ecc2331000637cbc2523653642d926935b5b83fc chmalee Sat Jun 13 00:42:03 2026 -0700 gnomAD v4.1.1 bigBed variant track for hg38, refs #37351 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> diff --git src/hg/makeDb/gnomad/gnomadVcfBedToBigBed src/hg/makeDb/gnomad/gnomadVcfBedToBigBed index 30026e5231d..40d0beb2374 100755 --- src/hg/makeDb/gnomad/gnomadVcfBedToBigBed +++ src/hg/makeDb/gnomad/gnomadVcfBedToBigBed @@ -12,42 +12,64 @@ 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|VARIANT_CLASS|MINIMISED\ |SYMBOL_SOURCE|HGNC_ID|CANONICAL|TSL|APPRIS|CCDS|ENSP|SWISSPROT|TREMBL|UNIPARC\ |GENE_PHENO|SIFT|PolyPhen|DOMAINS|HGVS_OFFSET|GMAF|AFR_MAF|AMR_MAF|EAS_MAF|EUR_MAF\ |SAS_MAF|AA_MAF|EA_MAF|ExAC_MAF|ExAC_Adj_MAF|ExAC_AFR_MAF|ExAC_AMR_MAF|ExAC_EAS_MAF\ |ExAC_FIN_MAF|ExAC_NFE_MAF|ExAC_OTH_MAF|ExAC_SAS_MAF|CLIN_SIG|SOMATIC|PHENO|PUBMED\ |MOTIF_NAME|MOTIF_POS|HIGH_INF_POS|MOTIF_SCORE_CHANGE|LoF|LoF_filter|LoF_flags|LoF_info"> """ import sys, argparse, hashlib,json from collections import defaultdict,namedtuple,OrderedDict # which version of gnomAD for parsing VEP string -versions = ["v2.1.1", "v3.1", "v3.1_chrM", "v3.1.1"] +versions = ["v2.1.1", "v3.1", "v3.1_chrM", "v3.1.1", "v4.1_genomes", "v4.1_exomes"] # the number of fields in the VEP string (depends on version): # how to count: # bcftools view -h in.vcf.gz | grep "^##INFO=<ID=vep" | grep -o "Format:.*" \ # | tr '|' '\t' | tl0 | wc -l -numVepFields = {"v2.1.1" : 68, "v3.1": 45, "v3.1_chrM": 45, "v3.1.1": 45} +# there are extra empty fields at the end of each vep annotation in v4.0: +# https://discuss.gnomad.broadinstitute.org/t/invalid-info-field-vep-in-gnomad-v4-vcfs/95/3 +numVepFields = {"v2.1.1" : 68, "v3.1": 45, "v3.1_chrM": 45, "v3.1.1": 45, "v4.1_exomes": 46, "v4.1_genomes": 46} # the different pipe separated fields in the VEP struct # how to get: # bcftools view -h in.vcf.gz | grep "^##INFO=<ID=vep" | grep -o "Format: .*" \ # | cut -d' ' -f2- | cut -d'"' -f1 | sed -e 's/^/"/' -e 's/$/"/' -e 's/|/", "/g' versionVepFields = { + "v4.1_exomes" : [ + "Allele", "Consequence", "IMPACT", "SYMBOL", "Gene", "Feature_type", + "Feature", "BIOTYPE", "EXON", "INTRON", "HGVSc", "HGVSp", "cDNA_position", + "CDS_position", "Protein_position", "Amino_acids", "Codons", "ALLELE_NUM", + "DISTANCE", "STRAND", "FLAGS", "VARIANT_CLASS", "SYMBOL_SOURCE", "HGNC_ID", + "CANONICAL", "MANE_SELECT", "MANE_PLUS_CLINICAL", "TSL", "APPRIS", "CCDS", + "ENSP", "UNIPROT_ISOFORM", "SOURCE", "DOMAINS", "miRNA", "HGVS_OFFSET", + "PUBMED", "MOTIF_NAME", "MOTIF_POS", "HIGH_INF_POS", "MOTIF_SCORE_CHANGE", + "TRANSCRIPTION_FACTORS", "LoF", "LoF_filter", "LoF_flags", "LoF_info" + ], + "v4.1_genomes" : [ + "Allele", "Consequence", "IMPACT", "SYMBOL", "Gene", "Feature_type", + "Feature", "BIOTYPE", "EXON", "INTRON", "HGVSc", "HGVSp", "cDNA_position", + "CDS_position", "Protein_position", "Amino_acids", "Codons", "ALLELE_NUM", + "DISTANCE", "STRAND", "FLAGS", "VARIANT_CLASS", "SYMBOL_SOURCE", "HGNC_ID", + "CANONICAL", "MANE_SELECT", "MANE_PLUS_CLINICAL", "TSL", "APPRIS", "CCDS", + "ENSP", "UNIPROT_ISOFORM", "SOURCE", "DOMAINS", "miRNA", "HGVS_OFFSET", + "PUBMED", "MOTIF_NAME", "MOTIF_POS", "HIGH_INF_POS", "MOTIF_SCORE_CHANGE", + "TRANSCRIPTION_FACTORS", "LoF", "LoF_filter", "LoF_flags", "LoF_info" + ], "v3.1.1": [ "Allele", "Consequence", "IMPACT", "SYMBOL", "Gene", "Feature_type", "Feature", "BIOTYPE", "EXON", "INTRON", "HGVSc", "HGVSp", "cDNA_position", "CDS_position", "Protein_position", "Amino_acids", "Codons", "ALLELE_NUM", "DISTANCE", "STRAND", "VARIANT_CLASS", "MINIMISED", "SYMBOL_SOURCE", "HGNC_ID", "CANONICAL", "TSL", "APPRIS", "CCDS", "ENSP", "SWISSPROT", "TREMBL", "UNIPARC", "GENE_PHENO", "SIFT", "PolyPhen", "DOMAINS", "HGVS_OFFSET", "MOTIF_NAME", "MOTIF_POS", "HIGH_INF_POS", "MOTIF_SCORE_CHANGE", "LoF", "LoF_filter", "LoF_flags", "LoF_info" ], "v3.1_chrM": [ "Allele", "Consequence", "IMPACT", "SYMBOL", "Gene", "Feature_type", "Feature", "BIOTYPE", "EXON", "INTRON", "HGVSc", "HGVSp", "cDNA_position", "CDS_position", "Protein_position", "Amino_acids", "Codons", "ALLELE_NUM", "DISTANCE", "STRAND", "VARIANT_CLASS", "MINIMISED", "SYMBOL_SOURCE", "HGNC_ID", "CANONICAL", "TSL", @@ -71,86 +93,104 @@ "Feature", "BIOTYPE", "EXON", "INTRON", "HGVSc", "HGVSp", "cDNA_position", "CDS_position", "Protein_position", "Amino_acids", "Codons", "Existing_variation", "ALLELE_NUM", "DISTANCE", "STRAND", "FLAGS", "VARIANT_CLASS", "MINIMISED", "SYMBOL_SOURCE", "HGNC_ID", "CANONICAL", "TSL", "APPRIS", "CCDS", "ENSP", "SWISSPROT", "TREMBL", "UNIPARC", "GENE_PHENO", "SIFT", "PolyPhen", "DOMAINS", "HGVS_OFFSET", "GMAF", "AFR_MAF", "AMR_MAF", "EAS_MAF", "EUR_MAF", "SAS_MAF", "AA_MAF", "EA_MAF", "ExAC_MAF", "ExAC_Adj_MAF", "ExAC_AFR_MAF", "ExAC_AMR_MAF", "ExAC_EAS_MAF", "ExAC_FIN_MAF", "ExAC_NFE_MAF", "ExAC_OTH_MAF", "ExAC_SAS_MAF", "CLIN_SIG", "SOMATIC", "PHENO", "PUBMED", "MOTIF_NAME", "MOTIF_POS", "HIGH_INF_POS", "MOTIF_SCORE_CHANGE", "LoF", "LoF_filter", "LoF_flags", "LoF_info" ] } versionPops = { + "v4.1_exomes": ["afr", "amr", "asj", "eas", "fin", "mid", "nfe", "sas", "remaining", "XX", "XY"], + "v4.1_genomes": ["afr", "ami", "amr", "asj", "eas", "fin", "mid", "nfe", "sas", "remaining", "XX", "XY"], "v3.1.1": ["afr", "ami", "amr", "asj", "eas", "fin", "mid", "nfe", "sas", "oth", "XX", "XY"], "v3.1_chrM": ['afr', 'ami', 'amr', 'asj', 'eas', 'fin', 'nfe', 'oth', 'sas', 'mid'], "v3.1": ["afr", "amr", "asj", "eas", "fin", "mid", "ami", "nfe", "sas", "oth", "XX", "XY"], "v2.1.1":["afr", "amr", "asj", "eas", "fin", "nfe", "sas", "oth"] } chrM_haplo_groups = [ 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'HV', 'I', 'J', 'K', 'L0', 'L1', 'L2', 'L3', 'L4', 'L5', 'M', 'N', 'P', 'R', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z' ] # the fields that MUST be in the bigBed (for filters, etc) versionAutoSql = { + "v4.1_exomes": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", + "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", + "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", + "_startPos", "displayName", "grpmax", "AC_grpmax", "AN_grpmax", "AF_grpmax", + "nhomaltX", "nhemi"], + "v4.1_genomes": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", + "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", + "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", + "_startPos", "displayName", "grpmax", "AC_grpmax", "AN_grpmax", "AF_grpmax", + "nhomaltX", "nhemi"], "v3.1.1": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", "_startPos", "displayName"], "v3.1_chrM": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", "_startPos", "displayName"], "v3.1": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", "_startPos", "displayName"], "v2.1.1": ["chrom", "chromStart", "chromEnd", "name", "score", "strand", "thickStart", "thickEnd", "itemRgb", "ref", "alt", "FILTER", "AC", "AN", "AF", "faf95", "nhomalt", "rsId", "genes", "annot", "variation_type", - "_startPos", "displayName", "pLoF", "lofFlags", "lofCuration", "pLoFCurationFlags"] + "pLoF", "lofFlags", "lofCuration", "pLoFCurationFlags", "_startPos", "displayName"] } # the fields in the extra tab file, specify order here so we have the same order # across different runs for different chromosomes versionExtraFields = { + "v4.1_exomes": ["_key", "_jsonVep", "_jsonPopTable", "cadd_phred", "cadd_raw_score", + "revel_max", "spliceai_ds_max", "segdup", "variant_type", "allele_type", "sift_max", + "pangolin_largest_ds", "polyphen_max"], + "v4.1_genomes": ["_key", "_jsonVep", "_jsonPopTable", "cadd_phred", "cadd_raw_score", + "revel_max", "spliceai_ds_max", "segdup", "variant_type", "allele_type", "sift_max", + "pangolin_largest_ds", "polyphen_max"], "v3.1.1": ["_key", "_jsonVep", "_jsonPopTable", "cadd_phred", "revel_score", "splice_ai_max_ds", "splice_ai_consequence", "primate_ai_score"], "v3.1_chrM": ["_key", "_jsonVep", "_jsonPopTable", "_jsonHapTable"], "v3.1": ["hgvsc", "hgvsp", "popmax", *[x + "_" + y for y in ["popmax", "afr", "ami", "amr", "asj", "eas", "fin", "mid", "nfe", "sas", "oth", "XX", "XY"] for x in ["AC", "AN", "AF", "nhomalt"]], "cadd_phred", "revel_score", "splice_ai_max_ds", "splice_ai_consequence", "primate_ai_score"], - "v2.1.1": ["hgvsc", "hgvsp", "popmax", "AC_popmax", "AN_popmax", "AF_popmax", - *[x + "_" + y for y in ["afr", "amr", "asj", "eas", "fin", "nfe", "oth", - "female", "male"] for x in ["AC", "AN", "AF", "nhomalt"]]] + "v2.1.1": ["hgvsc", "hgvsp", "popmax", *[x + "_" + y for y in ["popmax", "afr", "amr", + "asj", "eas", "fin", "nfe", "oth", "female", "male"] for x in ["AC", "AN", "AF", + "nhomalt"]]] } # determines the color of the variant in the browser plofTypes = ["frameshift", "stop gained", "splice donor", "splice acceptor"] -missenseTypes = ["missense", "inframe deletion", "inframe insertion", "start lost", "stop list"] +missenseTypes = ["missense", "inframe deletion", "inframe insertion", "start lost", "stop lost"] synTypes = ["synonymous"] # for printing the name of the popmax: -popAbbr = {"afr": "African/African American", "amr": "Latino/Admixed American", - "asj": "Ashkenazi Jewish", "eas": "East Asian", "fin": "Finnish", +popAbbr = {"afr": "African/African American", "ami": "Amish", "amr": "Admixed American", + "asj": "Ashkenazi Jewish", "eas": "East Asian", "fin": "European (Finnish)", "mid": "Middle Eastern", "ami": "Amish", - "nfe": "Non-Finnish European", "sas": "South Asian", "oth": "Other (population not assigned)"} + "nfe": "European (Non-Finnish)", "sas": "South Asian", "remaining": "Population Not Assigned", "oth": "Other (population not assigned)"} lofDesc = {"HC": "High-confidence", "OS": "Other Splice (beta)", "LC": "Low-confidence"} header = None def parseCommandLine(): parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter, description="""Transform gnomAD VCF to bigBed. This looks something like: vcfToBed -fields="list,of,info,fields" in.vcf.gz