reorganize repo to have python package 'variant_annotator'

.coveragerc

-[run]
-omit = */__init__.py

.gitignore

-# Project specific
-/htmlcov/
-
 # Logs 
 log/
 *.log
-*.coverage
 
-# Mac anc Vim specific
+# Mac specific
 .DS_Store
 .DS_Store?
 
 # Python
 __pycache__/
+*.pyc
+
+# Python test
+*.pytest_cache
+*.coverage
+*.egg-info/
+*htmlcov/
 
 # Open cached files 
 *.m~

.travis.yml

+language: python
+os:
+  - linux
+  - osx
+python:
+  - 3.6
+  - 3.7
+  - 3.8
+  - nightly
+
+after_success:
+  - julia -e 'using Pkg; cd(Pkg.dir("MyPkg")); Pkg.add("Coverage"); using Coverage; Codecov.submit(Codecov.process_folder())'
+  - bash <(curl -s https://codecov.io/bash)
+
+branches:
+  only:
+    - master
+    - /^dev/
+
+jobs:
+  allow_failures:
+  - julia: nightly

Makefile

+PYTHON ?= python
+PYTEST ?= pytest
+CTAGS ?= ctags
+
+init:
+	pip install -r requirements.txt
+
+test:
+	$(PYTEST) --cov-config=.coveragerc --cov-report term-missing --cov variant_annotator variant_annotator
+
+ctags:
+	$(CTAGS) --python-kinds=-i --exclude=*/tests/* variant_annotator
+
+clean:
+	rm -f tags

env.yml

-name: 3.8_bt_variant
-channels:
-  - anaconda
-  - defaults
-dependencies:
-  - coverage=5.0
-  - ipython=7.17.0
-  - numpy=1.19.1
-  - pandas=1.1.0
-  - pytest=6.0.1
-  - pytest-cov=2.10.0
-  - python=3.8.5

examples/results/TCGA_GA/tmp/out_vep/TCGA-A1-A0SB_db9d40fb-bfce-4c3b-a6c2-41c5c88982f1_a3254f8e-3bbd-42fc-abea-a5f25b7648b3.indel.capture.tcga.txt

 ## ENSEMBL VARIANT EFFECT PREDICTOR v101.0
-## Output produced at 2020-09-02 10:28:24
+## Output produced at 2020-10-30 16:15:42
 ## Using cache in /Users/ypradat/.vep/homo_sapiens/101_GRCh37
 ## Using API version 101, DB version ?
 ## ensembl-funcgen version 101.b918a49
 ## ensembl-io version 101.943b6c2
-## ensembl version 101.856c8e8
 ## ensembl-variation version 101.851c7e0
-## polyphen version 2.2.2
-## ClinVar version 201912
-## regbuild version 1.0
-## COSMIC version 90
+## ensembl version 101.856c8e8
+## gnomAD version r2.1
+## dbSNP version 153
 ## gencode version GENCODE 19
+## genebuild version 2011-04
+## ESP version 20141103
 ## assembly version GRCh37.p13
-## sift version sift5.2.2
 ## 1000genomes version phase3
-## ESP version 20141103
+## ClinVar version 201912
 ## HGMD-PUBLIC version 20194
-## gnomAD version r2.1
-## genebuild version 2011-04
-## dbSNP version 153
+## sift version sift5.2.2
+## polyphen version 2.2.2
+## regbuild version 1.0
+## COSMIC version 90
 ## Column descriptions:
 ## Uploaded_variation : Identifier of uploaded variant
 ## Location : Location of variant in standard coordinate format (chr:start or chr:start-end)

examples/results/TCGA_GA/tmp/tmp_vcf2maf/TCGA-A1-A0SB_db9d40fb-bfce-4c3b-a6c2-41c5c88982f1_a3254f8e-3bbd-42fc-abea-a5f25b7648b3.indel.capture.tcga.vep.vcf

