416-2 1261 G aa_new_seq=E|NA aa_position=338|NA aa_ref_seq=K|NA codon_new_seq=GAA|NA codon_number=338|NA codon_position=1|NA codon_ref_seq=AAA|NA gene_name=orf-401|orf206b gene_position=1012|noncoding (107/621 nt) gene_product=Tail fiber protein|orf206b gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90_made_noncoding locus_tags_overlapping=lambdap27,lambdap90_made_noncoding mutation_category=snp_nonsynonymous|noncoding position_end=1261 position_start=1261 ref_seq=A snp_type=nonsynonymous|noncoding transl_table=11|NA INS 4 32 NC_001416-2 1435 C gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=1435 position_start=1435 ref_seq=C @@ -37,7 +37,7 @@ SNP 20 47 NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_ SNP 21 48 NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 22 49 NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 23 50 NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 24 51 NC_001416-4 8868 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 24 51 NC_001416-4 8868 C gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 25 52 NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 26 53 NC_001416-4 9172 C gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic SUB 27 54,55 NC_001416-4 9176 2 AC gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=9177 position_start=9176 ref_seq=GT diff --git a/tests/lambda_mult_ref_read_polymorphism/expected.gd b/tests/lambda_mult_ref_read_polymorphism/expected.gd index 283129f4..8f92c189 100644 --- a/tests/lambda_mult_ref_read_polymorphism/expected.gd +++ b/tests/lambda_mult_ref_read_polymorphism/expected.gd @@ -15,14 +15,14 @@ #=INPUT-READS 200000 #=MAPPED-BASES 4939668 #=MAPPED-READS 142258 -DEL 1 49 NC_001416-0 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 49 NC_001416-0 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 50 NC_001416-1 4566 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=4566 position_start=4566 ref_seq=C SNP 3 51 NC_001416-2 1261 G aa_new_seq=E|NA aa_position=338|NA aa_ref_seq=K|NA codon_new_seq=GAA|NA codon_number=338|NA codon_position=1|NA codon_ref_seq=AAA|NA frequency=1 gene_name=orf-401|orf206b gene_position=1012|noncoding (107/621 nt) gene_product=Tail fiber protein|orf206b gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90_made_noncoding locus_tags_overlapping=lambdap27,lambdap90_made_noncoding mutation_category=snp_nonsynonymous|noncoding position_end=1261 position_start=1261 ref_seq=A snp_type=nonsynonymous|noncoding transl_table=11|NA INS 4 52 NC_001416-2 1435 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=1435 position_start=1435 ref_seq=C SNP 5 53 NC_001416-2 2314 A aa_new_seq=N aa_position=229 aa_ref_seq=S codon_new_seq=AAC codon_number=229 codon_position=2 codon_ref_seq=AGC frequency=1 gene_name=orf-314 gene_position=686 gene_product=Tail fiber gene_strand=> genes_overlapping=orf-314 locus_tag=lambdap28 locus_tags_overlapping=lambdap28 mutation_category=snp_nonsynonymous position_end=2314 position_start=2314 ref_seq=G snp_type=nonsynonymous transl_table=11 DEL 6 98,102 NC_001416-2 2338 5996 frequency=1 gene_name=[orf-314]–ea59 gene_product=[orf-314],orf-194,ea47,ea31,ea59 genes_inactivated=orf-314,orf-194,ea47,ea31,ea59 locus_tag=[lambdap28]–[lambdap82] locus_tags_inactivated=lambdap28,lambdap29,lambdap80,lambdap81,lambdap82 mutation_category=large_deletion position_end=8333 position_start=2338 ref_seq=5996-bp SNP 7 54 NC_001416-3 1915 C frequency=1 gene_name=orf61|orf63 gene_position=pseudogene (9/186 nt)|noncoding (181/192 nt) gene_product=hypothetical protein|hypothetical protein gene_strand=<|< genes_overlapping=orf61,orf63 locus_tag=lambdap37_made_noncoding|lambdap38_made_noncoding locus_tags_overlapping=lambdap37_made_noncoding,lambdap38_made_noncoding mutation_category=snp_pseudogene|noncoding position_end=1915 position_start=1915 ref_seq=T snp_type=pseudogene|noncoding -SNP 8 55 NC_001416-3 5327 G frequency=1.03496552e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47 mutation_category=snp_intergenic position_end=5327 position_start=5327 ref_seq=T snp_type=intergenic +SNP 8 55 NC_001416-3 5327 G frequency=1.03496552e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28,lambdap48 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47,lambdap48 mutation_category=snp_intergenic position_end=5327 position_start=5327 ref_seq=T snp_type=intergenic SNP 9 56 NC_001416-3 5833 G aa_new_seq=G aa_position=151 aa_ref_seq=G codon_new_seq=GGG codon_number=151 codon_position=3 codon_ref_seq=GGA frequency=1 gene_name=lambdap48 gene_position=453 gene_product=Superinfection exclusion protein B gene_strand=> genes_overlapping=lambdap48 locus_tag=lambdap48 locus_tags_overlapping=lambdap48 mutation_category=snp_synonymous position_end=5833 position_start=5833 ref_seq=A snp_type=synonymous transl_table=11 DEL 10 57 NC_001416-3 8717 1 frequency=1 gene_name=cI gene_position=coding (123/714 nt) gene_product=repressor gene_strand=< genes_inactivated=cI locus_tag=lambdap88 locus_tags_inactivated=lambdap88 mutation_category=small_indel position_end=8717 position_start=8717 ref_seq=C SNP 11 58 NC_001416-4 6817 C aa_new_seq=F aa_position=42 aa_ref_seq=F codon_new_seq=TTC codon_number=42 codon_position=3 codon_ref_seq=TTT frequency=1 gene_name=R gene_position=126 gene_product=endolysin gene_strand=> genes_overlapping=R locus_tag=lambdap75 locus_tags_overlapping=lambdap75 mutation_category=snp_synonymous position_end=6817 position_start=6817 ref_seq=T