Skip to content

Commit

Permalink
Use GRCh38.109 annotation database in snpEff
Browse files Browse the repository at this point in the history
  • Loading branch information
@jkokosar
jkokosar committed Apr 17, 2024
1 parent 742fc3c commit 6ea1c05
Show file tree
Hide file tree
Showing 14 changed files with 151 additions and 133 deletions.
1 change: 1 addition & 0 deletions docs/CHANGELOG.rst
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ Changed
- **BACKWARD INCOMPATIBLE:** Require Resolwe 39.x
- Rewrite ``expression-aggregator`` process to Python and make it
compatible with the new annotation model
- Use GRCh38.109 genome annotation version in snpEff processes

Fixed
-----
Expand Down
24 changes: 16 additions & 8 deletions resolwe_bio/processes/variant_calling/snpeff.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ class SnpEff(Process):
requirements = {
"expression-engine": "jinja",
"executor": {
"docker": {"image": "public.ecr.aws/genialis/resolwebio/snpeff:2.1.1"},
"docker": {"image": "public.ecr.aws/genialis/resolwebio/snpeff:3.0.0"},
},
"resources": {
"cores": 2,
Expand All @@ -63,7 +63,7 @@ class SnpEff(Process):
}
category = "WGS"
data_name = "Annotated variants (SnpEff)"
version = "1.1.1"
version = "1.2.0"
scheduling_class = SchedulingClass.BATCH
persistence = Persistence.CACHED

Expand All @@ -76,8 +76,12 @@ class Input:
)
database = StringField(
label="snpEff database",
default="GRCh38.99",
choices=[("GRCh37.75", "GRCh37.75"), ("GRCh38.99", "GRCh38.99")],
default="GRCh38.109",
choices=[
("GRCh37.75", "GRCh37.75"),
("GRCh38.99", "GRCh38.99"),
("GRCh38.109", "GRCh38.109"),
],
)
dbsnp = DataField(
data_type="variants:vcf",
Expand Down Expand Up @@ -287,7 +291,7 @@ class SnpEffSingleSample(Process):
requirements = {
"expression-engine": "jinja",
"executor": {
"docker": {"image": "public.ecr.aws/genialis/resolwebio/snpeff:2.1.1"},
"docker": {"image": "public.ecr.aws/genialis/resolwebio/snpeff:3.0.0"},
},
"resources": {
"cores": 2,
Expand All @@ -299,7 +303,7 @@ class SnpEffSingleSample(Process):
}
category = "WGS"
data_name = "{{ variants|name|default('?') }}"
version = "1.0.1"
version = "1.1.0"
scheduling_class = SchedulingClass.BATCH
persistence = Persistence.CACHED

Expand All @@ -312,8 +316,12 @@ class Input:
)
database = StringField(
label="snpEff database",
default="GRCh38.99",
choices=[("GRCh37.75", "GRCh37.75"), ("GRCh38.99", "GRCh38.99")],
default="GRCh38.109",
choices=[
("GRCh37.75", "GRCh37.75"),
("GRCh38.99", "GRCh38.99"),
("GRCh38.109", "GRCh38.109"),
],
)
dbsnp = DataField(
data_type="variants:vcf",
Expand Down
4 changes: 2 additions & 2 deletions resolwe_bio/processes/workflows/rnaseq_variant_calling.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ class WorkflowRnaseqVariantCalling(Process):
},
}
data_name = "RNA-seq Variants ({{ reads|name|default('?') if reads else bam|name|default('?') }})"
version = "2.4.0"
version = "2.5.0"
process_type = "data:workflow:rnaseq:variants"
category = "Pipeline"
entity = {
Expand Down Expand Up @@ -708,7 +708,7 @@ def run(self, inputs, outputs):
if "GRCh37" in inputs.ref_seq.output.build:
snpeff_inputs["database"] = "GRCh37.75"
elif "GRCh38" in inputs.ref_seq.output.build:
snpeff_inputs["database"] = "GRCh38.99"
snpeff_inputs["database"] = "GRCh38.109"