@@ -30,7 +30,7 @@
 ##INFO=<ID=VLSC,Number=1,Type=Integer,Description="Final somatic score between 0 and 255 when multiple lines of evidence are available">
 ##FILTER=<ID=mf1,Description="Filtered out by MuTect v.1">
 ##FILTER=<ID=oxoG3,Description="Filtered out by OxoG Artifact Filter v3">
-##VEP="v101" time="2020-09-02 10:32:28" cache="/Users/ypradat/.vep/homo_sapiens/101_GRCh37" ensembl-variation=101.851c7e0 ensembl=101.856c8e8 ensembl-io=101.943b6c2 ensembl-funcgen=101.b918a49 1000genomes="phase3" COSMIC="90" ClinVar="201912" ESP="20141103" HGMD-PUBLIC="20194" assembly="GRCh37.p13" dbSNP="153" gencode="GENCODE 19" genebuild="2011-04" gnomAD="r2.1" polyphen="2.2.2" regbuild="1.0" sift="sift5.2.2"
+##VEP="v101" time="2020-10-30 16:15:38" cache="/Users/ypradat/.vep/homo_sapiens/101_GRCh37" ensembl-variation=101.851c7e0 ensembl-io=101.943b6c2 ensembl-funcgen=101.b918a49 ensembl=101.856c8e8 1000genomes="phase3" COSMIC="90" ClinVar="201912" ESP="20141103" HGMD-PUBLIC="20194" assembly="GRCh37.p13" dbSNP="153" gencode="GENCODE 19" genebuild="2011-04" gnomAD="r2.1" polyphen="2.2.2" regbuild="1.0" sift="sift5.2.2"
 ##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence annotations from Ensembl VEP. Format: Allele|Consequence|IMPACT|SYMBOL|Gene|Feature_type|Feature|BIOTYPE|EXON|INTRON|HGVSc|HGVSp|cDNA_position|CDS_position|Protein_position|Amino_acids|Codons|Existing_variation|ALLELE_NUM|DISTANCE|STRAND|FLAGS|PICK|VARIANT_CLASS|SYMBOL_SOURCE|HGNC_ID|CANONICAL|TSL|CCDS|ENSP|SWISSPROT|TREMBL|UNIPARC|RefSeq|GENE_PHENO|SIFT|PolyPhen|DOMAINS|HGVS_OFFSET|AF|AFR_AF|AMR_AF|EAS_AF|EUR_AF|SAS_AF|AA_AF|EA_AF|gnomAD_AF|gnomAD_AFR_AF|gnomAD_AMR_AF|gnomAD_ASJ_AF|gnomAD_EAS_AF|gnomAD_FIN_AF|gnomAD_NFE_AF|gnomAD_OTH_AF|gnomAD_SAS_AF|CLIN_SIG|SOMATIC|PHENO|PUBMED|MOTIF_NAME|MOTIF_POS|HIGH_INF_POS|MOTIF_SCORE_CHANGE|TRANSCRIPTION_FACTORS">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	PRIMARY
 1	16386305	rs143272992	G	GC	50	PASS	DB;DP=17;Gene=FAM131C;MQ0=0;SOMATIC;SS=Somatic;VC=Intron;VT=INS;TID=ENST00000375662.4;VLSC=255;CSQ=C|intron_variant|MODIFIER|FAM131C|ENSG00000185519|Transcript|ENST00000375662|protein_coding||5/6|ENST00000375662.4:c.451+58dup|||||||rs372070031|1||-1||1|insertion|HGNC|26717|YES||CCDS41270.1|ENSP00000364814|Q96AQ9||UPI000022B016|NM_182623.2|||||||0.2731|0.3573|0.3581|0.3757|0.5051||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|CLCNKB|ENSG00000184908|Transcript|ENST00000375667|protein_coding||||||||||rs372070031|1|2502|1|||insertion|HGNC|2027|||CCDS57974.1|ENSP00000364819|P51801||UPI000046FF10|NM_001165945.2|1||||||0.2731|0.3573|0.3581|0.3757|0.5051||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|CLCNKB|ENSG00000184908|Transcript|ENST00000375679|protein_coding||||||||||rs372070031|1|2502|1|||insertion|HGNC|2027|YES||CCDS168.1|ENSP00000364831|P51801||UPI000040E261|NM_000085.4|1||||||0.2731|0.3573|0.3581|0.3757|0.5051||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|CLCNKB|ENSG00000184908|Transcript|ENST00000431772|protein_coding||||||||||rs372070031|1|2502|1|cds_start_NF||insertion|HGNC|2027||||ENSP00000389344||Q5T5Q6|UPI000046FF11||1||||||0.2731|0.3573|0.3581|0.3757|0.5051||||||||||||||||||||,C|intron_variant&non_coding_transcript_variant|MODIFIER|FAM131C|ENSG00000185519|Transcript|ENST00000494078|processed_transcript||4/5|ENST00000494078.1:n.525+58dup|||||||rs372070031|1||-1|||insertion|HGNC|26717|||||||||||||||0.2731|0.3573|0.3581|0.3757|0.5051||||||||||||||||||||	GT:AD:DP:FA:MQ0:BQ:SS:SSC	0/0:11,0:11:0.000:0:.:2:.	0/1:4,2:6:0.333:0:.:2:.