snp_type=synonymous transl_table=11 @@ -31,7 +31,7 @@ SNP 13 60 NC_001416-4 7353 A aa_new_seq=A aa_position=63 aa_ref_seq=A codon_new_ SNP 14 61 NC_001416-4 7356 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_seq=CTG codon_number=64 codon_position=3 codon_ref_seq=CTC frequency=6.45499229e-02 gene_name=Rz gene_position=192 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_synonymous position_end=7356 position_start=7356 ref_seq=C snp_type=synonymous transl_table=11 SNP 15 62 NC_001416-4 7384 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=8.00719261e-02 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=7384 position_start=7384 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 16 63 NC_001416-4 7389 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=9.26356316e-02 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=7389 position_start=7389 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 17 64 NC_001416-4 7629 C frequency=2.10496902e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic +SNP 17 64 NC_001416-4 7629 C frequency=2.10496902e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=7629 position_start=7629 ref_seq=T snp_type=intergenic SNP 18 65 NC_001416-4 7796 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=2.39160538e-01 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7796 position_start=7796 ref_seq=G snp_type=synonymous transl_table=11 SNP 19 66 NC_001416-4 7807 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=1.96143150e-01 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=7807 position_start=7807 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 20 67 NC_001416-4 7811 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=1.53741837e-01 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=7811 position_start=7811 ref_seq=C snp_type=synonymous transl_table=11 @@ -57,7 +57,7 @@ SNP 39 86 NC_001416-4 8597 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_ SNP 40 87 NC_001416-4 8708 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8708 position_start=8708 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 41 88 NC_001416-4 8728 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=8728 position_start=8728 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 42 89 NC_001416-4 8774 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=8774 position_start=8774 ref_seq=C snp_type=synonymous transl_table=11 -SNP 43 90 NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic +SNP 43 90 NC_001416-4 8868 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=8868 position_start=8868 ref_seq=T snp_type=intergenic SNP 44 91 NC_001416-4 9077 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=9077 position_start=9077 ref_seq=A snp_type=synonymous transl_table=11 SNP 45 92 NC_001416-4 9172 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=9172 position_start=9172 ref_seq=T snp_type=intergenic SUB 46 93,94 NC_001416-4 9176 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=9177 position_start=9176 ref_seq=GT diff --git a/tests/lambda_polymorphism/expected.gd b/tests/lambda_polymorphism/expected.gd index 67345f98..84e57992 100644 --- a/tests/lambda_polymorphism/expected.gd +++ b/tests/lambda_polymorphism/expected.gd @@ -10,14 +10,14 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4955561 #=MAPPED-READS 142716 -DEL 1 50 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 50 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 51 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 52 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 53 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C SNP 5 54 NC_001416 21714 A aa_new_seq=N aa_position=229 aa_ref_seq=S codon_new_seq=AAC codon_number=229 codon_position=2 codon_ref_seq=AGC frequency=1 gene_name=orf-314 gene_position=686 gene_product=Tail fiber gene_strand=> genes_overlapping=orf-314 locus_tag=lambdap28 locus_tags_overlapping=lambdap28 mutation_category=snp_nonsynonymous position_end=21714 position_start=21714 ref_seq=G snp_type=nonsynonymous transl_table=11 DEL 6 100,102 NC_001416 21738 5996 frequency=1 gene_name=[orf-314]–ea59 gene_product=[orf-314],orf-194,ea47,ea31,ea59 genes_inactivated=orf-314,orf-194,ea47,ea31,ea59 locus_tag=[lambdap28]–[lambdap82] locus_tags_inactivated=lambdap28,lambdap29,lambdap80,lambdap81,lambdap82 mutation_category=large_deletion position_end=27733 position_start=21738 ref_seq=5996-bp SNP 7 55 NC_001416 31016 C aa_new_seq=E|D aa_position=3|61 aa_ref_seq=E|N codon_new_seq=GAG|GAC codon_number=3|61 codon_position=3|1 codon_ref_seq=GAA|AAC frequency=1 gene_name=orf61|orf63 gene_position=9|181 gene_product=hypothetical protein|hypothetical protein gene_strand=<|< genes_overlapping=orf61,orf63 locus_tag=lambdap37|lambdap38 locus_tags_overlapping=lambdap37,lambdap38 mutation_category=snp_synonymous|nonsynonymous position_end=31016 position_start=31016 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 8 56 NC_001416 34428 G frequency=1.05375290e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic +SNP 8 56 NC_001416 34428 G frequency=1.05375290e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28,lambdap48 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47,lambdap48 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic SNP 9 57 NC_001416 34934 G aa_new_seq=G aa_position=151 aa_ref_seq=G codon_new_seq=GGG codon_number=151 codon_position=3 codon_ref_seq=GGA frequency=1 gene_name=lambdap48 gene_position=453 