firstOut.bed gnomadVcfBedToBigBed -v v2.1.1 -lof lofFile.txt firstOut.bed finalOut.bed""", ) parser.add_argument("infile", help="Input bed file with a vep field, use 'stdin' to read \ from stdin") parser.add_argument("-lof", "--lofFilePath", action="store", help="Path to tab separated \ loss-of-function curation file, where the first line is a header describing each \ @@ -167,31 +207,31 @@ if args.extra_output_file and args.extra_output_file == "stdout" and args.extra_output_file == args.infile: sys.stderr.write("ERROR: Only one of infile and --extra-output-file can be stdout.") sys.exit(255) return args def writeHeaders(version, outfh, extrafh): """Write out the field names""" outfh.write("#" + "\t".join(x for x in versionAutoSql[version])) if extrafh: if version == "v3.1.1" or version == "v3.1_chrM": extrafh.write("#" + "\t".join(versionExtraFields["v3.1.1"] + ["_jsonHapTable"])) else: extrafh.write("#" + "\t".join(versionExtraFields[version])) extrafh.write("\n") else: - outfh.write("\t" + "\t".join(versionExtraFields[version])) + outfh.write("\t" + "#" + "\t".join(versionExtraFields[version])) outfh.write("\n") def parseHeader(headerStr, infh, outfh, extraFh): """Parse the field names out of a header string""" global header headerStr = headerStr[1:] # chop off '#' fields = headerStr.strip('\n').split('\t') if not header: header = fields outfh.write("#%s\n" % ("\t".join(header[:17] + ["rsID","genes","annot","variation_type","_startPos"] + ["hgvsc", "hgvsp"]+ header[18:]))) elif fields != header: sys.stderr.write("Header differs from others: '%s'\n" % infh.name) sys.exit(1) @@ -276,45 +316,53 @@ hom_af, het_af = extraFieldList[16].split("/") hom_ac, het_ac = extraFieldList[14].split("/") popDict["Total"] = [extraFieldList[15], hom_ac, hom_af, het_ac, het_af] other = hapDict return popDict, other def convertExtraFields(extraFieldList, version): """Split the population data from the other extra fields and return the population data as a json blob and the other fields as a list""" versionPopNames = [] for x in versionPops[version]: if x in popAbbr: versionPopNames.append(popAbbr[x]) else: versionPopNames.append(x) - if version == "v3.1.1": + if version == "v3.1.1" or version.startswith("v4.1"): versionPopNames.append("Total") + if version == "v3.1.1": popData = extraFieldList[4:-9] + extraFieldList[-4:] + else: + popData = extraFieldList[4:-15] + extraFieldList[-5:] popDict = OrderedDict() # for keeping the header line first and total line last # in the final bigBed popDict["Populations"] = ["Allele Count", "Allele Number", "Allele Frequency", "Number of Homozygotes"] + #if version.startswith("v4.1"): + # popDict["Populations"].append("Number of Hemizygotes") i = 0 for popName in versionPopNames: val = popData[i:i+4] key = popAbbr[popName] if popName in popAbbr else popName popDict[key] = val i += 4 # Add an extra field for the chrM only haplogroup table + if version == "v3.1.1": other = extraFieldList[-9:-4] + [""] + else: + other = extraFieldList[-14:-4] else: popDict, other = buildMitoStructs(versionPopNames, extraFieldList) return popDict,other def splitVepField(vep, version): """Split the VEP string into a list of strings for each annotation. Because commas both delimit the multiple annotations of a single variant, and