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_vcf2maf/TCGA-A1-A0SB_db9d40fb-bfce-4c3b-a6c2-41c5c88982f1_a3254f8e-3bbd-42fc-abea-a5f25b7648b3.indel.capture.tcga.txt

 #version 2.4
 Hugo_Symbol	Entrez_Gene_Id	Center	NCBI_Build	Chromosome	Start_Position	End_Position	Strand	Variant_Classification	Variant_Type	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	dbSNP_RS	dbSNP_Val_Status	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Match_Norm_Seq_Allele1	Match_Norm_Seq_Allele2	Tumor_Validation_Allele1	Tumor_Validation_Allele2	Match_Norm_Validation_Allele1	Match_Norm_Validation_Allele2	Verification_Status	Validation_Status	Mutation_Status	Sequencing_Phase	Sequence_Source	Validation_Method	Score	BAM_File	Sequencer	Tumor_Sample_UUID	Matched_Norm_Sample_UUID	HGVSc	HGVSp	HGVSp_Short	Transcript_ID	Exon_Number	t_depth	t_ref_count	t_alt_count	n_depth	n_ref_count	n_alt_count	all_effects	Allele	Gene	Feature	Feature_type	Consequence	cDNA_position	CDS_position	Protein_position	Amino_acids	Codons	Existing_variation	ALLELE_NUM	DISTANCE	STRAND_VEP	SYMBOL	SYMBOL_SOURCE	HGNC_ID	BIOTYPE	CANONICAL	CCDS	ENSP	SWISSPROT	TREMBL	UNIPARC	RefSeq	SIFT	PolyPhen	EXON	INTRON	DOMAINS	AF	AFR_AF	AMR_AF	ASN_AF	EAS_AF	EUR_AF	SAS_AF	AA_AF	EA_AF	CLIN_SIG	SOMATIC	PUBMED	MOTIF_NAME	MOTIF_POS	HIGH_INF_POS	MOTIF_SCORE_CHANGE	IMPACT	PICK	VARIANT_CLASS	TSL	HGVS_OFFSET	PHENO	MINIMISED	ExAC_AF	ExAC_AF_AFR	ExAC_AF_AMR	ExAC_AF_EAS	ExAC_AF_FIN	ExAC_AF_NFE	ExAC_AF_OTH	ExAC_AF_SAS	GENE_PHENO	FILTER	flanking_bps	vcf_id	vcf_qual	ExAC_AF_Adj	ExAC_AC_AN_Adj	ExAC_AC_AN	ExAC_AC_AN_AFR	ExAC_AC_AN_AMR	ExAC_AC_AN_EAS	ExAC_AC_AN_FIN	ExAC_AC_AN_NFE	ExAC_AC_AN_OTH	ExAC_AC_AN_SAS	ExAC_FILTER	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	vcf_pos
-FAM131C	348487	.	GRCh37	1	16386305	16386306	+	Intron	INS	-	-	C	rs372070031		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	-	-																c.451+58dup			ENST00000375662								FAM131C,intron_variant,,ENST00000375662,NM_182623.2;CLCNKB,downstream_gene_variant,,ENST00000375667,NM_001165945.2;CLCNKB,downstream_gene_variant,,ENST00000375679,NM_000085.4;CLCNKB,downstream_gene_variant,,ENST00000431772,;FAM131C,intron_variant,,ENST00000494078,;	C	ENSG00000185519	ENST00000375662	Transcript	intron_variant						rs372070031	1		-1	FAM131C	HGNC	26717	protein_coding	YES	CCDS41270.1	ENSP00000364814	Q96AQ9		UPI000022B016	NM_182623.2				5/6			0.2731	0.3573		0.3581	0.3757	0.5051										MODIFIER	1	insertion														PASS	GGC	rs143272992	50																					16386305