gene_product=Superinfection exclusion protein B gene_strand=> genes_overlapping=lambdap48 locus_tag=lambdap48 locus_tags_overlapping=lambdap48 mutation_category=snp_synonymous position_end=34934 position_start=34934 ref_seq=A snp_type=synonymous transl_table=11 DEL 10 58 NC_001416 37818 1 frequency=1 gene_name=cI gene_position=coding (123/714 nt) gene_product=repressor gene_strand=< genes_inactivated=cI locus_tag=lambdap88 locus_tags_inactivated=lambdap88 mutation_category=small_indel position_end=37818 position_start=37818 ref_seq=C SNP 11 59 NC_001416 45618 C aa_new_seq=F aa_position=42 aa_ref_seq=F codon_new_seq=TTC codon_number=42 codon_position=3 codon_ref_seq=TTT frequency=1 gene_name=R gene_position=126 gene_product=endolysin gene_strand=> genes_overlapping=R locus_tag=lambdap75 locus_tags_overlapping=lambdap75 mutation_category=snp_synonymous position_end=45618 position_start=45618 ref_seq=T snp_type=synonymous transl_table=11 @@ -26,7 +26,7 @@ SNP 13 61 NC_001416 46154 A aa_new_seq=A aa_position=63 aa_ref_seq=A codon_new_s SNP 14 62 NC_001416 46157 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_seq=CTG codon_number=64 codon_position=3 codon_ref_seq=CTC frequency=6.40873909e-02 gene_name=Rz gene_position=192 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_synonymous position_end=46157 position_start=46157 ref_seq=C snp_type=synonymous transl_table=11 SNP 15 63 NC_001416 46185 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=8.00681114e-02 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=46185 position_start=46185 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 16 64 NC_001416 46190 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=9.29918289e-02 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=46190 position_start=46190 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 17 65 NC_001416 46430 C frequency=2.10921288e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic +SNP 17 65 NC_001416 46430 C frequency=2.10921288e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic SNP 18 66 NC_001416 46597 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=2.37744331e-01 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46597 position_start=46597 ref_seq=G snp_type=synonymous transl_table=11 SNP 19 67 NC_001416 46608 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=1.97285175e-01 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=46608 position_start=46608 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 20 68 NC_001416 46612 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=1.53755665e-01 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46612 position_start=46612 ref_seq=C snp_type=synonymous transl_table=11 @@ -53,7 +53,7 @@ SNP 40 88 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 41 89 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 42 90 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 43 91 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 44 92 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 44 92 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 45 93 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 46 94 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 47 95,96 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_polymorphism_aligned_sam/expected.gd b/tests/lambda_polymorphism_aligned_sam/expected.gd index be33a212..4aea8e12 100644 --- a/tests/lambda_polymorphism_aligned_sam/expected.gd +++ b/tests/lambda_polymorphism_aligned_sam/expected.gd @@ -8,7 +8,7 @@ #=INPUT-READS 0 #=MAPPED-BASES 2524732 #=MAPPED-READS 72486 -DEL 1 33 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 33 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 34 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 35 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 36 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -33,7 +33,7 @@ SNP 22 54 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 23 55 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 24 56 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 25 57 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 26 58 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 26 58 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 27 59 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 28 60 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 29 61,62 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_polymorphism_aligned_sam_user_evidence/expected.gd b/tests/lambda_polymorphism_aligned_sam_user_evidence/expected.gd index b9248b6c..2b588b94 100644 --- a/tests/lambda_polymorphism_aligned_sam_user_evidence/expected.gd +++ b/tests/lambda_polymorphism_aligned_sam_user_evidence/expected.gd @@ -8,17 +8,17 @@ #=INPUT-READS 0 #=MAPPED-BASES 2524732 #=MAPPED-READS 72486 -SNP 1 43 NC_001416 54 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-137) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=54 position_start=54 ref_seq=G snp_type=intergenic -SNP 2 44 NC_001416 73 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 3 45 NC_001416 73 G frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 4 46 NC_001416 73 T frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 5 47 NC_001416 75 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-116) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=75 position_start=75 ref_seq=A snp_type=intergenic -SNP 6 48 NC_001416 101 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=101 