if inputs.snpeff.filtering_options:
snpeff_inputs["filtering_options"] = inputs.snpeff.filtering_options
Expand Down
6 changes: 3 additions & 3 deletions resolwe_bio/tests/files/report_variants/output/ensembl_variants.tsv
View file
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
CHROM POS ID QUAL REF ALT DP FILTER Allele Annotation Annotation_Impact Gene_Name HGVS.p SAMPLENAME1.GT Feature_ID Base_A Base_C Base_G Base_T Total_depth
9 8428302 rs10739162 47.32 T C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.8,ENST00000397617.7,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
9 8428332 rs12348387 59.32000000000001 A C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.8,ENST00000397617.7,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
9 8428346 rs12349376 62.32 T C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.8,ENST00000397617.7,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
9 8428302 rs10739162 47.32 T C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.9,ENST00000397617.8,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
9 8428332 rs12348387 59.32000000000001 A C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.9,ENST00000397617.8,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
9 8428346 rs12349376 62.32 T C 2 DP C intron_variant MODIFIER PTPRD C/C ENST00000355233.9,ENST00000537002.5,ENST00000486161.5,ENST00000397606.7,ENST00000356435.9,ENST00000381196.9,ENST00000397617.8,ENST00000397611.7,ENST00000540109.5,ENST00000651105.1 0 2 0 0 2
2 changes: 1 addition & 1 deletion resolwe_bio/tests/files/report_variants/output/mutations_KRAS.tsv
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
CHROM POS ID QUAL REF ALT FILTER Allele Annotation Annotation_Impact Gene_Name HGVS.p DP Feature_ID Base_A Base_C Base_G Base_T Total_depth
chr12 25245347 rs112445441 974.64 C T PASS T missense_variant MODERATE KRAS p.Gly13Asp 41 ENST00000256078.9,ENST00000311936.8,ENST00000556131.1,ENST00000557334.5 0 14 0 33 47
chr12 25245347 rs112445441 974.64 C T PASS T missense_variant MODERATE KRAS p.Gly13Asp 41 ENST00000256078.10,ENST00000311936.8,ENST00000556131.2,ENST00000557334.6,ENST00000685328.1,ENST00000693229.1,ENST00000688940.1,ENST00000686969.1 0 14 0 33 47
33 changes: 22 additions & 11 deletions resolwe_bio/tests/files/report_variants/output/mutations_clinvar.tsv
View file
Original file line number Diff line number Diff line change
@@ -1,12 +1,23 @@
CHROM POS ID QUAL REF ALT DP CLNDN CLNSIG Allele Annotation Annotation_Impact Gene_Name HGVS.p SAMPLENAME1.GT Feature_ID Base_A Base_C Base_G Base_T Total_depth
chr12 25206394 rs1137189;308075 8699.05 A T 384 Noonan_syndrome Likely_benign T 3_prime_UTR_variant MODIFIER KRAS T/T ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206394 rs1137189;308075 8699.05 A T 384 Noonan_syndrome Likely_benign T downstream_gene_variant MODIFIER KRAS T/T ENST00000557334.5 0 0 0 0 0
chr12 25206418 rs1137188;308076 10865.059999999998 G A 344 Noonan_syndrome Likely_benign A 3_prime_UTR_variant MODIFIER KRAS A/A ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206418 rs1137188;308076 10865.059999999998 G A 344 Noonan_syndrome Likely_benign A downstream_gene_variant MODIFIER KRAS A/A ENST00000557334.5 0 0 0 0 0
chr12 25206530 rs34176876;308077 11672.029999999999 TA T 413 Noonan_syndrome Likely_benign T 3_prime_UTR_variant MODIFIER KRAS T/T ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206530 rs34176876;308077 11672.029999999999 TA T 413 Noonan_syndrome Likely_benign T downstream_gene_variant MODIFIER KRAS T/T ENST00000557334.5 0 0 0 0 0
chr12 25206907 rs13096;308082 9234.06 T C 337 Noonan_syndrome Likely_benign C 3_prime_UTR_variant MODIFIER KRAS C/C ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206907 rs13096;308082 9234.06 T C 337 Noonan_syndrome Likely_benign C downstream_gene_variant MODIFIER KRAS C/C ENST00000557334.5 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G intron_variant MODIFIER KRAS A/G ENST00000557334.5 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G synonymous_variant LOW KRAS p.Gly60Gly A/G ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25245348 rs121913535;45123 7936.639999999999 C A 337 Non-small_cell_lung_carcinoma|Neoplasm_of_the_large_intestine|Autoimmune_lymphoproliferative_syndrome_type_4|not_provided Pathogenic A missense_variant MODERATE KRAS p.Gly13Cys C/A ENST00000256078.9,ENST00000311936.8,ENST00000556131.1,ENST00000557334.5 0 48 0 0 48