can be part of the pipe separated strings that make up a single annotation, we can't just split on ',' like normal""" ret = [] # at the versionSpecific index '|', go back until we find a comma or | and split there ix = 1 copy = vep.split('|') try: numFields = numVepFields[version] @@ -354,171 +402,198 @@ genes = defaultdict(dict) annotList = splitVepField(vep, version) for annot in annotList: group = annot.split('|') if "&" in group[1]: consList = group[1].split('&') else: consList = [group[1]] #if "regulatory_region_variant" in consList \ # or "downstream_gene_variant" in consList \ # or "upstream_gene_variant" in consList \ # or "TF_binding_site_variant" in consList \ # or "intergenic_variant" in consList: # continue vepFields = dict(zip(versionVepFields[version],group)) - gene = vepFields["SYMBOL"] if vepFields["SYMBOL"] != "" else "N/A" + gene = vepFields["SYMBOL"] hgvsc = [vepFields["HGVSc"]] if vepFields["HGVSc"] != "" else None hgvsp = [vepFields["HGVSp"]] if vepFields["HGVSp"] != "" else None lof = [vepFields["LoF"]] if vepFields["LoF"] != "" else None lofFlags = [vepFields["LoF_flags"]] if vepFields["LoF_flags"] != "" else None lofFilter = [vepFields["LoF_filter"]] if vepFields["LoF_filter"] != "" else None + lofInfo = [vepFields["LoF_info"]] if vepFields["LoF_info"] != "" else None if lof: try: for i,x in enumerate(lof): if x == "LC": lof[i] = "Low Confidence (%s)" % lofFilter[i] else: lof[i] = lofDesc[x] except KeyError: sys.stderr.write("ERROR parsing lof information:\n") + sys.stderr.write("annot: %s\n" % annot) + sys.stderr.write("group: %s\n" % group) + sys.stderr.write("versionVepFields: %s\n" % versionVepFields[version]) + sys.stderr.write("vepFields: %s\n" % vepFields) + sys.stderr.write("vep:\n%s\n" % vep) sys.stderr.write("lof: %s\n" % lof) - sys.stderr.write("lofFlags: %s\n" % lof) - sys.stderr.write("lofFilter: %s\n" % lof) + sys.stderr.write("lofFlags: %s\n" % lofFlags) + sys.stderr.write("lofFilter: %s\n" % lofFilter) + sys.stderr.write("lofInfo: %s\n" % lofInfo) sys.exit(255) if gene in genes: genes[gene]["cons"].update(list(consList)) if hgvsc: genes[gene]["hgvsc"].update(hgvsc) if hgvsp: genes[gene]["hgvsp"].update(hgvsp) if lof: genes[gene]["pLoF"] = set(lof) if lofFlags: genes[gene]["Flag"] = set(lofFlags) else: genes[gene]["cons"] = set(consList) genes[gene]["hgvsc"] = set(hgvsc) if hgvsc else set() genes[gene]["hgvsp"] = set(hgvsp) if hgvsp else set() genes[gene]["pLoF"] = set(lof) if lof else set() + try: genes[gene]["Flag"] = set(lof) if lofFlags else set() + except TypeError: + sys.stderr.write("ERROR parsing lof information:\n") + sys.stderr.write("annot: %s\n" % annot) + sys.stderr.write("group: %s\n" % group) + sys.stderr.write("versionVepFields: %s\n" % versionVepFields[version]) + sys.stderr.write("vepFields: %s\n" % vepFields) + sys.stderr.write("vep:\n%s\n" % vep) + sys.stderr.write("lof: %s\n" % lof) + sys.stderr.write("lofFlags: %s\n" % lofFlags) + sys.stderr.write("lofFilter: %s\n" % lofFilter) + sys.stderr.write("lofInfo: %s\n" % lofInfo) + sys.exit(255) for gene in genes: genes[gene]["cons"] = list(genes[gene]["cons"]) genes[gene]["hgvsc"] = list(genes[gene]["hgvsc"]) genes[gene]["hgvsp"] = list(genes[gene]["hgvsp"]) genes[gene]["pLoF"] = list(genes[gene]["pLoF"]) genes[gene]["Flag"] = list(genes[gene]["Flag"]) return