position_start=101 ref_seq=C snp_type=intergenic -INS 7 49 NC_001416 101 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> insert_position=10 locus_tag=–/lambdap01 mutation_category=small_indel position_end=101 position_start=101 ref_seq=C -SNP 8 50 NC_001416 102 C frequency=1.14761829e-01 gene_name=–/nu1 gene_position=intergenic (–/-89) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=102 position_start=102 ref_seq=T snp_type=intergenic -SNP 9 51 NC_001416 134 A frequency=2.98089981e-02 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=134 position_start=134 ref_seq=G snp_type=intergenic -INS 10 52 NC_001416 134 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> insert_position=1 locus_tag=–/lambdap01 mutation_category=small_indel position_end=134 position_start=134 ref_seq=G -DEL 11 53 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +SNP 1 43 NC_001416 54 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-137) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=54 position_start=54 ref_seq=G snp_type=intergenic +SNP 2 44 NC_001416 73 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 3 45 NC_001416 73 G frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 4 46 NC_001416 73 T frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 5 47 NC_001416 75 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-116) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=75 position_start=75 ref_seq=A snp_type=intergenic +SNP 6 48 NC_001416 101 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=101 position_start=101 ref_seq=C snp_type=intergenic +INS 7 49 NC_001416 101 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 insert_position=10 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=101 position_start=101 ref_seq=C +SNP 8 50 NC_001416 102 C frequency=1.14761829e-01 gene_name=–/nu1 gene_position=intergenic (–/-89) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=102 position_start=102 ref_seq=T snp_type=intergenic +SNP 9 51 NC_001416 134 A frequency=2.98089981e-02 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=134 position_start=134 ref_seq=G snp_type=intergenic +INS 10 52 NC_001416 134 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 insert_position=1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=134 position_start=134 ref_seq=G +DEL 11 53 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 12 54 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 13 55 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 14 56 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -43,7 +43,7 @@ SNP 32 74 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 33 75 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 34 76 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 35 77 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 36 78 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 36 78 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 37 79 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 38 80 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 39 81,82 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_polymorphism_ignore_low_quality/expected.gd b/tests/lambda_polymorphism_ignore_low_quality/expected.gd index 6b14563c..d97e714f 100644 --- a/tests/lambda_polymorphism_ignore_low_quality/expected.gd +++ b/tests/lambda_polymorphism_ignore_low_quality/expected.gd @@ -8,7 +8,7 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4955561 #=MAPPED-READS 142716 -DEL 1 32 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 32 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 33 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 34 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 35 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -18,7 +18,7 @@ SNP 7 37 NC_001416 31016 C aa_new_seq=E|D aa_position=3|61 aa_ref_seq=E|N codon_ SNP 8 38 NC_001416 34934 G aa_new_seq=G aa_position=151 aa_ref_seq=G codon_new_seq=GGG codon_number=151 codon_position=3 codon_ref_seq=GGA frequency=1 gene_name=lambdap48 gene_position=453 gene_product=Superinfection exclusion protein B gene_strand=> genes_overlapping=lambdap48 locus_tag=lambdap48 locus_tags_overlapping=lambdap48 mutation_category=snp_synonymous position_end=34934 position_start=34934 ref_seq=A snp_type=synonymous transl_table=11 DEL 9 39 NC_001416 37818 1 frequency=1 gene_name=cI gene_position=coding (123/714 nt) gene_product=repressor gene_strand=< genes_inactivated=cI locus_tag=lambdap88 locus_tags_inactivated=lambdap88 mutation_category=small_indel position_end=37818 position_start=37818 ref_seq=C SNP 10 40 NC_001416 45618 C aa_new_seq=F aa_position=42 aa_ref_seq=F codon_new_seq=TTC codon_number=42 codon_position=3 codon_ref_seq=TTT frequency=1 gene_name=R gene_position=126 gene_product=endolysin gene_strand=> genes_overlapping=R locus_tag=lambdap75 locus_tags_overlapping=lambdap75 mutation_category=snp_synonymous position_end=45618 position_start=45618 ref_seq=T snp_type=synonymous transl_table=11 -SNP 11 41 NC_001416 46430 C frequency=2.11790562e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic +SNP 11 41 NC_001416 46430 C frequency=2.11790562e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic SNP 12 42 NC_001416 46597 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=2.40274906e-01 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46597 position_start=46597 ref_seq=G snp_type=synonymous transl_table=11 