examples/results/TCGA_GA/tmp/tmp_vcf2maf/TCGA-A1-A0SB_db9d40fb-bfce-4c3b-a6c2-41c5c88982f1_a3254f8e-3bbd-42fc-abea-a5f25b7648b3.oxoG.snp.capture.tcga.vep.vcf

@@ -30,7 +30,7 @@
 ##INFO=<ID=VLSC,Number=1,Type=Integer,Description="Final somatic score between 0 and 255 when multiple lines of evidence are available">
 ##FILTER=<ID=mf1,Description="Filtered out by MuTect v.1">
 ##FILTER=<ID=oxoG3,Description="Filtered out by OxoG Artifact Filter v3">
-##VEP="v101" time="2020-09-02 10:32:33" cache="/Users/ypradat/.vep/homo_sapiens/101_GRCh37" ensembl-funcgen=101.b918a49 ensembl=101.856c8e8 ensembl-variation=101.851c7e0 ensembl-io=101.943b6c2 1000genomes="phase3" COSMIC="90" ClinVar="201912" ESP="20141103" HGMD-PUBLIC="20194" assembly="GRCh37.p13" dbSNP="153" gencode="GENCODE 19" genebuild="2011-04" gnomAD="r2.1" polyphen="2.2.2" regbuild="1.0" sift="sift5.2.2"
+##VEP="v101" time="2020-10-30 14:50:25" cache="/Users/ypradat/.vep/homo_sapiens/101_GRCh37" ensembl-variation=101.851c7e0 ensembl-io=101.943b6c2 ensembl=101.856c8e8 ensembl-funcgen=101.b918a49 1000genomes="phase3" COSMIC="90" ClinVar="201912" ESP="20141103" HGMD-PUBLIC="20194" assembly="GRCh37.p13" dbSNP="153" gencode="GENCODE 19" genebuild="2011-04" gnomAD="r2.1" polyphen="2.2.2" regbuild="1.0" sift="sift5.2.2"
 ##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence annotations from Ensembl VEP. Format: Allele|Consequence|IMPACT|SYMBOL|Gene|Feature_type|Feature|BIOTYPE|EXON|INTRON|HGVSc|HGVSp|cDNA_position|CDS_position|Protein_position|Amino_acids|Codons|Existing_variation|ALLELE_NUM|DISTANCE|STRAND|FLAGS|PICK|VARIANT_CLASS|SYMBOL_SOURCE|HGNC_ID|CANONICAL|TSL|CCDS|ENSP|SWISSPROT|TREMBL|UNIPARC|RefSeq|GENE_PHENO|SIFT|PolyPhen|DOMAINS|HGVS_OFFSET|AF|AFR_AF|AMR_AF|EAS_AF|EUR_AF|SAS_AF|AA_AF|EA_AF|gnomAD_AF|gnomAD_AFR_AF|gnomAD_AMR_AF|gnomAD_ASJ_AF|gnomAD_EAS_AF|gnomAD_FIN_AF|gnomAD_NFE_AF|gnomAD_OTH_AF|gnomAD_SAS_AF|CLIN_SIG|SOMATIC|PHENO|PUBMED|MOTIF_NAME|MOTIF_POS|HIGH_INF_POS|MOTIF_SCORE_CHANGE|TRANSCRIPTION_FACTORS">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	PRIMARY
 1	44476442	.	C	T	43	PASS	DP=127;Gene=SLC6A9;MQ0=0;SOMATIC;SS=Somatic;VC=5'UTR;VT=SNP;TID=ENST00000372307.3;VLSC=255;CSQ=T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000357730|protein_coding|2/13||ENST00000357730.2:c.200G>A|ENSP00000350362.2:p.Gly67Asp|392/2168|200/1959|67/652|G/D|gGc/gAc|COSV62211565|1||-1|||SNV|HGNC|11056|||CCDS41316.1|ENSP00000350362|P48067|E9PJ65&B7Z589&B7Z3W8|UPI000053030A|NM_006934.3&NM_001261380.1|1|deleterious(0)|probably_damaging(0.999)|Transmembrane_helices:TMhelix&PROSITE_profiles:PS50267&PANTHER:PTHR11616&PANTHER:PTHR11616:SF110&Pfam:PF00209&Superfamily:0053687&Prints:PR00176||||||||||||||||||||1|1||||||,T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000360584|protein_coding|3/14||ENST00000360584.2:c.362G>A|ENSP00000353791.2:p.Gly121Asp|554/2330|362/2121|121/706|G/D|gGc/gAc|COSV62211565|1||-1||1|SNV|HGNC|11056|YES||CCDS41317.1|ENSP00000353791|P48067|B7Z589|UPI000053030B|NM_201649.3|1|deleterious(0)|probably_damaging(1)|Transmembrane_helices:TMhelix&PROSITE_profiles:PS50267&PANTHER:PTHR11616:SF110&PANTHER:PTHR11616&Pfam:PF00209&Superfamily:0053687&Prints:PR00176||||||||||||||||||||1|1||||||,T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000372306|protein_coding|3/12||ENST00000372306.3:c.143G>A|ENSP00000361380.3:p.Gly48Asp|283/1926|143/1740|48/579|G/D|gGc/gAc|COSV62211565|1||-1|||SNV|HGNC|11056||||ENSP00000361380||J3KPA5|UPI0001F7803E||1|deleterious(0)|probably_damaging(0.993)|Transmembrane_helices:TMhelix&PROSITE_profiles:PS50267&PANTHER:PTHR11616&PANTHER:PTHR11616:SF110&Pfam:PF00209&Superfamily:0053687&Prints:PR00176||||||||||||||||||||1|1||||||,T|5_prime_UTR_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000372307|protein_coding|2/12||ENST00000372307.3:c.-53G>A||276/2162|||||COSV62211565|1||-1|||SNV|HGNC|11056||||ENSP00000361381||B7Z3A9|UPI0001914B58||1|||||||||||||||||||||||1|1||||||,T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000372310|protein_coding|3/14||ENST00000372310.3:c.143G>A|ENSP00000361384.3:p.Gly48Asp|309/3130|143/1902|48/633|G/D|gGc/gAc|COSV62211565|1||-1|||SNV|HGNC|11056|||CCDS30695.1|ENSP00000361384|P48067|B7Z589|UPI0000204F05|NM_001024845.2|1|deleterious(0)|probably_damaging(0.999)|Transmembrane_helices:TMhelix&PROSITE_profiles:PS50267&PANTHER:PTHR11616:SF110&PANTHER:PTHR11616&Pfam:PF00209&Superfamily:0053687&Prints:PR00176||||||||||||||||||||1|1||||||,T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000466926|protein_coding|4/4||ENST00000466926.1:c.305G>A|ENSP00000433241.1:p.Gly102Asp|547/591|305/349|102/116|G/D|gGc/gAc|COSV62211565|1||-1|cds_end_NF||SNV|HGNC|11056||||ENSP00000433241||E9PLM5|UPI0001F78040||1|deleterious(0)|probably_damaging(1)|Superfamily:0053687&Pfam:PF00209&PANTHER:PTHR11616&PANTHER:PTHR11616:SF110&PROSITE_profiles:PS50267||||||||||||||||||||1|1||||||,T|intron_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000475075|protein_coding||2/11|ENST00000475075.2:c.-14-2147G>A|||||||COSV62211565|1||-1|||SNV|HGNC|11056||||ENSP00000434460||B7Z589|UPI0001914EDD||1|||||||||||||||||||||||1|1||||||,T|non_coding_transcript_exon_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000489764|retained_intron|3/3||ENST00000489764.1:n.352G>A||352/930|||||COSV62211565|1||-1|||SNV|HGNC|11056|||||||||1|||||||||||||||||||||||1|1||||||,T|intron_variant&non_coding_transcript_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000492434|processed_transcript||3/4|ENST00000492434.2:n.351+39G>A|||||||COSV62211565|1||-1|||SNV|HGNC|11056|||||||||1|||||||||||||||||||||||1|1||||||,T|missense_variant|MODERATE|SLC6A9|ENSG00000196517|Transcript|ENST00000528803|protein_coding|3/5||ENST00000528803.1:c.200G>A|ENSP00000435652.1:p.Gly67Asp|321/524|200/403|67/134|G/D|gGc/gAc|COSV62211565|1||-1|cds_end_NF||SNV|HGNC|11056||||ENSP00000435652||E9PJ65|UPI0001F7803F||1|deleterious(0)|probably_damaging(0.999)|PROSITE_profiles:PS50267&PANTHER:PTHR11616:SF110&PANTHER:PTHR11616&Pfam:PF00209&Superfamily:0053687&Prints:PR00176||||||||||||||||||||1|1||||||,T|downstream_gene_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000533007|processed_transcript||||||||||COSV62211565|1|3860|-1|||SNV|HGNC|11056|||||||||1|||||||||||||||||||||||1|1||||||,T|intron_variant|MODIFIER|SLC6A9|ENSG00000196517|Transcript|ENST00000537678|protein_coding||2/10|ENST00000537678.1:c.-8-674G>A|||||||COSV62211565|1||-1|||SNV|HGNC|11056||||ENSP00000442523||B7Z9G8|UPI000191543C||1|||||||||||||||||||||||1|1||||||	GT:AD:DP:FA:MQ0:BQ:SS:SSC	0/0:69,0:69:0.000:0:.:2:.	0/1:42,16:58:0.276:0:31:2:.

