MetaSUB_CAP/pipeline_definition.yml at master · MetaSUB/MetaSUB_CAP · 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
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
---
NAME: metasub_cap
VERSION: 1.1.0
SNAKEMAKE:
  DIR: snakemake_files
  CONF: pipeline_config.py
REQUIREMENTS: {}
SAMPLE_TYPES: []
PACKAGE_MEGA:
  RECIPE_DIR: recipes

ORIGINS:
- - raw_short_read_dna

FILE_TYPES:
- name: gz_fastq
  ext: fastq.gz
- name: minsketch
  ext: msh
- fastqc
- bam
- sam
- txt
- m8
- name: gz_m8
  ext: m8.gz
- name: mpa
  ext: mpa.tsv
- fasta
- fastg
- vcf
- tsv
- csv
- name: gz_tsv
  ext: tsv.gz
- json
- name: jellyfish
  ext: jf


RESULT_TYPES:
- NAME: raw_short_read_dna
  FILES:
    read1: gz_fastq
    read2: gz_fastq

- NAME: adapter_removal
  DEPENDENCIES:
  - raw_short_read_dna
  FILES:
    clean_read1: gz_fastq
    clean_read2: gz_fastq

- NAME: filter_human_dna
  DEPENDENCIES:
  - adapter_removal
  FILES:
    nonhuman_read1: gz_fastq
    nonhuman_read2: gz_fastq
    bam: bam

- NAME: align_to_sa_n315
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    bam: bam

- NAME: count_31mers
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    jf: jellyfish

- NAME: resistome_amrs
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    sam: sam
    gene: tsv
    group: tsv
    classus: tsv
    mech: tsv
    gene_normalized: csv
    group_normalized: csv
    classus_normalized: csv
    mech_normalized: csv

- NAME: krakenhll_taxonomy_profiling
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    read_assignments: tsv
    report: tsv
    report_medium: tsv
    report_strict: tsv

- NAME: finch_sketch
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    sketch: minsketch

- NAME: read_classification_proportions
  DEPENDENCIES:
  - krakenhll_taxonomy_profiling
  - adapter_removal
  - filter_human_dna
  - quantify_macrobial
  FILES:
    json: json

- NAME: read_stats
  DEPENDENCIES:
  - filter_human_dna
  - raw_short_read_dna
  FILES:
    json: json

- NAME: microbe_directory_annotate
  DEPENDENCIES:
  - metaphlan2_taxonomy_profiling
  FILES:
    json: json

- NAME: alpha_diversity_stats
  DEPENDENCIES:
  - kraken_taxonomy_profiling
  - metaphlan2_taxonomy_profiling
  FILES:
    json: json

- NAME: beta_diversity_stats
  DEPENDENCIES:
  - kraken_taxonomy_profiling
  - metaphlan2_taxonomy_profiling
  LEVEL: GROUP
  FILES:
    json: json

- NAME: mash_intersample_dists
  LEVEL: GROUP
  DEPENDENCIES:
  - mash_sketch
  FILES:
    distance_table: csv

- NAME: metaphlan2_taxonomy_profiling
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    mpa: mpa

- NAME: microbe_census
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    stats: txt

- NAME: hmp_site_dists
  DEPENDENCIES:
  - metaphlan2_taxonomy_profiling
  - kraken_taxonomy_profiling
  - mash_intersample_dists
  FILES:
    metaphlan2: json

- NAME: humann2_functional_profiling
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    m8: gz_m8
    genes: tsv
    path_abunds: tsv
    path_cov: tsv

- NAME: humann2_normalize_genes
  DEPENDENCIES:
  - humann2_functional_profiling
  FILES:
    ags_norm_genes: tsv
    read_depth_norm_genes: tsv

- NAME: quantify_macrobial
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    bam: bam
    tbl: json

- NAME: align_to_amr_genes
  DEPENDENCIES:
  - filter_human_dna
  FILES:
    table: csv
    m8: gz_m8