INS 13 43 NC_001416 46957 A frequency=1 gene_name=bor/lambdap78 gene_position=intergenic (-205/+85) gene_product=Bor protein precursor/putative envelope protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 27 57 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 28 58 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 29 59 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 30 60,61 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_polymorphism_mapping_quality_mismatches/expected.gd b/tests/lambda_polymorphism_mapping_quality_mismatches/expected.gd index a80c6d47..d0961f76 100644 --- a/tests/lambda_polymorphism_mapping_quality_mismatches/expected.gd +++ b/tests/lambda_polymorphism_mapping_quality_mismatches/expected.gd @@ -8,7 +8,7 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4240683 #=MAPPED-READS 121295 -DEL 1 26 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 26 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 27 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 28 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 29 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C @@ -29,7 +29,7 @@ SNP 18 43 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 19 44 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 20 45 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 21 46 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 22 47 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 22 47 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 23 48 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 24 49 NC_001416 48160 C frequency=7.66649246e-01 gene_name=lambdap79/– gene_position=intergenic (+216/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=48160 position_start=48160 ref_seq=T snp_type=intergenic SNP 25 50 NC_001416 48295 A frequency=1.05131626e-01 gene_name=lambdap79/– gene_position=intergenic (+351/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=48295 position_start=48295 ref_seq=C snp_type=intergenic diff --git a/tests/lambda_polymorphism_no_junction_bad_orfs/expected.gd b/tests/lambda_polymorphism_no_junction_bad_orfs/expected.gd index 8910c740..bcb72457 100644 --- a/tests/lambda_polymorphism_no_junction_bad_orfs/expected.gd +++ b/tests/lambda_polymorphism_no_junction_bad_orfs/expected.gd @@ -8,13 +8,13 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4956428 #=MAPPED-READS 142742 -DEL 1 49 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +DEL 1 49 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 2 50 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 3 51 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 4 52 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C SNP 5 53 NC_001416 21714 A aa_new_seq=N aa_position=229 aa_ref_seq=S codon_new_seq=AAC codon_number=229 codon_position=2 codon_ref_seq=AGC frequency=1 gene_name=orf-314 gene_position=686 gene_product=Tail fiber gene_strand=> genes_overlapping=orf-314 locus_tag=lambdap28 locus_tags_overlapping=lambdap28 mutation_category=snp_nonsynonymous position_end=21714 position_start=21714 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 6 55 NC_001416 31016 C aa_new_seq=E|D aa_position=3|61 aa_ref_seq=E|N codon_new_seq=GAG|GAC codon_number=3|61 codon_position=3|1 codon_ref_seq=GAA|AAC frequency=1 gene_name=orf61|orf63 gene_position=9|181 gene_product=hypothetical protein|hypothetical protein gene_strand=<|< genes_overlapping=orf61,orf63 locus_tag=lambdap37|lambdap38 locus_tags_overlapping=lambdap37,lambdap38 mutation_category=snp_synonymous|nonsynonymous position_end=31016 position_start=31016 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 7 56 NC_001416 34428 G frequency=1.05371475e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic +SNP 7 56 NC_001416 34428 G frequency=1.05371475e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28,lambdap48 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47,lambdap48 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic SNP 8 57 NC_001416 34934 G aa_new_seq=G aa_position=151 aa_ref_seq=G codon_new_seq=GGG codon_number=151 codon_position=3 codon_ref_seq=GGA frequency=1 gene_name=lambdap48 gene_position=453 gene_product=Superinfection exclusion protein B gene_strand=> genes_overlapping=lambdap48 locus_tag=lambdap48 locus_tags_overlapping=lambdap48 mutation_category=snp_synonymous position_end=34934 position_start=34934 ref_seq=A snp_type=synonymous transl_table=11 DEL 9 58 NC_001416 37818 1 frequency=1 gene_name=cI gene_position=coding (123/714 nt) gene_product=repressor gene_strand=< genes_inactivated=cI locus_tag=lambdap88 locus_tags_inactivated=lambdap88 mutation_category=small_indel position_end=37818 position_start=37818 ref_seq=C SNP 10 59 NC_001416 45618 C aa_new_seq=F aa_position=42 aa_ref_seq=F codon_new_seq=TTC codon_number=42 codon_position=3 codon_ref_seq=TTT frequency=1 gene_name=R gene_position=126 gene_product=endolysin gene_strand=> genes_overlapping=R locus_tag=lambdap75 locus_tags_overlapping=lambdap75 mutation_category=snp_synonymous position_end=45618 position_start=45618 ref_seq=T snp_type=synonymous transl_table=11 @@ -23,7 +23,7 @@ SNP 12 61 NC_001416 46154 A aa_new_seq=A aa_position=63 aa_ref_seq=A codon_new_s SNP 13 62 NC_001416 46157 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_seq=CTG codon_number=64 codon_position=3 codon_ref_seq=CTC frequency=6.40873909e-02 gene_name=Rz gene_position=192 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_synonymous