@sjcrh/proteinpaint-shared 2.180.0 → 2.180.1

package/src/bulk.snv.js

@@ -4,12 +4,12 @@
 //
 ///////////////////////////////
 
-import * as common from './common.js'
-import * as bulk from './bulk.js'
+import * as common from "./common.js"
+import * as bulk from "./bulk.js"
 
 export function parseheader(line, flag) {
-	const header = line.toLowerCase().split('\t')
-	if (header.length <= 1) return 'invalid file header for snv/indel'
+	const header = line.toLowerCase().split("\t")
+	if (header.length <= 1) return "invalid file header for snv/indel"
 	const htry = (...args) => {
 		for (const s of args) {
 			const i = header.indexOf(s)
@@ -17,98 +17,127 @@ export function parseheader(line, flag) {
 		}
 		return -1
 	}
-	let i = htry('annovar_gene', 'annovar_sj_gene', 'gene', 'genename', 'gene_symbol', 'hugo_symbol')
-	if (i == -1) return 'gene missing from header'
-	header[i] = 'gene'
-	i = htry('annovar_aachange', 'amino_acid_change', 'annovar_sj_aachange', 'aachange', 'protein_change', 'variant')
-	if (i == -1) return 'amino_acid_change missing from header'
-	header[i] = 'mname'
-	i = htry('annovar_class', 'class', 'mclass', 'variant_class', 'variant_classification', 'annovar_sj_class')
-	if (i == -1) return 'variant_class missing from header'
-	header[i] = 'class'
-	i = htry('chromosome', 'chr')
-	if (i == -1) return 'chromosome missing from header'
-	header[i] = 'chr'
-	i = htry('wu_hg19_pos', 'start', 'start_position', 'chr_position', 'position')
-	if (i == -1) return 'start missing from header'
-	header[i] = 'pos'
+	let i = htry(
+		"annovar_gene",
+		"annovar_sj_gene",
+		"gene",
+		"genename",
+		"gene_symbol",
+		"hugo_symbol"
+	)
+	if (i == -1) return "gene missing from header"
+	header[i] = "gene"
+	i = htry(
+		"annovar_aachange",
+		"amino_acid_change",
+		"annovar_sj_aachange",
+		"aachange",
+		"protein_change",
+		"variant"
+	)
+	if (i == -1) return "amino_acid_change missing from header"
+	header[i] = "mname"
+	i = htry(
+		"annovar_class",
+		"class",
+		"mclass",
+		"variant_class",
+		"variant_classification",
+		"annovar_sj_class"
+	)
+	if (i == -1) return "variant_class missing from header"
+	header[i] = "class"
+	i = htry("chromosome", "chr")
+	if (i == -1) return "chromosome missing from header"
+	header[i] = "chr"
+	i = htry("wu_hg19_pos", "start", "start_position", "chr_position", "position")
+	if (i == -1) return "start missing from header"
+	header[i] = "pos"
 	i = htry(
-		'annovar_isoform',
-		'mrna_accession',
-		'mrna accession',
-		'refseq_mrna_id',
-		'annovar_sj_filter_isoform',
-		'refseq',
-		'isoform'
+		"annovar_isoform",
+		"mrna_accession",
+		"mrna accession",
+		"refseq_mrna_id",
+		"annovar_sj_filter_isoform",
+		"refseq",
+		"isoform"
 	)
-	if (i == -1) return 'isoform missing from header'
-	header[i] = 'isoform'
+	if (i == -1) return "isoform missing from header"
+	header[i] = "isoform"
 