-ZIC4	84107	.	GRCh37	3	147121630	147121631	+	Intron	DEL	TC	TC	-	rs142316820		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	TC	TC																c.135+120_135+121del			ENST00000525172								ZIC4,intron_variant,,ENST00000383075,NM_032153.5;ZIC4,intron_variant,,ENST00000425731,NM_001168379.1;ZIC4,intron_variant,,ENST00000462748,;ZIC4,intron_variant,,ENST00000463250,;ZIC4,intron_variant,,ENST00000473123,;ZIC4,intron_variant,,ENST00000484399,;ZIC1,intron_variant,,ENST00000488404,;ZIC4,intron_variant,,ENST00000491672,NM_001243256.1;ZIC4,intron_variant,,ENST00000525172,NM_001168378.1;ZIC4,upstream_gene_variant,,ENST00000484586,;ZIC1,intron_variant,,ENST00000472523,;ZIC4,downstream_gene_variant,,ENST00000464144,;	-	ENSG00000174963	ENST00000525172	Transcript	intron_variant						rs142316820	1		-1	ZIC4	HGNC	20393	protein_coding	YES	CCDS54652.1	ENSP00000435509	Q8N9L1	C9JZU7,C9JD04,C9J6T3,B3KPI4	UPI0001914D88	NM_001168378.1				1/4																		MODIFIER	1	deletion													1	PASS	GATCT	.	50																					147121629
-EIF4G1	1981	.	GRCh37	3	184043926	184043927	+	Intron	DEL	AC	AC	-	rs34901174		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	AC	AC																c.3243+217_3243+218del			ENST00000424196								EIF4G1,intron_variant,,ENST00000319274,;EIF4G1,intron_variant,,ENST00000342981,NM_182917.4;EIF4G1,intron_variant,,ENST00000346169,NM_198241.2;EIF4G1,intron_variant,,ENST00000350481,NM_198242.2;EIF4G1,intron_variant,,ENST00000352767,NM_001194947.1;EIF4G1,intron_variant,,ENST00000382330,NM_001194946.1;EIF4G1,intron_variant,,ENST00000392537,NM_198244.2;EIF4G1,intron_variant,,ENST00000411531,;EIF4G1,intron_variant,,ENST00000414031,;EIF4G1,intron_variant,,ENST00000424196,;EIF4G1,intron_variant,,ENST00000427845,;EIF4G1,intron_variant,,ENST00000434061,NM_004953.4;EIF4G1,intron_variant,,ENST00000435046,;EIF4G1,intron_variant,,ENST00000441154,;EIF2B5,intron_variant,,ENST00000444495,;EIF4G1,intron_variant,,ENST00000448284,;EIF4G1,downstream_gene_variant,,ENST00000421110,;EIF4G1,downstream_gene_variant,,ENST00000426123,;EIF4G1,downstream_gene_variant,,ENST00000427607,;EIF4G1,downstream_gene_variant,,ENST00000428387,;EIF4G1,downstream_gene_variant,,ENST00000444134,;EIF4G1,downstream_gene_variant,,ENST00000444861,;EIF4G1,downstream_gene_variant,,ENST00000450424,;EIF4G1,downstream_gene_variant,,ENST00000457456,;SNORD66,downstream_gene_variant,,ENST00000390856,NR_003055.1;EIF4G1,intron_variant,,ENST00000442406,;EIF4G1,intron_variant,,ENST00000466311,;EIF4G1,downstream_gene_variant,,ENST00000413967,;EIF4G1,upstream_gene_variant,,ENST00000422614,;EIF4G1,upstream_gene_variant,,ENST00000460829,;EIF4G1,upstream_gene_variant,,ENST00000464548,;EIF4G1,upstream_gene_variant,,ENST00000475721,;EIF4G1,upstream_gene_variant,,ENST00000482303,;EIF4G1,downstream_gene_variant,,ENST00000484862,;EIF4G1,downstream_gene_variant,,ENST00000493299,;	-	ENSG00000114867	ENST00000424196	Transcript	intron_variant						rs34901174	1		1	EIF4G1	HGNC	3296	protein_coding	YES	CCDS54687.1	ENSP00000416255	Q04637	Q96I65,C9JWW9,C9JWH7,C9JSU8,C9J987,C9J6B6,C9J556	UPI00015E0966					20/31																		MODIFIER	1	deletion													1	PASS	AAACA	rs112208190	50																					184043925