position_end=46157 position_start=46157 ref_seq=C snp_type=synonymous transl_table=11 SNP 14 63 NC_001416 46185 A aa_position=74 codon_number=74 codon_position=1 codon_ref_seq=G frequency=8.00738335e-02 gene_name=Rz gene_position=coding (220/220 nt) gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_ position_end=46185 position_start=46185 ref_seq=G SNP 15 64 NC_001416 46190 G aa_new_seq=R aa_position=2 aa_ref_seq=L codon_new_seq=CGA codon_number=2 codon_position=2 codon_ref_seq=CTA frequency=9.29923058e-02 gene_name=Rz1 gene_position=5 gene_product=Rz1 protein gene_strand=> genes_overlapping=Rz1 locus_tag=lambdap91 locus_tags_overlapping=lambdap91 mutation_category=snp_nonsynonymous position_end=46190 position_start=46190 ref_seq=T snp_type=nonsynonymous transl_table=11 -SNP 16 65 NC_001416 46430 C frequency=2.10918427e-01 gene_name=Rz1/bor gene_position=intergenic (+62/+29) gene_product=Rz1 protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap91/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic +SNP 16 65 NC_001416 46430 C frequency=2.10918427e-01 gene_name=Rz1/bor gene_position=intergenic (+62/+29) gene_product=Rz1 protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap91/lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic SNP 17 66 NC_001416 46597 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=2.37746716e-01 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46597 position_start=46597 ref_seq=G snp_type=synonymous transl_table=11 SNP 18 67 NC_001416 46608 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=1.97282791e-01 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=46608 position_start=46608 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 19 68 NC_001416 46612 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=1.53758049e-01 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46612 position_start=46612 ref_seq=C snp_type=synonymous transl_table=11 @@ -50,7 +50,7 @@ SNP 39 88 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_s SNP 40 89 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 41 90 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 42 91 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 43 92 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 43 92 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 44 93 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 45 94 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 46 95,96 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT diff --git a/tests/lambda_polymorphism_user_evidence/expected.gd b/tests/lambda_polymorphism_user_evidence/expected.gd index 0ac9061a..07919332 100644 --- a/tests/lambda_polymorphism_user_evidence/expected.gd +++ b/tests/lambda_polymorphism_user_evidence/expected.gd @@ -8,24 +8,24 @@ #=INPUT-READS 200010 #=MAPPED-BASES 4955561 #=MAPPED-READS 142716 -SNP 1 60 NC_001416 54 A frequency=9.29455757e-02 gene_name=–/nu1 gene_position=intergenic (–/-137) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=54 position_start=54 ref_seq=G snp_type=intergenic -SNP 2 61 NC_001416 73 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 3 62 NC_001416 73 G frequency=7.63196945e-02 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 4 63 NC_001416 73 T frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic -SNP 5 64 NC_001416 75 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-116) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=75 position_start=75 ref_seq=A snp_type=intergenic -SNP 6 65 NC_001416 101 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=101 position_start=101 ref_seq=C snp_type=intergenic -INS 7 66 NC_001416 101 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> insert_position=10 locus_tag=–/lambdap01 mutation_category=small_indel position_end=101 position_start=101 ref_seq=C -SNP 8 67 NC_001416 102 C frequency=8.00042152e-02 gene_name=–/nu1 gene_position=intergenic (–/-89) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=102 position_start=102 ref_seq=T snp_type=intergenic -SNP 9 68 NC_001416 134 A frequency=9.52515602e-02 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=snp_intergenic position_end=134 position_start=134 ref_seq=G snp_type=intergenic -INS 10 69 NC_001416 134 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> insert_position=1 locus_tag=–/lambdap01 mutation_category=small_indel position_end=134 position_start=134 ref_seq=G -DEL 11 70 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> locus_tag=–/lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G +SNP 1 60 NC_001416 54 A frequency=9.29455757e-02 gene_name=–/nu1 gene_position=intergenic (–/-137) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=54 position_start=54 ref_seq=G snp_type=intergenic +SNP 2 61 NC_001416 73 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 3 62 NC_001416 73 G frequency=7.63196945e-02 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 4 63 NC_001416 73 T frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-118) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=73 position_start=73 ref_seq=A snp_type=intergenic +SNP 5 64 NC_001416 75 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-116) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=75 position_start=75 ref_seq=A snp_type=intergenic +SNP 6 65 NC_001416 101 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=101 position_start=101 ref_seq=C snp_type=intergenic +INS 7 66 NC_001416 101 C frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-90) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 insert_position=10 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=101 position_start=101 ref_seq=C +SNP 8 67 NC_001416 102 C frequency=8.00042152e-02 gene_name=–/nu1 gene_position=intergenic (–/-89) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=102 position_start=102 ref_seq=T snp_type=intergenic +SNP 9 68 NC_001416 134 A frequency=9.52515602e-02 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=snp_intergenic position_end=134 position_start=134 ref_seq=G snp_type=intergenic +INS 10 69 NC_001416 134 A frequency=0.00000000e+00 gene_name=–/nu1 gene_position=intergenic (–/-57) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 insert_position=1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=134 position_start=134 ref_seq=G +DEL 11 70 NC_001416 139 1 frequency=1 gene_name=–/nu1 gene_position=intergenic (–/-52) gene_product=–/DNA packaging protein gene_strand=–/> genes_promoter=nu1 locus_tag=–/lambdap01 locus_tags_promoter=lambdap01 mutation_category=small_indel position_end=139 position_start=139 ref_seq=G INS 12 71 NC_001416 14266 G frequency=1 gene_name=L/K gene_position=intergenic (+139/-10) gene_product=tail component/tail component gene_strand=>/> genes_promoter=K insert_position=1 locus_tag=lambdap18/lambdap19 locus_tags_promoter=lambdap19 mutation_category=small_indel position_end=14266 position_start=14266 ref_seq=C SNP 13 72 NC_001416 20661 G aa_new_seq=E|S aa_position=338|36 aa_ref_seq=?|? codon_new_seq=GAA|TCT codon_number=338|36 codon_position=1|2 codon_ref_seq=NAA|TNT frequency=1 gene_name=orf-401|orf206b gene_position=1012|107 gene_product=Tail fiber protein|hypothetical protein gene_strand=>|< genes_overlapping=orf-401,orf206b locus_tag=lambdap27|lambdap90 locus_tags_overlapping=lambdap27,lambdap90 mutation_category=snp_nonsynonymous|nonsynonymous position_end=20661 position_start=20661 ref_seq=N snp_type=nonsynonymous|nonsynonymous transl_table=11|11 INS 14 73 NC_001416 20835 C frequency=1 gene_name=orf-401 gene_position=coding (1186/1206 nt) gene_product=Tail fiber protein gene_strand=> genes_overlapping=orf-401 insert_position=1 locus_tag=lambdap27 locus_tags_overlapping=lambdap27 mutation_category=small_indel position_end=20835 position_start=20835 ref_seq=C SNP 15 74 NC_001416 21714 A aa_new_seq=N aa_position=229 aa_ref_seq=S codon_new_seq=AAC codon_number=229 codon_position=2 codon_ref_seq=AGC frequency=1 gene_name=orf-314 gene_position=686 gene_product=Tail fiber gene_strand=> genes_overlapping=orf-314 locus_tag=lambdap28 locus_tags_overlapping=lambdap28 mutation_category=snp_nonsynonymous position_end=21714 position_start=21714 ref_seq=G snp_type=nonsynonymous transl_table=11 DEL 16 120,123 NC_001416 21738 5996 frequency=1 gene_name=[orf-314]–ea59 gene_product=[orf-314],orf-194,ea47,ea31,ea59 genes_inactivated=orf-314,orf-194,ea47,ea31,ea59 locus_tag=[lambdap28]–[lambdap82] locus_tags_inactivated=lambdap28,lambdap29,lambdap80,lambdap81,lambdap82 mutation_category=large_deletion position_end=27733 position_start=21738 ref_seq=5996-bp SNP 17 75 NC_001416 31016 C aa_new_seq=E|D aa_position=3|61 aa_ref_seq=E|N codon_new_seq=GAG|GAC codon_number=3|61 codon_position=3|1 codon_ref_seq=GAA|AAC frequency=1 gene_name=orf61|orf63 gene_position=9|181 gene_product=hypothetical protein|hypothetical protein gene_strand=<|< genes_overlapping=orf61,orf63 locus_tag=lambdap37|lambdap38 locus_tags_overlapping=lambdap37,lambdap38 mutation_category=snp_synonymous|nonsynonymous position_end=31016 position_start=31016 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 18 76 NC_001416 34428 G frequency=1.05375290e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic +SNP 18 76 NC_001416 34428 G frequency=1.05375290e-01 gene_name=orf28/lambdap48 gene_position=intergenic (-71/-54) gene_product=hypothetical protein/Superinfection exclusion protein B gene_strand= genes_promoter=orf28,lambdap48 locus_tag=lambdap47/lambdap48 locus_tags_promoter=lambdap47,lambdap48 mutation_category=snp_intergenic position_end=34428 position_start=34428 ref_seq=T snp_type=intergenic SNP 19 77 NC_001416 34934 G aa_new_seq=G aa_position=151 aa_ref_seq=G codon_new_seq=GGG codon_number=151 codon_position=3 codon_ref_seq=GGA frequency=1 gene_name=lambdap48 gene_position=453 gene_product=Superinfection exclusion protein B gene_strand=> genes_overlapping=lambdap48 locus_tag=lambdap48 locus_tags_overlapping=lambdap48 mutation_category=snp_synonymous position_end=34934 position_start=34934 ref_seq=A snp_type=synonymous transl_table=11 DEL 20 78 NC_001416 37818 1 frequency=1 gene_name=cI gene_position=coding (123/714 nt) gene_product=repressor gene_strand=< genes_inactivated=cI locus_tag=lambdap88 locus_tags_inactivated=lambdap88 mutation_category=small_indel position_end=37818 position_start=37818 ref_seq=C SNP 21 79 NC_001416 45618 C aa_new_seq=F aa_position=42 aa_ref_seq=F codon_new_seq=TTC codon_number=42 codon_position=3 codon_ref_seq=TTT frequency=1 gene_name=R gene_position=126 gene_product=endolysin gene_strand=> genes_overlapping=R locus_tag=lambdap75 locus_tags_overlapping=lambdap75 mutation_category=snp_synonymous position_end=45618 position_start=45618 ref_seq=T snp_type=synonymous transl_table=11 @@ -34,7 +34,7 @@ SNP 23 81 NC_001416 46154 A aa_new_seq=A aa_position=63 aa_ref_seq=A codon_new_s SNP 24 82 NC_001416 46157 G aa_new_seq=L aa_position=64 aa_ref_seq=L