tourmaline/config.yaml at master · ropolomx/tourmaline · GitHub

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
# fastq manifests and metadata
manifest_se: 00-data/manifest_se.csv
manifest_pe: 00-data/manifest_pe.csv
metadata: 00-data/metadata.tsv

# reference sequences
refseqs: 00-data/refseqs.fna
reftax: 00-data/reftax.tsv
pcr_locus: 16S-EMP
pcr_primer_fwd: GTACACACCGCCCGTC
pcr_primer_rev: TGATCCTTCTGCAGGTTCACCTAC

# deblur
deblur_trim_length: 100
deblur_sample_stats: --p-sample-stats
deblur_mean_error: 0.005
deblur_indel_prob: 0.01
deblur_indel_max: 3
deblur_min_reads: 10
deblur_min_size: 2
deblur_jobs_to_start: 1
deblur_hashed_feature_ids: --p-hashed-feature-ids

# dada2 single-end
dada2se_trunc_len: 0
dada2se_trim_left: 0
dada2se_max_ee: 2
dada2se_trunc_q: 2
dada2se_chimera_method: consensus
dada2se_min_fold_parent_over_abundance: 1
dada2se_n_threads: 16
dada2se_n_reads_learn: 1000000
dada2se_hashed_feature_ids: --p-hashed-feature-ids

# dada2 paired-end
dada2pe_trunc_len_f: 280
dada2pe_trunc_len_r: 200
dada2pe_trim_left_f: 10
dada2pe_trim_left_r: 10
dada2pe_max_ee_f: 2
dada2pe_max_ee_r: 2
dada2pe_trunc_q: 2
dada2pe_chimera_method: consensus
dada2pe_min_fold_parent_over_abundance: 1
dada2pe_n_threads: 8
dada2pe_n_reads_learn: 1000000
dada2pe_hashed_feature_ids: --p-hashed-feature-ids

# subsampling
core_sampling_depth: 848
alpha_max_depth: 848

# statistics
beta_group_column: treatment

# report theme (choose from: github, gothic, newsprint, night, pixyll, whitey)
report_theme: github

# NOTE: refseqs.fasta and reftax.tsv -- and/or their outputs refseqs.qza,
# reftax.qza, and classifier.qza -- should ideally be in an external directory.
# We recommend setting symbolic links in 00-data and 01-imported to these
# external files. Adding these files will circumvent the rules that produce
# them; e.g., if classifier.qza is added, the rule
# feature_classifier_fit_classifier_naive_bayes will be skipped.

# WARNING: Snakemake will not automatically rerun if parameters change. It
# should rerun if input files change. To ensure that a file is regenerated,
# you can delete it directly before re-running Snakemake. For Snakemake to
# work with the symbolic links, you may first have to run:
#
#   snakemake --cleanup-metadata <filenames>
#