dna-seq/dvc.lock at master · vovixsw/dna-seq · 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
schema: '2.0'
stages:
  prepare:
    cmd: gunzip -k data/gwas/homo_sapiens_ensembl_103/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
      && unzip -o -d data/ensembl/103 data/ensembl/103/103.zip && mv data/ensembl/103/VEP_plugins-release-103
      data/ensembl/103/plugins
    deps:
    - path: data/ensembl/103/103.zip
    - path: data/gwas/homo_sapiens_ensembl_103/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
    outs:
    - path: data/ensembl/103/plugins
    - path: data/gwas/homo_sapiens_ensembl_103/Homo_sapiens.GRCh38.dna.primary_assembly.fa
  start:
    cmd: docker-compose up
  stop:
    cmd: docker-compose down
  cache:
    cmd: tar -C  data/ensembl/103/cache/ -zxvf data/ensembl/103/cache/homo_sapiens_vep_103_GRCh38.tar.gz
    deps:
    - path: data/ensembl/103/cache/homo_sapiens_vep_103_GRCh38.tar.gz
    outs:
    - path: data/ensembl/103/cache/homo_sapiens
  prepare_genome:
    cmd: gunzip -k data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
      && samtools faidx data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa
      && samtools dict data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa
      -o data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.dict
      md5sum data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.*
      > data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.md5
    deps:
    - path: data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
      md5: f58a039f83d8944ceb79cdd16cbda583
      size: 881211416
    outs:
    - path: data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa
      md5: 9e6b9465dc708d92bf6d67e9c9fa9389
      size: 3151425857
    - path: data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.dict
      md5: dc1b3dc9c008222222c89dfd9eca0087
      size: 34186
    - path: data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.fai
      md5: d527f3eb6b664020cf4d882b5820056f
      size: 6406
    - path: data/ensembl/106/species/Homo_sapiens/Homo_sapiens.GRCh38.dna.primary_assembly.fa.md5
      md5: d41d8cd98f00b204e9800998ecf8427e
      size: 0
  prepare_vep:
    cmd: unzip -u data/ensembl/103/103.zip -d data/ensembl/103/ && mv data/ensembl/103/VEP_plugins-release-103
      data/ensembl/103/plugins
    deps:
    - path: data/ensembl/103/103.zip
    - path: data/ensembl/103/cache/homo_sapiens_vep_103_GRCh38.tar.gz
    outs:
    - path: data/ensembl/103/plugins/
  prepare_annotations:
    cmd: "gunzip -c data/gwas/annotations/all_variant_disease_pmid_associations.tsv.gz\
      \ |\n   awk '($1 ~ /^snpId/ || $2 ~ /NA/) {next} {print $0}' |\n   sort -t $'\\\
      t' -k2,2 -k3,3n |\n   awk '{ gsub (/\\t +/, \"\\t\", $0); print}' |\n   bgzip\
      \ -c > data/gwas/annotations/all_variant_disease_pmid_associations_final.tsv.gz\
      \ &&\nrm -f data/gwas/annotations/gene2phenotype/AllG2P.csv && awk '(NR == 1)\
      \ || (FNR > 1)' data/gwas/annotations/gene2phenotype/*.csv  > data/gwas/annotations/gene2phenotype/AllG2P.csv"
    deps:
    - path: data/gwas/annotations/all_variant_disease_pmid_associations.tsv.gz
    - path: data/gwas/annotations/clinvar.vcf.gz
    - path: data/gwas/annotations/clinvar.vcf.gz.tbi
    - path: data/gwas/annotations/gene2phenotype/CancerG2P.csv
    - path: data/gwas/annotations/gene2phenotype/DDG2P.csv
    - path: data/gwas/annotations/gene2phenotype/EyeG2P.csv
    - path: data/gwas/annotations/gene2phenotype/SkinG2P.csv
    outs:
    - path: data/gwas/annotations/all_variant_disease_pmid_associations_final.tsv.gz
    - path: data/gwas/annotations/gene2phenotype/AllG2P.csv