chr12 25206394 rs1137189;308075 8699.05 A T 384 Noonan_syndrome Likely_benign T 3_prime_UTR_variant MODIFIER KRAS T/T ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25206394 rs1137189;308075 8699.05 A T 384 Noonan_syndrome Likely_benign T downstream_gene_variant MODIFIER KRAS T/T ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206394 rs1137189;308075 8699.05 A T 384 Noonan_syndrome Likely_benign T non_coding_transcript_exon_variant MODIFIER KRAS T/T ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206418 rs1137188;308076 10865.059999999998 G A 344 Noonan_syndrome Likely_benign A 3_prime_UTR_variant MODIFIER KRAS A/A ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25206418 rs1137188;308076 10865.059999999998 G A 344 Noonan_syndrome Likely_benign A downstream_gene_variant MODIFIER KRAS A/A ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206418 rs1137188;308076 10865.059999999998 G A 344 Noonan_syndrome Likely_benign A non_coding_transcript_exon_variant MODIFIER KRAS A/A ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206530 rs34176876;308077 11672.029999999999 TA T 413 Noonan_syndrome Likely_benign T 3_prime_UTR_variant MODIFIER KRAS T/T ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25206530 rs34176876;308077 11672.029999999999 TA T 413 Noonan_syndrome Likely_benign T downstream_gene_variant MODIFIER KRAS T/T ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206530 rs34176876;308077 11672.029999999999 TA T 413 Noonan_syndrome Likely_benign T non_coding_transcript_exon_variant MODIFIER KRAS T/T ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206907 rs13096;308082 9234.06 T C 337 Noonan_syndrome Likely_benign C non_coding_transcript_exon_variant MODIFIER KRAS C/C ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206907 rs13096;308082 9234.06 T C 337 Noonan_syndrome Likely_benign C downstream_gene_variant MODIFIER KRAS C/C ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206907 rs13096;308082 9234.06 T C 337 Noonan_syndrome Likely_benign C 3_prime_UTR_variant MODIFIER KRAS C/C ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G 3_prime_UTR_variant MODIFIER KRAS A/G ENST00000686877.1,ENST00000690804.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G 5_prime_UTR_variant MODIFIER KRAS A/G ENST00000692768.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G intron_variant MODIFIER KRAS A/G ENST00000557334.6,ENST00000687356.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G non_coding_transcript_exon_variant MODIFIER KRAS A/G ENST00000686877.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G splice_region_variant&intron_variant LOW KRAS A/G ENST00000693229.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G synonymous_variant LOW KRAS p.Gly60Gly A/G ENST00000256078.10,ENST00000311936.8,ENST00000685328.1,ENST00000688940.1 0 0 0 0 0
chr12 25227344 . 8356.64 A G 333 G upstream_gene_variant MODIFIER KRAS A/G ENST00000690406.1 0 0 0 0 0
chr12 25245348 rs121913535;45123 7936.639999999999 C A 337 Non-small_cell_lung_carcinoma|Neoplasm_of_the_large_intestine|Autoimmune_lymphoproliferative_syndrome_type_4|not_provided Pathogenic A intron_variant MODIFIER KRAS C/A ENST00000692768.1 0 48 0 0 48
chr12 25245348 rs121913535;45123 7936.639999999999 C A 337 Non-small_cell_lung_carcinoma|Neoplasm_of_the_large_intestine|Autoimmune_lymphoproliferative_syndrome_type_4|not_provided Pathogenic A missense_variant MODERATE KRAS p.Gly13Cys C/A ENST00000256078.10,ENST00000311936.8,ENST00000556131.2,ENST00000557334.6,ENST00000685328.1,ENST00000693229.1,ENST00000688940.1,ENST00000686969.1 0 48 0 0 48
chr12 25245348 rs121913535;45123 7936.639999999999 C A 337 Non-small_cell_lung_carcinoma|Neoplasm_of_the_large_intestine|Autoimmune_lymphoproliferative_syndrome_type_4|not_provided Pathogenic A non_coding_transcript_exon_variant MODIFIER KRAS C/A ENST00000686877.1,ENST00000687356.1,ENST00000690804.1 0 48 0 0 48
