-
Notifications
You must be signed in to change notification settings - Fork 5
/
config_hpf.yaml
203 lines (190 loc) · 11.2 KB
/
config_hpf.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
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
196
197
198
199
200
201
202
203
run:
project: "NA12878"
samples: samples.tsv
units: units.tsv
ped: "" # leave this string empty if there is no ped
panel: "" # three-column BED file based on hpo file; leave this string empty if there is no panel
hpo: "" # five-column TSV with HPO terms; leave this string empty is there are no hpo terms
flank: 100000
gatk: "gatk"
pipeline: "wes" #either wes (exomes) or wgs (genomes) or annot (to annotate and produce reports for an input vcf) or mity (to generate mitochondrial reports)
minio: ""
PT_credentials: ""
genes:
ensembl: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/Homo_sapiens.GRCh37.87.gtf_subset.csv"
refseq: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/GRCh37_latest_genomic.gff_subset.csv"
hgnc: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/HGNC_20210617.txt"
tools:
svscore_script: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/SVScore/svscore.pl"
annotsv: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/AnnotSV_2.1"
cre: "~/cre"
crg: "~/crg"
crg2: "~/crg2"
ehdn: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/EHDN.TCAG/ExpansionHunterDenovo-v0.7.0"
mity: "/hpf/largeprojects/ccmbio/ajain/mity/mity_package/bin"
melt: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/MELT/MELTv2.2.2/MELT.jar"
orad: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/orad_2_6_1/orad"
annovar: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/annovar"
ref:
name: GRCh37.75
no_decoy_name: GRCh37
genome: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/GRCh37d5/GRCh37d5.fa
known-variants: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/dbsnp.b147.20160601.tidy.vcf.gz
no_decoy: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/GRCh37/GRCh37.fa
decoy_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/pipelines/cre/data/grch37d5.decoy.bed"
canon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/grch37.canon.bed"
split_genome: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/split_genome"
gatk-known: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/Mills_and_1000G_gold_standard.indels.vcf.gz"
ref_cache: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/REF_CACHE/GRCh37d5/%2s/%2s/%s:/hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/REF_CACHE/hg19/%2s/%2s/%s"
bed_index: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa.bedtoolsindex"
melt_element_ref: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MELT/transposon_file_list.txt"
orad_ref: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/orad_2_6_1/oradata"
filtering:
vqsr: false
hard:
# hard filtering as outlined in GATK docs
# (https://gatkforums.broadinstitute.org/gatk/discussion/2806/howto-apply-hard-filters-to-a-call-set)
snvs:
"QD < 2.0 || FS > 60.0 || MQ < 30.0 || MQRankSum < -12.5 || ReadPosRankSum < -8.0"
indels:
"QD < 2.0 || FS > 200.0 || ReadPosRankSum < -20.0"
soft:
platypus:
name: 'PlatQualDepth'
filter: '(FR[0] <= 0.5 && TC < 4 && %QUAL < 20) || (TC < 13 && %QUAL < 10) || (FR[0] > 0.5 && TC < 4 && %QUAL < 50)'
freebayes:
name: 'FBQualDepth'
filter: '(AF[0] <= 0.5 && (max(FORMAT/DP) < 4 || (max(FORMAT/DP) < 13 && %QUAL < 10))) || (AF[0] > 0.5 && (max(FORMAT/DP) < 4 && %QUAL < 50))'
samtools:
name: 'stQualDepth'
filter: '((AC[0] / AN) <= 0.5 && max(FORMAT/DP) < 4 && %QUAL < 20) || (max(FORMAT/DP) < 13 && %QUAL < 10) || ((AC[0] / AN) > 0.5 && max(format/DP) < 4 && %QUAL < 50)'
gatk:
snvs:
name: 'GATKCutoffSNP'
filter: 'TYPE="snp" && (MQRankSum < -12.5 || ReadPosRankSum < -8.0 || QD < 2.0 || FS > 60.0 || MQ < 30.0)'
indel:
name: 'GATKCutoffIndel'
filter: 'TYPE="indel" && (ReadPosRankSum < -20.0 || QD < 2.0 || FS > 200.0 || SOR > 10.0)'
processing:
mark-duplicates: true
# Uncomment and point to a bed file with, e.g., captured regions if necessary,
# see https://gatkforums.broadinstitute.org/gatk/discussion/4133/when-should-i-use-l-to-pass-in-a-list-of-intervals.
# restrict-regions: captured_regions.bed
# If regions are restricted, uncomment this to enlarge them by the given value in order to include
# flanking areas.
# region-padding: 100
qc:
fastq_screen:
conf: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/qc/FastQ_Screen_Genomes/fastq_screen.conf"
annotation:
cre.vcfanno:
conf: "~/crg2/vcfanno/cre.vcfanno.conf"
lua_script: "~/crg2/vcfanno/cre.vcfanno.lua"
base_path: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/"
vcfanno:
conf: "~/crg2/vcfanno/crg.vcfanno.conf"
lua_script: "~/crg2/vcfanno/crg.vcfanno.lua"
base_path: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/"
mt.vcfanno:
conf: "~/crg2/vcfanno/mt.vcfanno.conf"
base_path: "/hpf/largeprojects/ccmbio/ajain/mity/vcfanno"
vep:
dir: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/snakemake/6f4af8a1/share/ensembl-vep-104.0-0/"
dir_cache: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/vep/"
snpeff:
dataDir: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/snpeff"
svscore:
exon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/refGene.exons.bed.gz"
intron_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/refGene.introns.bed.gz"
cadd: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/whole_genome_SNVs.tsv.gz"
svreport:
hgmd: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/HGMD_2018/hgmd_pro.db"
protein_coding_genes: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/grch37.p13.ensembl.sorted.protein.coding.genes.bed"
exon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/exons/hg19_UCSC_exons_canonical.bed"
exac: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExAC/fordist_cleaned_nonpsych_z_pli_rec_null_data.txt"
omim: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/OMIM_2024-02-06/genemap2.txt"
gnomad: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/gnomad_v2_sv.sites.bed"
gnomad_ins: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MELT/gnomad_v2_sv.sites.INS.bed"
biomart: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/BioMaRt.GrCh37.75.ensembl.mim.hgnc.entrez.txt"
mssng_manta_counts: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MSSNG_COUNTS/Canadian_MSSNG_parent_SVs.Manta.counts.txt"
mssng_lumpy_counts: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MSSNG_COUNTS/Canadian_MSSNG_parent_SVs.LUMPY.counts.txt"
eh:
catalog: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunter/tandem_repeat_disease_loci_v1.1.hg19.masked.json"
trf: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunter/tandem_repeat_disease_loci_v1.1.tsv"
1000g: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunter/1000G_EH_v1.0.tsv"
ehdn:
files: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/"
g1k_outlier: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/1000G_outlier"
g1k_manifest: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/manifest.1000G.txt"
g1k_samples: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/1000G.samples.txt"
trf: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/UCSC_simple_repeats_hg19_coord_motif.tsv"
omim: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo/OMIM_hgnc_join_omim_phenos_2024-02-06.tsv"
gnomad: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExpansionHunterDenovo//gnomad.v2.1.1.lof_metrics.by_gene.txt"
annovar_db: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/annovar/humandb/"
cre:
database_path: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/"
melt:
genes: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/MELT/MELTv2.2.2/add_bed_files/1KGP_Hg19/hg19.genes.bed"
validation:
benchmark: "benchmark_hpf.tsv"
params:
bwa:
verbosity: "-v 1"
markSplitReads: "-M"
maxMem: ""
gatk:
java_opts: "-Xms500m -Xmx9555m -Dsamjdk.compression_level=5"
HaplotypeCaller: ""
BaseRecalibrator: ""
#BaseRecalibrator: "--interval-set-rule INTERSECTION -U LENIENT-VCF-PROCESSING --read-filter BadCigar --read-filter NotzPrimaryAlignment"
GenotypeGVCFs: ""
VariantRecalibrator: ""
Mutect2:
gnomad_germline: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/Mutect2/af-only-gnomad.raw.sites.vcf"
FilterMutectCalls: ""
gatk3:
java_opts: "-Xms500m -Xmx9555m"
HaplotypeCaller: "-drf DuplicateRead --interval_set_rule INTERSECTION --pair_hmm_implementation VECTOR_LOGLESS_CACHING -ploidy 2 -U LENIENT_VCF_PROCESSING --read_filter BadCigar --read_filter NotPrimaryAlignment"
annotation: "MappingQualityRankSumTest MappingQualityZero QualByDepth ReadPosRankSumTest RMSMappingQuality BaseQualityRankSumTest FisherStrand GCContent HaplotypeScore HomopolymerRun DepthPerAlleleBySample Coverage ClippingRankSumTest DepthPerSampleHC"
RealignerTargetCreator: " -l INFO --interval_set_rule INTERSECTION -U LENIENT_VCF_PROCESSING --read_filter BadCigar --read_filter NotPrimaryAlignment "
IndelRealigner: " -U LENIENT_VCF_PROCESSING --read_filter BadCigar --read_filter NotPrimaryAlignment "
BaseRecalibrator: " --interval_set_rule INTERSECTION -U LENIENT_VCF_PROCESSING --read_filter BadCigar --read_filter NotPrimaryAlignment "
PrintReads: " -jdk_deflater -jdk_inflater -U LENIENT_VCF_PROCESSING --read_filter BadCigar --read_filter NotPrimaryAlignment "
picard:
MarkDuplicates: "REMOVE_DUPLICATES=false"
ValidationStringency: "VALIDATION_STRINGENCY=SILENT"
AssumeSortOrder: "ASSUME_SORT_ORDER=coordinate"
java_opts: "-Xmx2g"
qualimap:
mem: "60G"
nw: 400
c: "-c"
hm: 3
gtf: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/exons/hg19_UCSC_exons_canonical_placeholder.bed"
extra: ""
verifybamid2:
svd_prefix: "1000g.phase3 100k b37"
# --DisableSanityCheck ensures verifybamid2 does not fail for exomes with < 10,000 markers
extra: "--DisableSanityCheck"
multiqc:
config: "~/crg2/rules/multiqc_config.yaml"
snpeff:
java_opts: "-Xms750m -Xmx20g"
svscore:
operations: "max,sum,top5,top10,mean"
samtools:
mpileup: " -t DP -t AD -u -g "
bcftools:
mpileup: "-a DP -a AD "
call: " -m -v "
# -F x sets the output filter to PASS if any of the variant filters is PASS in sample VCFs to be merged
merge: "-F x"
freebayes:
call: " --genotype-qualities --strict-vcf --ploidy 2 --no-partial-observations --min-repeat-entropy 1 "
platypus: "--filterDuplicates=0"
rtg-tools:
java_opts: "-Xmx20g"
vcfeval:
sdf: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/rtg-tools/GRch37_SDF/"
vcfsubset:
java_opts: "-Xmx2048m"