 	// optional
-	i = htry('sample', 'sample_name', 'tumor_sample_barcode')
-	if (i != -1) header[i] = 'sample'
-	i = htry('patient', 'donor', 'target_case_id')
-	if (i != -1) header[i] = 'patient'
-	i = htry('quantitative_measurements')
-	if (i != -1) header[i] = 'qmset'
+	i = htry("sample", "sample_name", "tumor_sample_barcode")
+	if (i != -1) header[i] = "sample"
+	i = htry("patient", "donor", "target_case_id")
+	if (i != -1) header[i] = "patient"
+	i = htry("quantitative_measurements")
+	if (i != -1) header[i] = "qmset"
 	// dna maf tumor
-	i = htry('mutant_reads_in_case', 'mutant_in_tumor', 'tumor_readcount_alt')
-	if (i != -1) header[i] = 'maf_tumor_v1'
-	i = htry('total_reads_in_case', 'total_in_tumor', 'tumor_readcount_total')
-	if (i != -1) header[i] = 'maf_tumor_v2'
+	i = htry("mutant_reads_in_case", "mutant_in_tumor", "tumor_readcount_alt")
+	if (i != -1) header[i] = "maf_tumor_v1"
+	i = htry("total_reads_in_case", "total_in_tumor", "tumor_readcount_total")
+	if (i != -1) header[i] = "maf_tumor_v2"
 	// dna maf normal
-	i = htry('mutant_reads_in_control', 'mutant_in_normal', 'normal_readcount_alt')
-	if (i != -1) header[i] = 'maf_normal_v1'
-	i = htry('total_reads_in_control', 'total_in_normal', 'normal_readcount_total')
-	if (i != -1) header[i] = 'maf_normal_v2'
+	i = htry(
+		"mutant_reads_in_control",
+		"mutant_in_normal",
+		"normal_readcount_alt"
+	)
+	if (i != -1) header[i] = "maf_normal_v1"
+	i = htry(
+		"total_reads_in_control",
+		"total_in_normal",
+		"normal_readcount_total"
+	)
+	if (i != -1) header[i] = "maf_normal_v2"
 	// rna maf
 	// cdna
-	i = htry('cdna_change')
-	if (i != -1) header[i] = 'cdna_change'
-	i = htry('sampletype', 'sample type', 'sample_type')
-	if (i != -1) header[i] = 'sampletype'
-	i = htry('origin')
-	if (i != -1) header[i] = 'origin'
-	i = htry('cancer', 'disease', 'diagnosis')
-	if (i != -1) header[i] = 'disease'
+	i = htry("cdna_change")
+	if (i != -1) header[i] = "cdna_change"
+	i = htry("sampletype", "sample type", "sample_type")
+	if (i != -1) header[i] = "sampletype"
+	i = htry("origin")
+	if (i != -1) header[i] = "origin"
+	i = htry("cancer", "disease", "diagnosis")
+	if (i != -1) header[i] = "disease"
 	flag.snv.header = header
 	flag.snv.loaded = true
 	return false
 }
 