  prepare_vep_plugins:
    cmd: unzip -u data/ensembl/106/106.zip -d data/ensembl/106/ && mv data/ensembl/106/VEP_plugins-release-106
      data/ensembl/106/plugins
    deps:
    - path: data/ensembl/106/106.zip
      md5: 24158d25f82878edcacf444da702ed23
      size: 519178
    outs:
    - path: data/ensembl/106/plugins/
      md5: 46e9f69002e39c1fb41138fe8ac01710.dir
      size: 1470134
      nfiles: 77
  prepare_vep_cache:
    cmd: tar -zxf data/ensembl/106/homo_sapiens_vep_106_GRCh38.tar.gz -C data/ensembl/106/cache/
      && md5sum data/ensembl/106/homo_sapiens_vep_106_GRCh38.tar.gz > data/ensembl/106/homo_sapiens_vep_106_GRCh38.tar.gz.md5
    deps:
    - path: data/ensembl/106/homo_sapiens_vep_106_GRCh38.tar.gz
      md5: f2d4487002a86fe4c39a9ca0fbfab9da
      size: 19350569358
    outs:
    - path: data/ensembl/106/cache/homo_sapiens
      md5: f921763987635b40b85cfaf8a3f68048.dir
      size: 19621031672
      nfiles: 13892
  prepare_annotations_clinvar:
    cmd: echo "Clinvars annotations prepared"
    deps:
    - path: data/gwas/annotations/clinvar.vcf.gz
      md5: 1a0bd5729abb411a388e590431c62f99
      size: 57813301
    - path: data/gwas/annotations/clinvar.vcf.gz.tbi
      md5: 32876337b3454813376f2599b38fd96a
      size: 327433
  prepare_annotations_gene2phenotype:
    cmd: rm -f data/gwas/annotations/gene2phenotype/AllG2P.csv && awk '(NR == 1) ||
      (FNR > 1)' data/gwas/annotations/gene2phenotype/*.csv  > data/gwas/annotations/gene2phenotype/AllG2P.csv
    deps:
    - path: data/gwas/annotations/gene2phenotype/CancerG2P.csv
      md5: 6504732dc971b2578c21a8cbd6c2d3ad
      size: 19914
    - path: data/gwas/annotations/gene2phenotype/DDG2P.csv
      md5: d21a0e446a3cc3b3adbae486cd6d11c6
      size: 776664
    - path: data/gwas/annotations/gene2phenotype/EyeG2P.csv
      md5: 9bf5d96096c52df97792b165fbfeda45
      size: 221233
    - path: data/gwas/annotations/gene2phenotype/SkinG2P.csv
      md5: 15e1b25db13f3929357ba3dba60e7e1b
      size: 214278
    outs:
    - path: data/gwas/annotations/gene2phenotype/AllG2P.csv
      md5: ccf679127863b2832ccb1ceb2561502a
      size: 1231432
  prepare_annotations_digenet:
    cmd: "gunzip -c data/gwas/annotations/all_variant_disease_pmid_associations.tsv.gz\
      \ |\n   awk '($1 ~ /^snpId/ || $2 ~ /NA/) {next} {print $0}' |\n   sort -t $'\\\
      t' -k2,2 -k3,3n |\n   awk '{ gsub (/\\t +/, \"\\t\", $0); print}' |\n   bgzip\
      \ -c > data/gwas/annotations/all_variant_disease_pmid_associations_final.tsv.gz"
    deps:
    - path: data/gwas/annotations/all_variant_disease_pmid_associations.tsv.gz
      md5: a393c9e8e104297aadcb7188f6460eaf
      size: 11171100
    outs:
    - path: data/gwas/annotations/all_variant_disease_pmid_associations_final.tsv.gz
      md5: 3d5dea024369a02f300ca3346eedc967
      size: 9918420
  prepare_opencravat:
    cmd: oc module install-base
  test_opencravat:
    cmd: oc new example-input . && oc run ./example_input -l hg38 && oc gui example_input/example_input.sqlite
  install_opencravat:
    cmd: oc module install-base && oc module install -y clinvar clinvar_acmg biogrid
      uk10k_cohort uniprot pubmed provean polyphen2 cardioboost civic civic_gene cosmic
      cosmic_gene go sift ensembl_regulatory_build dgi cvdkp
  install_cancer:
    cmd: oc module install chasmplus cgc cgl cancer_genome_interpreter cancer_hotspots
      civic
  prepare_annotations_longevity:
    cmd: wget -qO- --timestamping https://genomics.senescence.info/longevity/longevity_genes.zip
      | bsdtar -xvf- -C data/gwas/annotations/ longevity.csv
    outs:
    - path: data/gwas/annotations/longevity.csv
      md5: 54e53fe8c1a97282458249e1625beec8
      size: 66288