meta.yaml

-{% set name = "bt_variant_annotator" %}
-{% set version = "0.99" %}
-
-package:
-  name: "{{ name|lower }}"
-  version: "{{ version }}"
-
-source:
-  git_rev: v0.99
-  git_url: https://github.com/durzot/bt_variant_annotator.git
-
-requirements:
-  run:
-    - python>=3.5
-    - numpy>=1.11.0
-    - pandas>=1.0.0
-
-build:
-  number: 0
-  script: python setup.py install --single-version-externally-managed --record=record.txt
-
-about:
-  home: https://github.com/durzot/bt_variant_annotator 
-  license: MIT
-  license_family: MIT
-  license_file: 'LICENSE'
-  summary: VCF annotator
-  description: VCF annotator
-  dev_url: https://github.com/durzot/bt_variant_annotator

requirements.txt

+numpy>=1.14.0
+pandas>=0.23.0

setup.py

+from setuptools import setup
+
+setup(
+    name = "variant_annotator",
+    version = "1.0.0",
+    author = "Yoann Pradat",
+    author_email = "yoann.pradat@centralesupelec.fr",
+    install_requires = [
+        "numpy",
+        "pandas",
+    ],
+)

src/.coveragerc

+[run]
+omit = */__init__.py, *tests*

src/variant_annotator/__init__.py

+"""
+The :mod:`variant_annotator` module defines functions for annotating variants using a combination of manual, vep and
+vcf2maf annotations.
+"""
+
+from ._main import run_annotator
+from ._manual import run_manual_annotator
+from ._vcf2maf import run_vcf2maf_annotator
+from ._vep import run_vep_annotator
+
+__all__ = [
+    'run_annotator',
+    'run_manual_annotator',
+    'run_vcf2maf_annotator',
+    'run_vep_annotator'
+]
+

src/main.py → src/variant_annotator/_main.py

 # -*- coding: utf-8 -*-
 """
-Created on Thu Aug 13 2020
-
+@created: Aug 13 2020
+@modified: Oct 30 2020
 @author: Yoann Pradat
 
     CentraleSupelec
@@ -15,9 +15,9 @@ import numpy  as np
 import pandas as pd
 from   typing import Union
 
-from   .manual  import run_manual_annotator
-from   .vcf2maf import run_vcf2maf_annotator
-from   .vep     import run_vep_annotator
+from   ._manual  import run_manual_annotator
+from   ._vcf2maf import run_vcf2maf_annotator
+from   ._vep     import run_vep_annotator
 
 DataFrame = pd.core.frame.DataFrame
 
@@ -71,8 +71,8 @@ class Vcf2mafConfig:
     overwrite: bool=False
 
 def run_annotator(vcf_folder: str, vcf_file: str, col_normal: str, col_tumor: str, tumor_id: str, normal_id: str,
-                  infos_n_reads: list, infos_other: list, dt_folders: dict, vcf2maf_config: Vcf2mafConfig,
-                  vep_config: VepConfig, dt_identifiers: dict=None) -> None:
+                      infos_n_reads: list, infos_other: list, dt_folders: dict, vcf2maf_config: Vcf2mafConfig,
+                      vep_config: VepConfig, dt_identifiers: dict=None) -> None:
     """
     Run the manual, vcf2maf and/or vep annotations on one VCF file and assemble.
 