-STEAP1B	256227	.	GRCh37	7	22533452	22533453	+	Frame_Shift_Del	DEL	CA	CA	-	novel		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	CA	CA																c.87_88del	p.His29GlnfsTer24	p.H29Qfs*24	ENST00000404369	3/5							STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000404369,NM_001164460.1;STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000424363,;STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000439708,;STEAP1B,intron_variant,,ENST00000406890,NM_207342.2;STEAP1B,splice_region_variant,,ENST00000483679,;	-	ENSG00000105889	ENST00000404369	Transcript	frameshift_variant,splice_region_variant	503-504/1515	87-88/1029	29-30/342	HE/QX	caTGag/caag		1		-1	STEAP1B	HGNC	41907	protein_coding	YES	CCDS56469.1	ENSP00000384370		C9JL51,C9JE84,B5MCI2	UPI000173A267	NM_001164460.1			3/5		PANTHER:PTHR14239:SF3,PANTHER:PTHR14239																	HIGH	1	deletion														PASS	CTCAT	rs116873396	50																					22533451
-TEX12	56158	.	GRCh37	11	112042480	112042480	+	Intron	DEL	T	T	-	rs1225064086		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	T	T																c.228-9del			ENST00000280358								TEX12,intron_variant,,ENST00000280358,NM_031275.4;TEX12,intron_variant,,ENST00000530752,;AP002884.3,intron_variant,,ENST00000532612,;BCO2,upstream_gene_variant,,ENST00000357685,;BCO2,upstream_gene_variant,,ENST00000361053,NM_001256398.1;BCO2,upstream_gene_variant,,ENST00000393032,NM_031938.5;BCO2,upstream_gene_variant,,ENST00000438022,;BCO2,upstream_gene_variant,,ENST00000526088,NM_001037290.2,NM_001256397.1;BCO2,upstream_gene_variant,,ENST00000531169,;BCO2,upstream_gene_variant,,ENST00000532593,NM_001256400.1;RP11-356J5.4,intron_variant,,ENST00000527589,;SDHD,intron_variant,,ENST00000525468,;SDHD,intron_variant,,ENST00000525987,;SDHD,intron_variant,,ENST00000531744,;SDHD,intron_variant,,ENST00000532699,;BCO2,upstream_gene_variant,,ENST00000460924,;BCO2,upstream_gene_variant,,ENST00000461480,;BCO2,upstream_gene_variant,,ENST00000494860,;BCO2,upstream_gene_variant,,ENST00000527939,;BCO2,upstream_gene_variant,,ENST00000531003,;BCO2,upstream_gene_variant,,ENST00000534122,;BCO2,upstream_gene_variant,,ENST00000534550,;	-	ENSG00000150783	ENST00000280358	Transcript	intron_variant						rs1225064086	1		1	TEX12	HGNC	11734	protein_coding	YES	CCDS31679.1	ENSP00000280358	Q9BXU0		UPI00001377E3	NM_031275.4				4/4																		MODIFIER	1	deletion														PASS	ACTT	.	50												1.711e-05	8.319e-05			8.285e-05		1.133e-05			112042479
-KMT2D	8085	.	GRCh37	12	49431403	49431404	+	Frame_Shift_Ins	INS	-	-	T	novel		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	-	-																c.9735dup	p.Pro3246ThrfsTer5	p.P3246Tfs*5	ENST00000301067	34/54							KMT2D,frameshift_variant,p.Pro3246ThrfsTer5,ENST00000301067,NM_003482.3;KMT2D,upstream_gene_variant,,ENST00000549743,;KMT2D,downstream_gene_variant,,ENST00000549799,;	T	ENSG00000167548	ENST00000301067	Transcript	frameshift_variant	9735-9736/19419	9735-9736/16614	3245-3246/5537	-/X	-/A		1		-1	KMT2D	HGNC	7133	protein_coding	YES	CCDS44873.1	ENSP00000301067	O14686	Q6PIA1,Q59FG6,F8VWW4	UPI0000EE84D6	NM_003482.3			34/54		PANTHER:PTHR22884,PANTHER:PTHR22884:SF324																	HIGH	1	insertion													1	PASS	GGT	.	50																					49431403
