-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathhumann2.yaml
132 lines (104 loc) · 5.19 KB
/
humann2.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
Basic:
humann2 --input $SAMPLE --output $OUTPUT_DIR
humann2_renorm_table --input $SAMPLE_genefamilies.tsv --output $SAMPLE_genefamilies_relab.tsv --units relab
humann2_join_tables --input $OUTPUT_DIR --output humann2_genefamilies.tsv --file_name genefamilies_relab
humann2_join_tables --input $OUTPUT_DIR --output humann2_pathcoverage.tsv --file_name pathcoverage
humann2_join_tables --input $OUTPUT_DIR --output humann2_pathabundance.tsv --file_name pathabundance_relab
$SAMPLE = a single file of FASTQ,SAM, TSV format
Bypass options:
--bypass-translated-search
runs all of the alignment steps except the translated search
--bypass-nucleotide-search
bypasses all of the alignment steps before the translated search
--bypass-prescreen
bypasses the taxomonic profiling step and uses the full ChocoPhlAn database
--taxonomic-profile bugs_list.tsv
bypasses the taxomonic profiling step and creates a custom ChocoPhlAn database of the species included in the list provided
--bypass-nucleotide-index
starts the workflow with the nucleotide alignment step using the indexed database from "--nucleotide-database $DIR"
Other options:
--resume
--verbose
--threads
--remove-temp-output
--nucleotide-database $DIR
--protein-database $DIR
--taxonomic-profile $file
--output-basename $NAME
--remove-stratified-output
--pathways $pathway
--output-format $FORMAT
--identity-threshold $THRESH
--metaphlan $METAPHLAN_PATH (probably don't need this)
--metaphlan-options=$OPTIONS
--annotation-gene-index $IND
--search-mode
--o-log $LOG
--log-level $LEVEL
--prescreen-threshold $THRESH
--translated-subject-coverage-threshold $THRESH
--translated-query-coverage-threshold $THRESH
--bowtie2 $BOWTIE2_PATH (also don't need this)
--usearch $USEARCH_PATH (or this)
--rapsearch $RAPSEARCH_PATH
--diamond $DIAMOND_PATH
--id-mapping
--translated-alignment
--xipe
--minpath
--pick-frames
--output-format
--output-max-decimals
--output-basename
--input-format
--pathways-database
--pathways
--memory-use
Example:
humann2 --input /Users/aguang/miniconda3/envs/humann2/lib/python3.7/site-packages/humann2/tests/data/demo.fastq --output /var/folders/xk/1630rnpd1_9fzr8vlhxjrx_w0000gn/T/humann2_test_bgg6xhzd_fastq_custom_taxonomic_profile --taxonomic-profile /Users/aguang/miniconda3/envs/humann2/lib/python3.7/site-packages/humann2/tests/data/demo_metaphlan_bugs_list.tsv --nucleotide-database /Users/aguang/miniconda3/envs/humann2/lib/python3.7/site-packages/humann2/tests/../data/chocophlan_DEMO --protein-database /Users/aguang/miniconda3/envs/humann2/lib/python3.7/site-packages/humann2/tests/../data/uniref_DEMO
PICRUSt output: (have to split table first)
humann2_split_table --input picrust.biom --output $OUTPUT_DIR
humann2 --input $SAMPLE.biom --output $OUTPUT_DIR2 --pathways-database humann1/data/keggc
humann2_join_tables --input $OUTPUT_DIR2 --output humann2_pathcoverage.tsv --file_name pathcoverage
humann2_join_tables --input $OUTPUT_DIR2 --output humann2_pathabundance.tsv --file_name pathabundance
Barplot:
humann2_barplot --input $TABLE.tsv --feature $FEATURE --outfile $FIGURE
Build_custom_database:
humann2_gene_families_genus_level:
Databases:
humann2_databases --download $DATABASE $BUILD $INSTALL_LOCATION
humann2_databases --download chocophlan full $INSTALL_LOCATION
humann2_databases --download uniref uniref90_diamond $INSTALL_LOCATION
humann2_databases --download uniref uniref90_ec_filtered_diamond $INSTALL_LOCATION
humann2_databases --download uniref uniref50_diamond $INSTALL_LOCATION
humann2_databases --download uniref uniref50_ec_filtered_diamond $INSTALL_LOCATION
humann2_config:
humann2_config --update $SECTION $NAME $VALUE
humann2_config --update database_folders nucleotide $DIR
humann2_config --update database_folders protein $DIR
humann2_humann1_kegg: (legacy database)
humann2_humann1_kegg --ikoc humann1/data/koc --igenels humann1/data/genels --o legacy_kegg_idmapping.tsv
humann2_gene_families_genus_level:
humann2_gene_families_genus_level --input $SAMPLE_genefamilies.tsv --output $SAMPLE_genefamilies_genus_level.tsv
humann2_infer_taxonomy:
humann2_infer_taxonomy --input $INPUT_GENES.tsv --level $LEVEL --resolution $RES --output $OUTPUT.tsv
humann2_join_tables:
humann2_join_tables --input $INPUT_DIR --output $TABLE
humann2_reduce_table:
humann2_reduce_table --input joined_taxonomic_profile.tsv --output max_taxonomic_profile.tsv --function max --sort-by level
humann2_regroup_table:
humann2_regroup_table --input $TABLE --groups $GROUPS --output $TABLE2
humann2_rename_table:
humann2_rename_table --input $TABLE --names $NAMES --output $TABLE2
humann2_renorm_table:
humann2_renorm_table --input $TABLE --units $CHOICE --output $TABLE2
humann2_rna_dna_norm:
humann2_rna_dna_norm --input_dna $TABLE_DNA --input_rna $TABLE_RNA --output_basename $OUTPUT_BASENAME
humann2_split_stratified_table:
humann2_split_stratified_table --input $TABLE --output $OUTPUT_DIR
humann2_split_table:
humann2_split_table --input $TABLE --output $OUTPUT_DIR
humann2_strain_profiler:
humann2_strain_profiler --input $TABLE
humann2_unpack_pathways:
humann2_unpack_pathways --input-genes $INPUT_GENES.tsv --input-pathways $INPUT_PATHWAYS.tsv --output $OUTPUT.tsv