codon_new_seq=CTG codon_number=64 codon_position=3 codon_ref_seq=CTC frequency=6.40873909e-02 gene_name=Rz gene_position=192 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_synonymous position_end=46157 position_start=46157 ref_seq=C snp_type=synonymous transl_table=11 SNP 25 83 NC_001416 46185 A aa_new_seq=N aa_position=74 aa_ref_seq=D codon_new_seq=AAT codon_number=74 codon_position=1 codon_ref_seq=GAT frequency=8.00681114e-02 gene_name=Rz gene_position=220 gene_product=cell lysis protein gene_strand=> genes_overlapping=Rz locus_tag=lambdap76 locus_tags_overlapping=lambdap76 mutation_category=snp_nonsynonymous position_end=46185 position_start=46185 ref_seq=G snp_type=nonsynonymous transl_table=11 SNP 26 84 NC_001416 46190 G aa_new_seq=A|R aa_position=75|2 aa_ref_seq=A|L codon_new_seq=GCG|CGA codon_number=75|2 codon_position=3|2 codon_ref_seq=GCT|CTA frequency=9.29918289e-02 gene_name=Rz|Rz1 gene_position=225|5 gene_product=cell lysis protein|Rz1 protein gene_strand=>|> genes_overlapping=Rz,Rz1 locus_tag=lambdap76|lambdap91 locus_tags_overlapping=lambdap76,lambdap91 mutation_category=snp_synonymous|nonsynonymous position_end=46190 position_start=46190 ref_seq=T snp_type=synonymous|nonsynonymous transl_table=11|11 -SNP 27 85 NC_001416 46430 C frequency=2.10921288e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< genes_promoter=bor locus_tag=lambdap76/lambdap77 locus_tags_promoter=lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic +SNP 27 85 NC_001416 46430 C frequency=2.10921288e-01 gene_name=Rz/bor gene_position=intergenic (+3/+29) gene_product=cell lysis protein/Bor protein precursor gene_strand=>/< locus_tag=lambdap76/lambdap77 mutation_category=snp_intergenic position_end=46430 position_start=46430 ref_seq=T snp_type=intergenic SNP 28 86 NC_001416 46597 A aa_new_seq=V aa_position=52 aa_ref_seq=V codon_new_seq=GTT codon_number=52 codon_position=3 codon_ref_seq=GTC frequency=2.37744331e-01 gene_name=bor gene_position=156 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46597 position_start=46597 ref_seq=G snp_type=synonymous transl_table=11 SNP 29 87 NC_001416 46608 C aa_new_seq=E aa_position=49 aa_ref_seq=K codon_new_seq=GAG codon_number=49 codon_position=1 codon_ref_seq=AAG frequency=1.97285175e-01 gene_name=bor gene_position=145 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_nonsynonymous position_end=46608 position_start=46608 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 30 88 NC_001416 46612 T aa_new_seq=G aa_position=47 aa_ref_seq=G codon_new_seq=GGA codon_number=47 codon_position=3 codon_ref_seq=GGG frequency=1.53755665e-01 gene_name=bor gene_position=141 gene_product=Bor protein precursor gene_strand=< genes_overlapping=bor locus_tag=lambdap77 locus_tags_overlapping=lambdap77 mutation_category=snp_synonymous position_end=46612 position_start=46612 ref_seq=C snp_type=synonymous transl_table=11 @@ -61,7 +61,7 @@ SNP 50 108 NC_001416 47398 T aa_new_seq=N aa_position=60 aa_ref_seq=D codon_new_ SNP 51 109 NC_001416 47509 C aa_new_seq=A aa_position=23 aa_ref_seq=T codon_new_seq=GCG codon_number=23 codon_position=1 codon_ref_seq=ACG frequency=1 gene_name=lambdap78 gene_position=67 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47509 position_start=47509 ref_seq=T snp_type=nonsynonymous transl_table=11 SNP 52 110 NC_001416 47529 T aa_new_seq=K aa_position=16 aa_ref_seq=R codon_new_seq=AAG codon_number=16 codon_position=2 codon_ref_seq=AGG frequency=1 gene_name=lambdap78 gene_position=47 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_nonsynonymous position_end=47529 position_start=47529 ref_seq=C snp_type=nonsynonymous transl_table=11 SNP 53 111 NC_001416 47575 A aa_new_seq=M aa_position=1 aa_ref_seq=M codon_new_seq=TTG codon_number=1 codon_position=1 codon_ref_seq=GTG frequency=1 gene_name=lambdap78 gene_position=1 gene_product=putative envelope protein gene_strand=< genes_overlapping=lambdap78 locus_tag=lambdap78 locus_tags_overlapping=lambdap78 mutation_category=snp_synonymous position_end=47575 position_start=47575 ref_seq=C snp_type=synonymous transl_table=11 -SNP 54 112 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic +SNP 54 112 NC_001416 47669 C frequency=1 gene_name=lambdap78/lambdap79 gene_position=intergenic (-94/-69) gene_product=putative envelope protein/hypothetical protein gene_strand= genes_promoter=lambdap78,lambdap79 locus_tag=lambdap78/lambdap79 locus_tags_promoter=lambdap78,lambdap79 mutation_category=snp_intergenic position_end=47669 position_start=47669 ref_seq=T snp_type=intergenic SNP 55 113 NC_001416 47878 G aa_new_seq=R aa_position=47 aa_ref_seq=R codon_new_seq=AGG codon_number=47 codon_position=3 codon_ref_seq=AGA frequency=1 gene_name=lambdap79 gene_position=141 gene_product=hypothetical protein gene_strand=> genes_overlapping=lambdap79 locus_tag=lambdap79 locus_tags_overlapping=lambdap79 mutation_category=snp_synonymous position_end=47878 position_start=47878 ref_seq=A snp_type=synonymous transl_table=11 SNP 56 114 NC_001416 47973 C frequency=1 gene_name=lambdap79/– gene_position=intergenic (+29/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=snp_intergenic position_end=47973 position_start=47973 ref_seq=T snp_type=intergenic SUB 57 115,116 NC_001416 47977 2 AC frequency=1 gene_name=lambdap79/– gene_position=intergenic (+33/–) gene_product=hypothetical protein/– gene_strand=>/– locus_tag=lambdap79/– mutation_category=small_indel position_end=47978 position_start=47977 ref_seq=GT