src/manual.py → src/variant_annotator/_manual.py

 # -*- coding: utf-8 -*-
 """
-Created on Thu Aug 13 2020
-
+@created: Aug 13 2020
+@modified: Oct 30 220
 @author: Yoann Pradat
-
     CentraleSupelec
     MICS laboratory
     9 rue Juliot Curie, Gif-Sur-Yvette, 91190 France
@@ -16,7 +15,7 @@ import numpy  as np
 import pandas as pd
 import re
 
-from .util import load_vcf
+from ._util import load_vcf
 
 DataFrame = pd.core.frame.DataFrame
 
@@ -294,7 +293,6 @@ def process_assemble(df_vcf: DataFrame, df_vcf_info: DataFrame, df_vcf_reads: Da
 def run_manual_annotator(vcf_path: str, out_path:str,  col_normal: str, col_tumor: str, infos_n_reads: list, infos_other: list):
     """
     Manually parse VCF file and save at the path specified.
-
     Paramters
     ---------
     vcf_path: str

src/util.py → src/variant_annotator/_util.py

 # -*- coding: utf-8 -*-
 """
 Created on Thu Aug 13 2020
-
 @author: Yoann Pradat
-
     CentraleSupelec
     MICS laboratory
     9 rue Juliot Curie, Gif-Sur-Yvette, 91190 France
-
 Useful functions
 """
 
@@ -46,14 +43,12 @@ def get_path_to_repo() -> str:
 def load_vcf(filepath: str, no_header: bool=False) -> DataFrame:
     """
     Load VCF file from the specified filepath into a pandas DataFrame.
-
     Parameters
     ----------
     filepath:  str
         Path to the file.
     no_header:  bool
         If True, set column names to default names.
-
     Returns
     -------
     df: DataFrame
@@ -61,7 +56,7 @@ def load_vcf(filepath: str, no_header: bool=False) -> DataFrame:
     """
 
     if not os.path.exists(filepath):
-        raise ValueError("The file %s does not exist.")
+        raise ValueError("The file %s does not exist." % filepath)
     else:
         if no_header:
             df_vcf = pd.read_csv(

src/vcf2maf.py → src/variant_annotator/_vcf2maf.py

 # -*- coding: utf-8 -*-
 """
-Created on Thu Aug 13 2020
-
+@created: Aug 13 2020
+@modified: Oct 30 2020
 @author: Yoann Pradat
-
     CentraleSupelec
     MICS laboratory
     9 rue Juliot Curie, Gif-Sur-Yvette, 91190 France
@@ -12,12 +11,11 @@ Python wrapper around vcf2maf perl script.
 """
 
 import os
-from  .util import get_path_to_repo
+from  ._util import get_path_to_repo
 
 def run_vcf2maf_annotator(vep_data: str, vep_n_fork: int, vcf_path: str, out_path: str, tmp_folder: str, tumor_id: str, normal_id: str, fasta: str, overwrite: bool=False):
     """
     Run vcf2maf reannotator. Details may found at https://github.com/mskcc/vcf2maf.
-
     Parameters
     ----------
     vep_data: str

src/vep.py → src/variant_annotator/_vep.py

 # -*- coding: utf-8 -*-
 """
-Created on Thu Aug 13 2020
-
+@created: Aug 13 2020
+@modified: Oct 30 2020
 @author: Yoann Pradat
-
     CentraleSupelec
     MICS laboratory
     9 rue Juliot Curie, Gif-Sur-Yvette, 91190 France
-
 Python wrapper around VEP command.
 """
 
 import os
-from   typing import Union
-from   .util  import get_path_to_repo
+from typing import Union
+from ._util import get_path_to_repo
 
 def run_vep_annotator(vep_data: str, vcf_path: str, out_path: str, fasta: str, vep_custom: Union[str,list]=None, overwrite: bool=False, vep_n_fork: int=4):
     """
     Run variant ensembl predictor alone with custom options. See options details at
     https://www.ensembl.org/info/docs/tools/vep/script/vep_options.html#opt_af
-
     Parameters
     ---------
     vep_data: str

src/tests/test_main.py → src/variant_annotator/tests/test_main.py

 # -*- coding: utf-8 -*-
 """
-Created on Thu Aug 13 2020
-
+@created: Aug 13 2020
+@modified: Oct 30 2020
 @author: Yoann Pradat
 