 export function parseline(linei, line, flag) {
-	if (line == '' || line[0] == '#') return
-	const lst = line.split('\t')
+	if (line == "" || line[0] == "#") return
+	const lst = line.split("\t")
 	const m = {}
 	for (let j = 0; j < flag.snv.header.length; j++) {
 		if (lst[j] == undefined) break
 		m[flag.snv.header[j]] = lst[j]
 	}
 	if (!m.gene) {
-		flag.snv.badlines.push([linei, 'missing gene', lst])
+		flag.snv.badlines.push([linei, "missing gene", lst])
 		return
 	}
-	if (m.gene.toUpperCase() == 'UNKNOWN') {
-		flag.snv.badlines.push([linei, 'gene name is UNKNOWN', lst])
+	if (m.gene.toUpperCase() == "UNKNOWN") {
+		flag.snv.badlines.push([linei, "gene name is UNKNOWN", lst])
 		return
 	}
 	if (!m.isoform) {
-		flag.snv.badlines.push([linei, 'missing isoform', lst])
+		flag.snv.badlines.push([linei, "missing isoform", lst])
 		return
 	}
 	if (!m.mname) {
 		m.mname = m.cdna_change
 		if (!m.mname) {
-			flag.snv.badlines.push([linei, 'missing amino acid change', lst])
+			flag.snv.badlines.push([linei, "missing amino acid change", lst])
 			return
 		}
 	} else {
-		if (m.mname.indexOf('p.') == 0) {
-			m.mname = m.mname.replace(/^p\./, '')
+		if (m.mname.indexOf("p.") == 0) {
+			m.mname = m.mname.replace(/^p\./, "")
 		}
 	}
 	if (!m.class) {
-		flag.snv.badlines.push([linei, 'missing mutation class', lst])
+		flag.snv.badlines.push([linei, "missing mutation class", lst])
 		return
 	}
 	let _c = flag.mclasslabel2key[m.class.toUpperCase()]
@@ -119,7 +148,7 @@ export function parseline(linei, line, flag) {
 		if (_c) {
 			m.class = _c
 		} else {
-			flag.snv.badlines.push([linei, 'wrong mutation class: ' + m.class, lst])
+			flag.snv.badlines.push([linei, "wrong mutation class: " + m.class, lst])
 			return
 		}
 	}
@@ -127,31 +156,35 @@ export function parseline(linei, line, flag) {
 		return
 	}
 	if (!m.chr) {
-		flag.snv.badlines.push([linei, 'missing chromosome', lst])
+		flag.snv.badlines.push([linei, "missing chromosome", lst])
 		return
 	}
-	if (m.chr.toLowerCase().indexOf('chr') != 0) {
-		m.chr = 'chr' + m.chr
+	if (m.chr.toLowerCase().indexOf("chr") != 0) {
+		m.chr = "chr" + m.chr
 	}
 	if (!m.pos) {
-		flag.snv.badlines.push([linei, 'missing chromosome position', lst])
+		flag.snv.badlines.push([linei, "missing chromosome position", lst])
 		return
 	}
 	const v = Number.parseInt(m.pos)
 	if (Number.isNaN(v)) {
-		flag.snv.badlines.push([linei, 'invalid chromosome position', lst])
+		flag.snv.badlines.push([linei, "invalid chromosome position", lst])
 		return
 	}
 	m.pos = v - 1
 
 	if (m.maf_tumor_v2 != undefined && m.maf_tumor_v1 != undefined) {
-		if (m.maf_tumor_v2 == '') {
+		if (m.maf_tumor_v2 == "") {
 			// no value, do not parse
 		} else {
 			let v1 = Number.parseInt(m.maf_tumor_v1),
 				v2 = Number.parseInt(m.maf_tumor_v2)
 			if (Number.isNaN(v1) || Number.isNaN(v2)) {
-				flag.snv.badlines.push([linei, 'invalid maf_tumor mutant and/or total read count', lst])
+				flag.snv.badlines.push([
+					linei,
+					"invalid maf_tumor mutant and/or total read count",
+					lst,
+				])
 				return
 			}
 			m.maf_tumor = { f: v1 / v2, v1: v1, v2: v2 }
@@ -161,13 +194,17 @@ export function parseline(linei, line, flag) {
 	}
 
 	if (m.maf_normal_v1 != undefined && m.maf_normal_v2 != undefined) {
-		if (m.maf_normal_v2 == '') {
+		if (m.maf_normal_v2 == "") {
 			// no value
 		} else {
 			let v1 = Number.parseInt(m.maf_normal_v1),
 				v2 = Number.parseInt(m.maf_normal_v2)
 			if (Number.isNaN(v1) || Number.isNaN(v2)) {
-				flag.snv.badlines.push([linei, 'invalid maf_normal mutant and/or total read count', lst])
+				flag.snv.badlines.push([
+					linei,
+					"invalid maf_normal mutant and/or total read count",
+					lst,
+				])
 				return
 			}
 			m.maf_normal = { f: v1 / v2, v1: v1, v2: v2 }
@@ -220,9 +257,9 @@ export function parseline(linei, line, flag) {
 	*/
 	flag.good++
 	// FIXME hard-coded M and S
-	if (m.class == 'M') {
+	if (m.class == "M") {
 		flag.snv.missense++
-	} else if (m.class == 'S') {
+	} else if (m.class == "S") {
 		flag.snv.silent++
 	}
 	const n = flag.geneToUpper ? m.gene.toUpperCase() : m.gene

package/src/bulk.sv.js

@@ -1,5 +1,5 @@
-import * as bulk from './bulk.js'
-import * as common from './common.js'
+import * as bulk from "./bulk.js"
+import * as common from "./common.js"
 