24 changes: 15 additions & 9 deletions resolwe_bio/tests/files/report_variants/output/no_mutations.tsv
View file
Original file line number Diff line number Diff line change
@@ -1,10 +1,16 @@
CHROM POS ID QUAL REF ALT FILTER Allele Annotation Annotation_Impact Gene_Name HGVS.p SAMPLENAME1.GT SAMPLENAME1.AD DP Feature_ID Base_A Base_C Base_G Base_T Total_depth
chr12 25205894 rs12587 323.05999999999995 T G PASS G 3_prime_UTR_variant MODIFIER KRAS G/G 0,11 11 ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25205894 rs12587 323.05999999999995 T G PASS G downstream_gene_variant MODIFIER KRAS G/G 0,11 11 ENST00000557334.5 0 0 0 0 0
chr12 25206009 rs8720 285.06 T C PASS C 3_prime_UTR_variant MODIFIER KRAS C/C 0,10 10 ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206009 rs8720 285.06 T C PASS C downstream_gene_variant MODIFIER KRAS C/C 0,10 10 ENST00000557334.5 0 0 0 0 0
chr12 25206394 rs1137189 200.85000000000002 A T PASS T 3_prime_UTR_variant MODIFIER KRAS A/T 1,8 9 ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25206394 rs1137189 200.85000000000002 A T PASS T downstream_gene_variant MODIFIER KRAS A/T 1,8 9 ENST00000557334.5 0 0 0 0 0
chr12 25207204 rs4963858 387.06000000000006 T C PASS C 3_prime_UTR_variant MODIFIER KRAS C/C 0,12 12 ENST00000256078.9,ENST00000311936.8 0 0 0 0 0
chr12 25207204 rs4963858 387.06000000000006 T C PASS C downstream_gene_variant MODIFIER KRAS C/C 0,12 12 ENST00000557334.5 0 0 0 0 0
chr12 25209283 rs9266 451.06 A G PASS G 3_prime_UTR_variant MODIFIER KRAS G/G 0,13 13 ENST00000256078.9,ENST00000311936.8,ENST00000557334.5 0 0 0 0 0
chr12 25205894 rs12587 323.05999999999995 T G PASS G 3_prime_UTR_variant MODIFIER KRAS G/G 0,11 11 ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25205894 rs12587 323.05999999999995 T G PASS G downstream_gene_variant MODIFIER KRAS G/G 0,11 11 ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25205894 rs12587 323.05999999999995 T G PASS G non_coding_transcript_exon_variant MODIFIER KRAS G/G 0,11 11 ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206009 rs8720 285.06 T C PASS C 3_prime_UTR_variant MODIFIER KRAS C/C 0,10 10 ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25206009 rs8720 285.06 T C PASS C downstream_gene_variant MODIFIER KRAS C/C 0,10 10 ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206009 rs8720 285.06 T C PASS C non_coding_transcript_exon_variant MODIFIER KRAS C/C 0,10 10 ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25206394 rs1137189 200.85000000000002 A T PASS T 3_prime_UTR_variant MODIFIER KRAS A/T 1,8 9 ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1 0 0 0 0 0
chr12 25206394 rs1137189 200.85000000000002 A T PASS T downstream_gene_variant MODIFIER KRAS A/T 1,8 9 ENST00000557334.6,ENST00000688940.1,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25206394 rs1137189 200.85000000000002 A T PASS T non_coding_transcript_exon_variant MODIFIER KRAS A/T 1,8 9 ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25207204 rs4963858 387.06000000000006 T C PASS C 3_prime_UTR_variant MODIFIER KRAS C/C 0,12 12 ENST00000256078.10,ENST00000311936.8,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1,ENST00000688940.1 0 0 0 0 0
chr12 25207204 rs4963858 387.06000000000006 T C PASS C downstream_gene_variant MODIFIER KRAS C/C 0,12 12 ENST00000557334.6,ENST00000690804.1,ENST00000688228.1 0 0 0 0 0
chr12 25207204 rs4963858 387.06000000000006 T C PASS C non_coding_transcript_exon_variant MODIFIER KRAS C/C 0,12 12 ENST00000690406.1,ENST00000686877.1,ENST00000687356.1 0 0 0 0 0
chr12 25209283 rs9266 451.06 A G PASS G 3_prime_UTR_variant MODIFIER KRAS G/G 0,13 13 ENST00000256078.10,ENST00000311936.8,ENST00000557334.6,ENST00000690406.1,ENST00000686877.1,ENST00000685328.1,ENST00000693229.1,ENST00000687356.1,ENST00000692768.1,ENST00000688940.1,ENST00000690804.1 0 0 0 0 0
chr12 25209283 rs9266 451.06 A G PASS G downstream_gene_variant MODIFIER KRAS G/G 0,13 13 ENST00000688228.1 0 0 0 0 0
chr12 25209283 rs9266 451.06 A G PASS G non_coding_transcript_exon_variant MODIFIER KRAS G/G 0,13 13 ENST00000690406.1,ENST00000686877.1,ENST00000687356.1,ENST00000690804.1 0 0 0 0 0
Loading

0 comments on commit 6ea1c05

Please sign in to comment.