-
Notifications
You must be signed in to change notification settings - Fork 8
/
config-update.yaml
113 lines (101 loc) · 4.09 KB
/
config-update.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
#-- email notifications of pipeline success/failure (use "Skip" to deactivate) --#
email: None
#-- databases to update --#
# Replace "Create" with "Skip" to skip creation of any of these
# Note that braken relies on the kraken2 database
databases:
kraken2: Create
bracken: Create
genes: Create
humann3_bowtie2: Create
humann3_diamond: Create
#-- Input --#
#--- If just a set of gene sequences to add ---#
# If you have nucleotide/amino-acid gene sequences formatted for humann
# If translate = True, missing nuc or AA seqs will be (rev)translated from the other, else seqs not used
new_genes: # remove "Skip" to add these genes instead of from the genomes
amino_acid: Skip #data/UniRef50/genome_reps_filtered.faa.gz
nucleotide: Skip #data/UniRef50/genome_reps_filtered.fna.gz
metadata: Skip #data/UniRef50/genome_reps_filtered.txt.gz
translate: True
#--- If a set of genomes to add ---#
# file listing samples and associated data
samples_file: data/GTDBr95_n5/GTDBr95_n5.tsv
## column names in samples table
samples_col: 'ncbi_organism_name'
accession_col: 'accession'
fasta_file_path_col: 'fasta_file_path'
taxID_col: 'gtdb_taxid' # or 'ncbi_species_taxid'
taxonomy_col: 'gtdb_taxonomy' # or 'ncbi_taxonomy'
# Saved databases that will be updated
kraken2_db:
library: tests/output/GTDBr95_n10/kraken2/library/
taxonomy: tests/output/GTDBr95_n10/kraken2/taxonomy/
genes_db:
genes:
mmseqs_db: tests/output/GTDBr95_n10/genes/genes_db.tar.gz
amino_acid: tests/output/GTDBr95_n10/genes/genome_reps_filtered.faa.gz
nucleotide: tests/output/GTDBr95_n10/genes/genome_reps_filtered.fna.gz
metadata: tests/output/GTDBr95_n10/genes/genome_reps_filtered.txt.gz
cluster:
mmseqs_db: tests/output/GTDBr95_n10/genes/cluster/clusters_db.tar.gz
humann_db:
query:
hits: tests/output/GTDBr95_n10/humann3/annotation_hits.gz
cluster:
reps: tests/output/GTDBr95_n10/genes/cluster/clusters_reps.faa.gz
membership: tests/output/GTDBr95_n10/genes/cluster/clusters_membership.tsv.gz
#-- Output --#
# output location
output_dir: tests/output/GTDBr95_n10-n5/
# Name of UniRef clustering (uniref90 or uniref50)
## "uniref90" highly recommended
uniref_name: uniref90
# Name of the humann3 diamond database to create
## This must match naming allowed by humann3
dmnd_name: uniref90_201901.dmnd
# Index mapping UniRef90 clusters to UniRef50 (saves time vs re-annotating)
## Skip if annotating with UniRef50
cluster_idx: data/uniref50-90.pkl
# temporary file directory (your username will be added automatically)
tmp_dir: tmp/db_update_tmp/
#-- if custom NCBI/GTDB taxdump files, "Skip" if standard NCBI taxdump --#
# Used for kraken taxonomy & metaphlan
names_dmp: data/taxdump/names.dmp
nodes_dmp: data/taxdump/nodes.dmp
#-- keep intermediate files required for re-creating DBs (eg., w/ more genomes) --#
# If "True", the intermediate files are saved to `output_dir`
# Else, the intermediate files are temporarily stored in `temp_folder`
keep_intermediate: True
#-- software parameters --#
# `vsearch_per_genome` = per-genome gene clustering
# for humann3, use either mmseqs or diamond (mmseqs gets priority if neither skipped)
# for humann3::mmseqs_search::run, --num-iterations must be >=2
params:
ionice: -c 3
bracken:
build_kmer: 35
build_read_lens:
- 100
- 150
genes:
prodigal: ""
vsearch_per_genome: --id 0.97 --strand both --qmask none --fasta_width 0
mmseqs_cluster_update: --min-seq-id 0.9 -c 0.8 -s 4.0
humann3:
batches: 2
filter_existing: --min-pident 0 # any existing genes w/ < cutoff with be re-queried
mmseqs_search:
db: data/UniRef90/uniref90
index: -s 6
run: -e 1e-3 --max-accept 1 --max-seqs 100 --num-iterations 2 --start-sens 1 --sens-steps 3 -s 6
diamond:
db: Skip #data/uniref90_ec-filtered/uniref90_ec_filt_201901.dmnd
run: --evalue 1e-3 --query-cover 80 --id 90 --max-target-seqs 1 --block-size 4 --index-chunks 2
propagate_annotations: --min-cov 80 --min-pident 90
#-- snakemake pipeline --#
pipeline:
snakemake_folder: ./
script_folder: ./bin/scripts/
name: Struo2_db-update
config: update