 /////////////////////////////////
 //
@@ -11,8 +11,8 @@ import * as common from './common.js'
 // must tell if the data is fusion or sv
 
 export function parseheader(line, flag, issv) {
-	const header = line.toLowerCase().split('\t')
-	if (header.length <= 1) return 'invalid file header for fusions'
+	const header = line.toLowerCase().split("\t")
+	if (header.length <= 1) return "invalid file header for fusions"
 	const htry = (...lst) => {
 		for (const a of lst) {
 			const j = header.indexOf(a)
@@ -20,47 +20,47 @@ export function parseheader(line, flag, issv) {
 		}
 		return -1
 	}
-	let i = htry('gene_a', 'gene1', 'genea')
-	if (i == -1) return 'gene_a missing from header'
-	header[i] = 'gene1'
-	i = htry('gene_b', 'gene2', 'geneb')
-	if (i == -1) return 'gene_b missing from header'
-	header[i] = 'gene2'
-	i = htry('chr_a', 'chr1', 'chra')
-	if (i == -1) return 'chr_a missing from header'
-	header[i] = 'chr1'
-	i = htry('chr_b', 'chr2', 'chrb')
-	if (i == -1) return 'chr_b missing from header'
-	header[i] = 'chr2'
-	i = htry('pos_a', 'position_a', 'position1', 'posa')
-	if (i == -1) return 'pos_a missing from header'
-	header[i] = 'position1'
-	i = htry('pos_b', 'position_b', 'position2', 'posb')
-	if (i == -1) return 'pos_b missing from header'
-	header[i] = 'position2'
-	i = htry('isoform_a', 'refseq_a', 'refseq1', 'isoform1', 'sv_refseqa')
-	if (i == -1) return 'isoform_a missing from header'
-	header[i] = 'isoform1'
-	i = htry('isoform_b', 'refseq_b', 'refseq2', 'isoform2', 'sv_refseqb')
-	if (i == -1) return 'isoform_b missing from header'
-	header[i] = 'isoform2'
-	i = htry('strand_a', 'orta')
-	if (i == -1) return 'strand_a missing from header'
-	header[i] = 'strand1'
-	i = htry('strand_b', 'ortb')
-	if (i == -1) return 'strand_b missing from header'
-	header[i] = 'strand2'
+	let i = htry("gene_a", "gene1", "genea")
+	if (i == -1) return "gene_a missing from header"
+	header[i] = "gene1"
+	i = htry("gene_b", "gene2", "geneb")
+	if (i == -1) return "gene_b missing from header"
+	header[i] = "gene2"
+	i = htry("chr_a", "chr1", "chra")
+	if (i == -1) return "chr_a missing from header"
+	header[i] = "chr1"
+	i = htry("chr_b", "chr2", "chrb")
+	if (i == -1) return "chr_b missing from header"
+	header[i] = "chr2"
+	i = htry("pos_a", "position_a", "position1", "posa")
+	if (i == -1) return "pos_a missing from header"
+	header[i] = "position1"
+	i = htry("pos_b", "position_b", "position2", "posb")
+	if (i == -1) return "pos_b missing from header"
+	header[i] = "position2"
+	i = htry("isoform_a", "refseq_a", "refseq1", "isoform1", "sv_refseqa")
+	if (i == -1) return "isoform_a missing from header"
+	header[i] = "isoform1"
+	i = htry("isoform_b", "refseq_b", "refseq2", "isoform2", "sv_refseqb")
+	if (i == -1) return "isoform_b missing from header"
+	header[i] = "isoform2"
+	i = htry("strand_a", "orta")
+	if (i == -1) return "strand_a missing from header"
+	header[i] = "strand1"
+	i = htry("strand_b", "ortb")
+	if (i == -1) return "strand_b missing from header"
+	header[i] = "strand2"
 	// optional
-	i = htry('sample', 'sample_name', 'tumor_sample_barcode')
-	if (i != -1) header[i] = 'sample'
-	i = htry('patient', 'donor', 'target_case_id')
-	if (i != -1) header[i] = 'patient'
-	i = htry('sampletype', 'sample type', 'sample_type')
-	if (i != -1) header[i] = 'sampletype'
-	i = htry('disease')
-	if (i != -1) header[i] = 'disease'
-	i = htry('origin')
-	if (i != -1) header[i] = 'origin'
+	i = htry("sample", "sample_name", "tumor_sample_barcode")
+	if (i != -1) header[i] = "sample"
+	i = htry("patient", "donor", "target_case_id")
+	if (i != -1) header[i] = "patient"
+	i = htry("sampletype", "sample type", "sample_type")
+	if (i != -1) header[i] = "sampletype"
+	i = htry("disease")
+	if (i != -1) header[i] = "disease"
+	i = htry("origin")
+	if (i != -1) header[i] = "origin"
 	if (issv) {
 		flag.sv.loaded = true
 		flag.sv.header = header
@@ -72,8 +72,8 @@ export function parseheader(line, flag, issv) {
 }
 