genes def gnomadVcfBedToBigBed(infh, outfh, extraFh, version, lofDict): """Read from already opened infh, convert to more compact bed format, then write to already opened outfh, optionally use extraFh for non-necessary bed fields.""" writeHeaders(version, outfh, extraFh) for line in infh: genes = defaultdict(dict) extraInfo = [] if line.startswith("#"): continue - #parseHeader(line, infh, outfh, extraFh) - #continue fixedLine = line.strip('\n').split('\t') chrom, chromStart, chromEnd, bedName, score, strand, thickStart, thickEnd = fixedLine[:8] color = fixedLine[8] # defaults to black ref, alt, filterTag = fixedLine[9:12] filterTag = filterTag.replace(";",",") # replace so trackDb filterValues works if "chrM" not in version: vep = fixedLine[17] ac, an, af, faf95, nhomalt = fixedLine[12:17] maybeExtraFields = [x if x else "N/A" for x in fixedLine[18:]] else: vep = fixedLine[12] # ac and af are really AC_hom/AC_het and AF_hom/AF_het ac = fixedLine[14] + "/" + fixedLine[15] af = fixedLine[18] + "/" + fixedLine[19] an = fixedLine[13] faf95 = "" nhomalt = "" maybeExtraFields = fixedLine[16:18] + fixedLine[20:] if vep != "": genes = parseVep(vep, version) # Now that we've parsed all the incoming fields from vcfToBed, write # output to final bed, and maybe to extra tab file: - #if genes: + if genes: consList = [] for gene in genes: consList += list(genes[gene]["cons"]) annot,color = pickColor(consList) rsId = "" if bedName.startswith("rs"): rsId = bedName unshiftedStart = unshiftLeftPad(int(chromStart), ref, alt) displayName = chrom + "-" + str(unshiftedStart) + "-" displayName += ref[:10]+"..." if len(ref) > 13 else ref displayName += "-" displayName += alt[:10]+"..." if len(alt) > 13 else alt name = hashlib.md5(str.encode(chrom+chromStart+chromEnd+ref+alt)).hexdigest() - if version == "v3.1.1" or version == "v3.1_chrM": + if version == "v3.1.1" or version == "v3.1_chrM" or version.startswith("v4.1"): outfh.write("\t".join([chrom, chromStart, chromEnd, name, score, strand, thickStart, thickEnd, color, ref, alt, filterTag, ac, an, af, faf95, nhomalt, rsId, ", ".join(genes.keys()), annot, ",".join(consList), str(unshiftedStart), displayName])) + if version.startswith("v4.1"): + # add the grp max information for the mouseovers + grpmax = popAbbr[fixedLine[18]] if fixedLine[18] in popAbbr else "N/A" + AC_grpmax = fixedLine[19] if fixedLine[19] else "N/A" + AN_grpmax = fixedLine[20] if fixedLine[20] else "N/A" + AF_grpmax = fixedLine[21] if fixedLine[21] else "N/A" + outfh.write("\t" + "\t".join([grpmax, AC_grpmax, AN_grpmax, AF_grpmax])) + # add the hemizygosity + nHomaltX = "N/A" + nHemi = "N/A" + if version == "v4.1_genomes": + nHomaltX = fixedLine[65] if fixedLine[65] else "N/A" + if chrom == "chrX" or chrom == "chrY": + nHemi = fixedLine[66] if fixedLine[66] else "N/A" + else: + nHomaltX = fixedLine[61] if fixedLine[61] else "N/A" + if chrom == "chrX" or chrom == "chrY": + nHemi = fixedLine[62] if fixedLine[62] else "N/A" + outfh.write("\t" + nHomaltX + "\t" + nHemi) popTable, otherFields = convertExtraFields(maybeExtraFields + [ac, an, af, nhomalt], version) if version == "v3.1_chrM": # otherFields is the haplotype table plus empties for the v3.1.1 fields: otherFields = ["" for i in