-PDS5B	23047	.	GRCh37	13	33332314	33332314	+	Frame_Shift_Del	DEL	A	A	-	novel		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	A	A																c.3148del	p.Thr1050GlnfsTer12	p.T1050Qfs*12	ENST00000315596	27/35							PDS5B,frameshift_variant,p.Thr1050GlnfsTer12,ENST00000315596,NM_015032.3;PDS5B,frameshift_variant,p.Thr4GlnfsTer12,ENST00000447833,;PDS5B,frameshift_variant,p.Thr1050GlnfsTer12,ENST00000450460,;	-	ENSG00000083642	ENST00000315596	Transcript	frameshift_variant	3332/7497	3146/4344	1049/1447	Q/X	cAa/ca		1		1	PDS5B	HGNC	20418	protein_coding	YES	CCDS41878.1	ENSP00000313851	Q9NTI5		UPI000006D4A9	NM_015032.3			27/35		PANTHER:PTHR12663,PANTHER:PTHR12663:SF1																	HIGH	1	deletion		2												PASS	ACAA	.	50																					33332313
-CCR7	1236	.	GRCh37	17	38712161	38712161	+	Intron	DEL	T	T	-	rs372297045		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	T	T																c.61-91del			ENST00000246657								CCR7,intron_variant,,ENST00000246657,NM_001838.3;CCR7,intron_variant,,ENST00000578085,;CCR7,intron_variant,,ENST00000579344,;	-	ENSG00000126353	ENST00000246657	Transcript	intron_variant						rs372297045	1		-1	CCR7	HGNC	1608	protein_coding	YES	CCDS11369.1	ENSP00000246657	P32248	J3KTN5,J3KSS9,A0N0Q0	UPI0000001C2F	NM_001838.3				2/2						0.004												MODIFIER	1	deletion													1	PASS	TCTT	.	50																					38712160
-ATP9A	10079	.	GRCh37	20	50342307	50342308	+	Intron	DEL	TC	TC	-	novel		TCGA-A1-A0SB-01A-11D-A142-09	TCGA-A1-A0SB-10B-01D-A142-09	TC	TC																c.327+50_327+51del			ENST00000338821								ATP9A,intron_variant,,ENST00000311637,;ATP9A,intron_variant,,ENST00000338821,NM_006045.1;ATP9A,intron_variant,,ENST00000402822,;ATP9A,downstream_gene_variant,,ENST00000477492,;,regulatory_region_variant,,ENSR00001644001,;	-	ENSG00000054793	ENST00000338821	Transcript	intron_variant							1		-1	ATP9A	HGNC	13540	protein_coding	YES	CCDS33489.1	ENSP00000342481	O75110	Q2NLD0,B4DR18	UPI000004D334	NM_006045.1				3/27																		MODIFIER	1	deletion														PASS	TTTCT	.	50																					50342306
+FAM131C	348487	.	GRCh37	1	16386305	16386306	+	Intron	INS	-	-	C	rs372070031		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	-	-																c.451+58dup			ENST00000375662								FAM131C,intron_variant,,ENST00000375662,NM_182623.2;CLCNKB,downstream_gene_variant,,ENST00000375667,NM_001165945.2;CLCNKB,downstream_gene_variant,,ENST00000375679,NM_000085.4;CLCNKB,downstream_gene_variant,,ENST00000431772,;FAM131C,intron_variant,,ENST00000494078,;	C	ENSG00000185519	ENST00000375662	Transcript	intron_variant						rs372070031	1		-1	FAM131C	HGNC	26717	protein_coding	YES	CCDS41270.1	ENSP00000364814	Q96AQ9		UPI000022B016	NM_182623.2				5/6			0.2731	0.3573		0.3581	0.3757	0.5051										MODIFIER	1	insertion														PASS	GGC	rs143272992	50																					16386305