 export function parseline(i, line, flag, issv) {
-	if (line == '' || line[0] == '#') return
-	const lst = line.split('\t')
+	if (line == "" || line[0] == "#") return
+	const lst = line.split("\t")
 	const m = {}
 	const header = issv ? flag.sv.header : flag.fusion.header
 	const badlines = issv ? flag.sv.badlines : flag.fusion.badlines
@@ -82,56 +82,56 @@ export function parseline(i, line, flag, issv) {
 		m[header[j]] = lst[j]
 	}
 	if (!m.chr1) {
-		badlines.push([i, 'missing chr1', lst])
+		badlines.push([i, "missing chr1", lst])
 		return
 	}
-	if (m.chr1.toLowerCase().indexOf('chr') != 0) {
-		m.chr1 = 'chr' + m.chr1
+	if (m.chr1.toLowerCase().indexOf("chr") != 0) {
+		m.chr1 = "chr" + m.chr1
 	}
 	if (!m.chr2) {
-		badlines.push([i, 'missing chr2', lst])
+		badlines.push([i, "missing chr2", lst])
 		return
 	}
-	if (m.chr2.toLowerCase().indexOf('chr') != 0) {
-		m.chr2 = 'chr' + m.chr2
+	if (m.chr2.toLowerCase().indexOf("chr") != 0) {
+		m.chr2 = "chr" + m.chr2
 	}
 	let v = m.position1
 	if (!v) {
-		badlines.push([i, 'missing position1', lst])
+		badlines.push([i, "missing position1", lst])
 		return
 	}
 	let v2 = Number.parseInt(v)
 	if (Number.isNaN(v2) || v2 <= 0) {
-		badlines.push([i, 'invalid value for position1', lst])
+		badlines.push([i, "invalid value for position1", lst])
 		return
 	}
 	m.position1 = v2
 	v = m.position2
 	if (!v) {
-		badlines.push([i, 'missing position2', lst])
+		badlines.push([i, "missing position2", lst])
 		return
 	}
 	v2 = Number.parseInt(v)
 	if (Number.isNaN(v2) || v2 <= 0) {
-		badlines.push([i, 'invalid value for position2', lst])
+		badlines.push([i, "invalid value for position2", lst])
 		return
 	}
 	m.position2 = v2
 	if (bulk.parsesample(m, flag, i, lst, badlines)) {
 		return
 	}
-	if (m.isoform1 && m.isoform1.indexOf(',') != -1) {
-		const lst2 = m.isoform1.split(',')
+	if (m.isoform1 && m.isoform1.indexOf(",") != -1) {
+		const lst2 = m.isoform1.split(",")
 		m.isoform1 = undefined
 		for (const t of lst2) {
-			if (t != '') m.isoform1 = t
+			if (t != "") m.isoform1 = t
 		}
 	}
-	if (m.isoform2 && m.isoform2.indexOf(',') != -1) {
-		const lst2 = m.isoform2.split(',')
+	if (m.isoform2 && m.isoform2.indexOf(",") != -1) {
+		const lst2 = m.isoform2.split(",")
 		m.isoform2 = undefined
 		for (const t of lst2) {
-			if (t != '') m.isoform2 = t
+			if (t != "") m.isoform2 = t
 		}
 	}
 	if (!m.gene1) {