     CentraleSupelec
@@ -12,9 +12,10 @@ Test functions from vep module.
 """
 
 import os
-from ..main import run_annotator
-from ..main import VepConfig
-from ..main import Vcf2mafConfig
+from .._util import set_wd_to_repo
+from .._main import run_annotator
+from .._main import VepConfig
+from .._main import Vcf2mafConfig
 
 def test_main():
     vep_config = VepConfig(
@@ -29,6 +30,8 @@ def test_main():
         overwrite = True
     )
 
+    current_wd = set_wd_to_repo()
+
     #### # 1. TCGA GA
     #### # ########################################################################################################
 

src/tests/test_manual.py → src/variant_annotator/tests/test_manual.py

@@ -12,9 +12,11 @@ Test functions from manual module.
 """
 
 import os
-from ..manual import run_manual_annotator
+from .._util import set_wd_to_repo
+from .._manual import run_manual_annotator
 
 def test_manual():
+    current_wd = set_wd_to_repo()
 
     #### # 1. TCGA GA
     #### # ########################################################################################################

src/tests/test_util.py → src/variant_annotator/tests/test_util.py

@@ -12,7 +12,7 @@ Test functions in util.py module.
 """
 
 import os
-from ..util import load_vcf
+from .._util import load_vcf
 
 def test_load_vcf():
     folder = "./examples/data/TCGA_GA/"

src/tests/test_vcf2maf.py → src/variant_annotator/tests/test_vcf2maf.py

@@ -12,13 +12,16 @@ Test functions from vcf2maf module.
 """
 
 import os
-from ..vcf2maf import run_vcf2maf_annotator
+from .._util import set_wd_to_repo
+from .._vcf2maf import run_vcf2maf_annotator
 
 def test_vcf2maf():
     vep_data     = "~/.vep"
     vep_n_fork   = 4
     fasta        = "~/.vep/homo_sapiens/99_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa"
 
+    current_wd = set_wd_to_repo()
+
     #### # 1. TCGA GA
     #### # ########################################################################################################
 

src/tests/test_vep.py → src/variant_annotator/tests/test_vep.py

@@ -12,13 +12,16 @@ Test functions from vep module.
 """
 
 import os
-from ..vep import run_vep_annotator
+from .._util import set_wd_to_repo
+from .._vep import run_vep_annotator
 
 def test_vep():
     vep_data   = "~/.vep"
     vep_n_fork = 4
     fasta      = "~/.vep/homo_sapiens/99_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa"
 
+    current_wd = set_wd_to_repo()
+
     #### # 1. TCGA GA
     #### # ########################################################################################################
 

variant_annotator/__init__.py

+"""
+The :mod:`variant_annotator` module defines functions for annotating variants using a combination of manual, vep and
+vcf2maf annotations.
+"""
+
+from ._main import run_annotator
+from ._manual import run_manual_annotator
+from ._vcf2maf import run_vcf2maf_annotator
+from ._vep import run_vep_annotator
+
+__all__ = [
+    'run_annotator',
+    'run_manual_annotator',
+    'run_vcf2maf_annotator',
+    'run_vep_annotator'
+]
+