+ZIC4	84107	.	GRCh37	3	147121630	147121631	+	Intron	DEL	TC	TC	-	rs142316820		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	TC	TC																c.135+120_135+121del			ENST00000525172								ZIC4,intron_variant,,ENST00000383075,NM_032153.5;ZIC4,intron_variant,,ENST00000425731,NM_001168379.1;ZIC4,intron_variant,,ENST00000462748,;ZIC4,intron_variant,,ENST00000463250,;ZIC4,intron_variant,,ENST00000473123,;ZIC4,intron_variant,,ENST00000484399,;ZIC1,intron_variant,,ENST00000488404,;ZIC4,intron_variant,,ENST00000491672,NM_001243256.1;ZIC4,intron_variant,,ENST00000525172,NM_001168378.1;ZIC4,upstream_gene_variant,,ENST00000484586,;ZIC1,intron_variant,,ENST00000472523,;ZIC4,downstream_gene_variant,,ENST00000464144,;	-	ENSG00000174963	ENST00000525172	Transcript	intron_variant						rs142316820	1		-1	ZIC4	HGNC	20393	protein_coding	YES	CCDS54652.1	ENSP00000435509	Q8N9L1	C9JZU7,C9JD04,C9J6T3,B3KPI4	UPI0001914D88	NM_001168378.1				1/4																		MODIFIER	1	deletion													1	PASS	GATCT	.	50																					147121629
+EIF4G1	1981	.	GRCh37	3	184043926	184043927	+	Intron	DEL	AC	AC	-	rs34901174		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	AC	AC																c.3243+217_3243+218del			ENST00000424196								EIF4G1,intron_variant,,ENST00000319274,;EIF4G1,intron_variant,,ENST00000342981,NM_182917.4;EIF4G1,intron_variant,,ENST00000346169,NM_198241.2;EIF4G1,intron_variant,,ENST00000350481,NM_198242.2;EIF4G1,intron_variant,,ENST00000352767,NM_001194947.1;EIF4G1,intron_variant,,ENST00000382330,NM_001194946.1;EIF4G1,intron_variant,,ENST00000392537,NM_198244.2;EIF4G1,intron_variant,,ENST00000411531,;EIF4G1,intron_variant,,ENST00000414031,;EIF4G1,intron_variant,,ENST00000424196,;EIF4G1,intron_variant,,ENST00000427845,;EIF4G1,intron_variant,,ENST00000434061,NM_004953.4;EIF4G1,intron_variant,,ENST00000435046,;EIF4G1,intron_variant,,ENST00000441154,;EIF2B5,intron_variant,,ENST00000444495,;EIF4G1,intron_variant,,ENST00000448284,;EIF4G1,downstream_gene_variant,,ENST00000421110,;EIF4G1,downstream_gene_variant,,ENST00000426123,;EIF4G1,downstream_gene_variant,,ENST00000427607,;EIF4G1,downstream_gene_variant,,ENST00000428387,;EIF4G1,downstream_gene_variant,,ENST00000444134,;EIF4G1,downstream_gene_variant,,ENST00000444861,;EIF4G1,downstream_gene_variant,,ENST00000450424,;EIF4G1,downstream_gene_variant,,ENST00000457456,;SNORD66,downstream_gene_variant,,ENST00000390856,NR_003055.1;EIF4G1,intron_variant,,ENST00000442406,;EIF4G1,intron_variant,,ENST00000466311,;EIF4G1,downstream_gene_variant,,ENST00000413967,;EIF4G1,upstream_gene_variant,,ENST00000422614,;EIF4G1,upstream_gene_variant,,ENST00000460829,;EIF4G1,upstream_gene_variant,,ENST00000464548,;EIF4G1,upstream_gene_variant,,ENST00000475721,;EIF4G1,upstream_gene_variant,,ENST00000482303,;EIF4G1,downstream_gene_variant,,ENST00000484862,;EIF4G1,downstream_gene_variant,,ENST00000493299,;	