range(5)] + [json.dumps(otherFields)] if extraFh: extraFh.write("\t".join([name, json.dumps(genes), json.dumps(popTable)] + otherFields)) extraFh.write("\n") else: outfh.write("\t" + "\t".join([name] + [json.dumps(genes), json.dumps(popTable)] + otherFields)) outfh.write("\n") elif version == "v3.1": hgvscList = [", ".join(list(genes[gene]["hgvsc"]))] hgvspList = [", ".join(list(genes[gene]["hgvsp"]))] pLoFList = [", ".join(list(genes[gene]["pLoF"]))] pLoFFlags = [", ".join(list(genes[gene]["Flag"]))] outfh.write("\t".join([chrom, chromStart, chromEnd, name, score, strand, thickStart, thickEnd, color, ref, alt, filterTag, ac, an, af, faf95, nhomalt, rsId, gene, annot, *consList, str(unshiftedStart), displayName])) if extraFh: extraFh.write("\t".join([name] + hgvscList + hgvspList + maybeExtraFields)) extraFh.write("\n") else: outfh.write("\t" + "\t".join([name] + hgvscList + hgvspList + maybeExtraFields)) outfh.write("\n") else: - pLoFCuration = getLofCuration(lofDict, version, chrom, + pLoFCuration = getLofCuration(lofDict, version, bed8Fields[0], str(unshiftedStart), ref, alt) - hgvscList = [x for x in genes[gene]["hgvsc"] for gene in genes] - hgvspList = [x for x in genes[gene]["hgvsp"] for gene in genes] - pLoFList = [x for x in genes[gene]["pLoF"] for gene in genes] - pLoFFlags = [x for x in genes[gene]["Flag"] for gene in genes] outfh.write("\t".join([chrom, chromStart, chromEnd, name, score, strand, thickStart, thickEnd, color, ref, alt, filterTag, ac, an, af, faf95, nhomalt, - rsId, ", ".join(genes.keys()), annot, ", ".join(consList)])) - outfh.write("\t" + str(unshiftedStart)) - outfh.write("\t" + displayName) - outfh.write("\t" + ", ".join(pLoFList)) - outfh.write("\t" + ", ".join(pLoFFlags)) - outfh.write("\t" + "\t".join(pLoFCuration)) + rsId, gene, annot, *consList, displayName])) + outfh.write("\t" + "\t".join(pLoFCuration, [str(unshiftedStart)])) if extraFh: - extraFh.write(", ".join(hgvscList) + "\t" + ", ".join(hgvspList) + "\t" + "\t".join(maybeExtraFields)) + extraFh.write("\t".join(name + hgvscList + hgvspList + maybeExtraFields)) extraFh.write("\n") else: - outfh.write("\t" + ", ".join(hgvscList)) - outfh.write("\t" + ", ".join(hgvspList)) - outfh.write("\t" + "\t".join(maybeExtraFields)) + outfh.write("\t" + "\t".join([name] + hgvscList + hgvspList + maybeExtraFields)) outfh.write("\n") def parseLofFile(fpath): """Make a struct of the different loss of function flags for a curated variant.""" gotHeader = False lofHeader = [] ret = {} with open(fpath) as fh: for line in fh: if not gotHeader: lofHeader = line.strip().split("\t") gotHeader = True else: lofDetails = line.strip().split("\t") ret[lofDetails[0]] = {lofHeader[x]: lofDetails[x] for x in range(len(lofHeader))} @@ -535,18 +610,21 @@ infh = sys.stdin else: infh = open(args.infile) if args.outfile == "stdout": outfh = sys.stdout else: outfh = open(args.outfile, "w") if args.extra_output_file: if args.extra_output_file == "stdout": extraFh = sys.stdout else: extraFh = open(args.extra_output_file, "w") gnomadVcfBedToBigBed(infh, outfh, extraFh, args.version, lofDict) infh.close() outfh.close() + # close the extra-output file too, else its final buffered line can be lost + if extraFh is not None and extraFh is not sys.stdout: + extraFh.close() if __name__ == "__main__": main()