variant_annotator/_main.py

+# -*- coding: utf-8 -*-
+"""
+@created: Aug 13 2020
+@modified: Oct 30 2020
+@author: Yoann Pradat
+
+    CentraleSupelec
+    MICS laboratory
+    9 rue Juliot Curie, Gif-Sur-Yvette, 91190 France
+
+Main functions for running each step and the assembling step.
+"""
+import os
+import numpy  as np
+import pandas as pd
+from   typing import Union
+
+from   ._manual  import run_manual_annotator
+from   ._vcf2maf import run_vcf2maf_annotator
+from   ._vep     import run_vep_annotator
+
+DataFrame = pd.core.frame.DataFrame
+
+#### # FUNCTION FOR ONE VCF
+#### # #######################################################################################################
+
+from dataclasses import dataclass, field
+
+@dataclass
+class VepConfig:
+    """
+    Config for running VEP inside VCF2MAF and separately (custom options, optional).
+
+    Parameters
+    --------
+    data: str
+        path to the .vep data where the reference genome is located. Default: $HOME/.vep
+    fasta: str
+        relative path to fasta file from folder. Default
+        "$HOME/.vep/homo_sapiens/101_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa"
+    n_fork: int, optional.
+        number of forks to be used when running VEP. Use at least 2.
+    custom_run: bool, optional
+        set to True to run VEP separately from vcf2maf.
+    custom_opt: str or list, optional.
+        additional options to add to the vep cmd. For instance
+        '--custom ~/.vep/custom/ClinVar/clinvar.vcf.gz,ClinVar,vcf,exact,0,CLNSIG,CLNREVSTAT,CLNDN'
+    custom_overwrite: bool, optional.
+        set to True to overwrite any existing previous custom run of VEP.
+    """
+    data: str=os.path.expanduser("~/.vep")
+    fasta: str=os.path.expanduser("~/.vep/homo_sapiens/101_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa")
+    n_fork: int=4
+    custom_run: bool=False
+    custom_opt: Union[str, list]=None
+    custom_overwrite: bool=False
+
+@dataclass
+class Vcf2mafConfig:
+    """
+    Run vcf2maf. For VEP-related options, see VepConfig class.
+
+    Parameters
+    --------
+    run: bool, optional
+        set to False to not use vcf2maf.
+    overwrite: bool, optional.
+        set to True to overwrite any existing previous run of vcf2maf.
+    """
+    run: bool=True
+    overwrite: bool=False
+
+def run_annotator(vcf_folder: str, vcf_file: str, col_normal: str, col_tumor: str, tumor_id: str, normal_id: str,
+                      infos_n_reads: list, infos_other: list, dt_folders: dict, vcf2maf_config: Vcf2mafConfig,
+                      vep_config: VepConfig, dt_identifiers: dict=None) -> None:
+    """
+    Run the manual, vcf2maf and/or vep annotations on one VCF file and assemble.
+
+    Parameters
+    --------
+    vcf_file: str
+        name of the vcf file
+    vcf_folder: str
+        path to the folder where the vcf is
+    col_normal: str
+        name of the column in the vcf for the normal sample
+    col_tumor: str
+        name of the column in the vcf for the tumor sample
+    infos_n_reads: list
+        list of sigles that contain read info
+    infos_other: list
+        list of sigles that need extraction
+    dt_folders: dict
+        dict with the following keys:
+            * manual_out_folder
+            * vcf2maf_tmp_folder
+            * vcf2maf_out_folder
+            * vep_out_folder
+            * maf_folder
+    vcf2maf_config: object
+        See Vcf2mafConfig class.
+    vep_config: object
+        See VepConfig class.
+    dt_identifiers: dict, optional
+        dict with key, value pairs that will be added as single-value columns in the maf file
+    """
+    vcf_path = os.path.join(vcf_folder, vcf_file)
+    out_file = vcf_file.replace(".vcf", ".txt")
+
+    #### # 1. RUN EACH ANNOTATOR
+    #### # ###################################################################################################
+
+    manual_out_path  = os.path.join(dt_folders["manual_out_folder"], out_file)
+    run_manual_annotator(
+        vcf_path      = vcf_path,
+        out_path      = manual_out_path,
+        col_normal    = col_normal,
+        col_tumor     = col_tumor,
+        infos_n_reads = infos_n_reads,
+        infos_other   = infos_other
+    )
+
+    if vcf2maf_config.run:
+        vcf2maf_out_path = os.path.join(dt_folders["vcf2maf_out_folder"], out_file)
+        run_vcf2maf_annotator(
+            vep_data     = vep_config.data,
+            vep_n_fork   = vep_config.n_fork,
+            vcf_path     = vcf_path,
+            out_path     = vcf2maf_out_path,
+            tmp_folder   = dt_folders["vcf2maf_tmp_folder"],
+            tumor_id     = tumor_id,
+            normal_id    = normal_id,
+            fasta        = vep_config.fasta,
+            overwrite    = vcf2maf_config.overwrite
+        )
+
+    if vep_config.custom_run:
+        vep_out_path     = os.path.join(dt_folders["vep_out_folder"], out_file)
+        run_vep_annotator(
+            vep_data   = vep_config.data,
+            vep_n_fork = vep_config.n_fork,
+            vcf_path   = vcf_path,
+            out_path   = vep_out_path,
+            fasta      = vep_config.fasta,
+            vep_custom = vep_config.custom_opt,
+            overwrite  = vep_config.custom_overwrite,
+        )
+
+    #### # 2. ASSEMBLE ANNOTATIONS
+    #### ######################################################################################################
+
+    ddf_maf = {}
+
+    #### vep manual
+    ddf_maf["manual"] = pd.read_csv(