-	ENSG00000114867	ENST00000424196	Transcript	intron_variant						rs34901174	1		1	EIF4G1	HGNC	3296	protein_coding	YES	CCDS54687.1	ENSP00000416255	Q04637	Q96I65,C9JWW9,C9JWH7,C9JSU8,C9J987,C9J6B6,C9J556	UPI00015E0966					20/31																		MODIFIER	1	deletion													1	PASS	AAACA	rs112208190	50																					184043925
+STEAP1B	256227	.	GRCh37	7	22533452	22533453	+	Frame_Shift_Del	DEL	CA	CA	-	novel		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	CA	CA																c.87_88del	p.His29GlnfsTer24	p.H29Qfs*24	ENST00000404369	3/5							STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000404369,NM_001164460.1;STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000424363,;STEAP1B,frameshift_variant,p.His29GlnfsTer24,ENST00000439708,;STEAP1B,intron_variant,,ENST00000406890,NM_207342.2;STEAP1B,splice_region_variant,,ENST00000483679,;	-	ENSG00000105889	ENST00000404369	Transcript	frameshift_variant,splice_region_variant	503-504/1515	87-88/1029	29-30/342	HE/QX	caTGag/caag		1		-1	STEAP1B	HGNC	41907	protein_coding	YES	CCDS56469.1	ENSP00000384370		C9JL51,C9JE84,B5MCI2	UPI000173A267	NM_001164460.1			3/5		PANTHER:PTHR14239:SF3,PANTHER:PTHR14239																	HIGH	1	deletion														PASS	CTCAT	rs116873396	50																					22533451
+TEX12	56158	.	GRCh37	11	112042480	112042480	+	Intron	DEL	T	T	-	rs1225064086		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	T	T																c.228-9del			ENST00000280358								TEX12,intron_variant,,ENST00000280358,NM_031275.4;TEX12,intron_variant,,ENST00000530752,;AP002884.3,intron_variant,,ENST00000532612,;BCO2,upstream_gene_variant,,ENST00000357685,;BCO2,upstream_gene_variant,,ENST00000361053,NM_001256398.1;BCO2,upstream_gene_variant,,ENST00000393032,NM_031938.5;BCO2,upstream_gene_variant,,ENST00000438022,;BCO2,upstream_gene_variant,,ENST00000526088,NM_001037290.2,NM_001256397.1;BCO2,upstream_gene_variant,,ENST00000531169,;BCO2,upstream_gene_variant,,ENST00000532593,NM_001256400.1;RP11-356J5.4,intron_variant,,ENST00000527589,;SDHD,intron_variant,,ENST00000525468,;SDHD,intron_variant,,ENST00000525987,;SDHD,intron_variant,,ENST00000531744,;SDHD,intron_variant,,ENST00000532699,;BCO2,upstream_gene_variant,,ENST00000460924,;BCO2,upstream_gene_variant,,ENST00000461480,;BCO2,upstream_gene_variant,,ENST00000494860,;BCO2,upstream_gene_variant,,ENST00000527939,;BCO2,upstream_gene_variant,,ENST00000531003,;BCO2,upstream_gene_variant,,ENST00000534122,;BCO2,upstream_gene_variant,,ENST00000534550,;	-	ENSG00000150783	ENST00000280358	Transcript	intron_variant						rs1225064086	1		1	TEX12	HGNC	11734	protein_coding	YES	CCDS31679.1	ENSP00000280358	Q9BXU0		UPI00001377E3	NM_031275.4				4/4																		MODIFIER	1	deletion														PASS	ACTT	.	50												1.711e-05	8.319e-05			8.285e-05		1.133e-05			112042479