@@ -160,17 +160,17 @@ export function parseline(i, line, flag, issv) {
 						isoform: m.isoform1,
 						strand: m.strand1,
 						chr: m.chr1,
-						position: m.position1
+						position: m.position1,
 					},
 					b: {
 						name: m.gene2,
 						isoform: m.isoform2,
 						strand: m.strand2,
 						chr: m.chr2,
-						position: m.position2
-					}
-				}
-			]
+						position: m.position2,
+					},
+				},
+			],
 		}
 		const n = flag.geneToUpper ? m.gene1.toUpperCase() : m.gene1
 		if (!flag.data[n]) {
@@ -198,17 +198,17 @@ export function parseline(i, line, flag, issv) {
 						isoform: m.isoform1,
 						strand: m.strand1,
 						chr: m.chr1,
-						position: m.position1
+						position: m.position1,
 					},
 					b: {
 						name: m.gene2,
 						isoform: m.isoform2,
 						strand: m.strand2,
 						chr: m.chr2,
-						position: m.position2
-					}
-				}
-			]
+						position: m.position2,
+					},
+				},
+			],
 		}
 		const n = flag.geneToUpper ? m.gene2.toUpperCase() : m.gene2
 		if (!flag.data[n]) {
@@ -221,10 +221,10 @@ export function parseline(i, line, flag, issv) {
 export function duplicate(m) {
 	const n = {}
 	for (const k in m) {
-		if (k == 'pairlst') continue
+		if (k == "pairlst") continue
 		const v = m[k]
 		const type = typeof v
-		if (type == 'object') {
+		if (type == "object") {
 			continue
 		}
 		n[k] = v
@@ -234,7 +234,7 @@ export function duplicate(m) {
 		for (const pair of m.pairlst) {
 			const p = {}
 			for (const k in pair) {
-				if (k == 'a' || k == 'b' || k == 'interstitial') {
+				if (k == "a" || k == "b" || k == "interstitial") {
 					continue
 				}
 				p[k] = pair[k]
@@ -243,7 +243,7 @@ export function duplicate(m) {
 				p.a = {}
 				for (const k in pair.a) {
 					const v = pair.a[k]
-					if (typeof v == 'object') {
+					if (typeof v == "object") {
 						continue
 					}
 					p.a[k] = v
@@ -253,7 +253,7 @@ export function duplicate(m) {
 				p.b = {}
 				for (const k in pair.b) {
 					const v = pair.b[k]
-					if (typeof v == 'object') {
+					if (typeof v == "object") {
 						continue
 					}
 					p.b[k] = v
@@ -263,7 +263,7 @@ export function duplicate(m) {
 				p.interstitial = {}
 				for (const k in pair.interstitial) {
 					const v = pair.interstitial[k]
-					if (typeof v == 'object') {
+					if (typeof v == "object") {
 						continue
 					}
 					p.interstitial[k] = v