+KMT2D	8085	.	GRCh37	12	49431403	49431404	+	Frame_Shift_Ins	INS	-	-	T	novel		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	-	-																c.9735dup	p.Pro3246ThrfsTer5	p.P3246Tfs*5	ENST00000301067	34/54							KMT2D,frameshift_variant,p.Pro3246ThrfsTer5,ENST00000301067,NM_003482.3;KMT2D,upstream_gene_variant,,ENST00000549743,;KMT2D,downstream_gene_variant,,ENST00000549799,;	T	ENSG00000167548	ENST00000301067	Transcript	frameshift_variant	9735-9736/19419	9735-9736/16614	3245-3246/5537	-/X	-/A		1		-1	KMT2D	HGNC	7133	protein_coding	YES	CCDS44873.1	ENSP00000301067	O14686	Q6PIA1,Q59FG6,F8VWW4	UPI0000EE84D6	NM_003482.3			34/54		PANTHER:PTHR22884,PANTHER:PTHR22884:SF324																	HIGH	1	insertion													1	PASS	GGT	.	50																					49431403
+PDS5B	23047	.	GRCh37	13	33332314	33332314	+	Frame_Shift_Del	DEL	A	A	-	novel		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	A	A																c.3148del	p.Thr1050GlnfsTer12	p.T1050Qfs*12	ENST00000315596	27/35							PDS5B,frameshift_variant,p.Thr1050GlnfsTer12,ENST00000315596,NM_015032.3;PDS5B,frameshift_variant,p.Thr4GlnfsTer12,ENST00000447833,;PDS5B,frameshift_variant,p.Thr1050GlnfsTer12,ENST00000450460,;	-	ENSG00000083642	ENST00000315596	Transcript	frameshift_variant	3332/7497	3146/4344	1049/1447	Q/X	cAa/ca		1		1	PDS5B	HGNC	20418	protein_coding	YES	CCDS41878.1	ENSP00000313851	Q9NTI5		UPI000006D4A9	NM_015032.3			27/35		PANTHER:PTHR12663,PANTHER:PTHR12663:SF1																	HIGH	1	deletion		2												PASS	ACAA	.	50																					33332313
+CCR7	1236	.	GRCh37	17	38712161	38712161	+	Intron	DEL	T	T	-	rs372297045		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	T	T																c.61-91del			ENST00000246657								CCR7,intron_variant,,ENST00000246657,NM_001838.3;CCR7,intron_variant,,ENST00000578085,;CCR7,intron_variant,,ENST00000579344,;	-	ENSG00000126353	ENST00000246657	Transcript	intron_variant						rs372297045	1		-1	CCR7	HGNC	1608	protein_coding	YES	CCDS11369.1	ENSP00000246657	P32248	J3KTN5,J3KSS9,A0N0Q0	UPI0000001C2F	NM_001838.3				2/2						0.004												MODIFIER	1	deletion													1	PASS	TCTT	.	50																					38712160
+ATP9A	10079	.	GRCh37	20	50342307	50342308	+	Intron	DEL	TC	TC	-	novel		TCGA-A1-A0SD-01A-11D-A10Y-09	TCGA-A1-A0SD-10A-01D-A110-09	TC	TC																c.327+50_327+51del			ENST00000338821								ATP9A,intron_variant,,ENST00000311637,;ATP9A,intron_variant,,ENST00000338821,NM_006045.1;ATP9A,intron_variant,,ENST00000402822,;ATP9A,downstream_gene_variant,,ENST00000477492,;,regulatory_region_variant,,ENSR00001644001,;	-	ENSG00000054793	ENST00000338821	Transcript	intron_variant							1		-1	ATP9A	HGNC	13540	protein_coding	YES	CCDS33489.1	ENSP00000342481	O75110	Q2NLD0,B4DR18	UPI000004D334	NM_006045.1				3/27																		MODIFIER	1	deletion														PASS	TTTCT	.	50																					50342306

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