@teselagen/bio-parsers 0.4.1 → 0.4.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/index.js +10 -17
- package/index.mjs +10 -17
- package/index.umd.js +10 -17
- package/package.json +2 -2
- package/src/utils/validateSequence.js +0 -2
package/index.js
CHANGED
|
@@ -6170,7 +6170,7 @@ lodash.exports;
|
|
|
6170
6170
|
})(lodash, lodash.exports);
|
|
6171
6171
|
var lodashExports = lodash.exports;
|
|
6172
6172
|
const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
|
|
6173
|
-
const
|
|
6173
|
+
const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
|
|
6174
6174
|
const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
|
|
6175
6175
|
const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
|
|
6176
6176
|
const aminoAcidToDegenerateDnaMap = {
|
|
@@ -11281,15 +11281,13 @@ function filterSequenceString(sequenceString, {
|
|
|
11281
11281
|
name,
|
|
11282
11282
|
isProtein,
|
|
11283
11283
|
isRna,
|
|
11284
|
-
isMixedRnaAndDna
|
|
11285
|
-
includeStopCodon
|
|
11284
|
+
isMixedRnaAndDna
|
|
11286
11285
|
} = {}) {
|
|
11287
11286
|
const acceptedChars = getAcceptedChars({
|
|
11288
11287
|
isOligo,
|
|
11289
11288
|
isProtein,
|
|
11290
11289
|
isRna,
|
|
11291
|
-
isMixedRnaAndDna
|
|
11292
|
-
includeStopCodon
|
|
11290
|
+
isMixedRnaAndDna
|
|
11293
11291
|
});
|
|
11294
11292
|
const replaceChars = getReplaceChars({
|
|
11295
11293
|
isOligo,
|
|
@@ -11339,10 +11337,9 @@ function getAcceptedChars({
|
|
|
11339
11337
|
isOligo,
|
|
11340
11338
|
isProtein,
|
|
11341
11339
|
isRna,
|
|
11342
|
-
isMixedRnaAndDna
|
|
11343
|
-
includeStopCodon
|
|
11340
|
+
isMixedRnaAndDna
|
|
11344
11341
|
} = {}) {
|
|
11345
|
-
return isProtein ? `${
|
|
11342
|
+
return isProtein ? `${extended_protein_letters.toLowerCase()}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
|
|
11346
11343
|
//just plain old dna
|
|
11347
11344
|
ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
|
|
11348
11345
|
);
|
|
@@ -11496,7 +11493,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
|
|
|
11496
11493
|
const {
|
|
11497
11494
|
annotationsAsObjects,
|
|
11498
11495
|
logMessages,
|
|
11499
|
-
|
|
11496
|
+
doNotRemoveInvalidChars,
|
|
11500
11497
|
additionalValidChars,
|
|
11501
11498
|
noTranslationData,
|
|
11502
11499
|
doNotProvideIdsForAnnotations,
|
|
@@ -11530,11 +11527,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
|
|
|
11530
11527
|
if (seqData.isRna) {
|
|
11531
11528
|
seqData.sequence = seqData.sequence.replace(/t/gi, "u");
|
|
11532
11529
|
}
|
|
11533
|
-
if (
|
|
11530
|
+
if (!doNotRemoveInvalidChars) {
|
|
11534
11531
|
if (seqData.isProtein) {
|
|
11535
|
-
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
|
|
11536
|
-
includeStopCodon: true
|
|
11537
|
-
}, topLevelSeqData || seqData));
|
|
11532
|
+
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
|
|
11538
11533
|
seqData.proteinSequence = newSeq;
|
|
11539
11534
|
} else {
|
|
11540
11535
|
const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
|
|
@@ -19375,8 +19370,7 @@ function validateSequence(sequence, options = {}) {
|
|
|
19375
19370
|
inclusive1BasedEnd,
|
|
19376
19371
|
additionalValidChars,
|
|
19377
19372
|
allowOverflowAnnotations,
|
|
19378
|
-
coerceFeatureTypes
|
|
19379
|
-
includeStopCodon
|
|
19373
|
+
coerceFeatureTypes
|
|
19380
19374
|
} = options;
|
|
19381
19375
|
[
|
|
19382
19376
|
"isDNA",
|
|
@@ -19436,8 +19430,7 @@ function validateSequence(sequence, options = {}) {
|
|
|
19436
19430
|
const [validChars, warnings] = filterSequenceString(sequence.sequence, {
|
|
19437
19431
|
name: sequence.name,
|
|
19438
19432
|
isProtein: true,
|
|
19439
|
-
additionalValidChars
|
|
19440
|
-
includeStopCodon
|
|
19433
|
+
additionalValidChars
|
|
19441
19434
|
});
|
|
19442
19435
|
if (validChars !== sequence.sequence) {
|
|
19443
19436
|
sequence.sequence = validChars;
|
package/index.mjs
CHANGED
|
@@ -6168,7 +6168,7 @@ lodash.exports;
|
|
|
6168
6168
|
})(lodash, lodash.exports);
|
|
6169
6169
|
var lodashExports = lodash.exports;
|
|
6170
6170
|
const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
|
|
6171
|
-
const
|
|
6171
|
+
const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
|
|
6172
6172
|
const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
|
|
6173
6173
|
const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
|
|
6174
6174
|
const aminoAcidToDegenerateDnaMap = {
|
|
@@ -11279,15 +11279,13 @@ function filterSequenceString(sequenceString, {
|
|
|
11279
11279
|
name,
|
|
11280
11280
|
isProtein,
|
|
11281
11281
|
isRna,
|
|
11282
|
-
isMixedRnaAndDna
|
|
11283
|
-
includeStopCodon
|
|
11282
|
+
isMixedRnaAndDna
|
|
11284
11283
|
} = {}) {
|
|
11285
11284
|
const acceptedChars = getAcceptedChars({
|
|
11286
11285
|
isOligo,
|
|
11287
11286
|
isProtein,
|
|
11288
11287
|
isRna,
|
|
11289
|
-
isMixedRnaAndDna
|
|
11290
|
-
includeStopCodon
|
|
11288
|
+
isMixedRnaAndDna
|
|
11291
11289
|
});
|
|
11292
11290
|
const replaceChars = getReplaceChars({
|
|
11293
11291
|
isOligo,
|
|
@@ -11337,10 +11335,9 @@ function getAcceptedChars({
|
|
|
11337
11335
|
isOligo,
|
|
11338
11336
|
isProtein,
|
|
11339
11337
|
isRna,
|
|
11340
|
-
isMixedRnaAndDna
|
|
11341
|
-
includeStopCodon
|
|
11338
|
+
isMixedRnaAndDna
|
|
11342
11339
|
} = {}) {
|
|
11343
|
-
return isProtein ? `${
|
|
11340
|
+
return isProtein ? `${extended_protein_letters.toLowerCase()}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
|
|
11344
11341
|
//just plain old dna
|
|
11345
11342
|
ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
|
|
11346
11343
|
);
|
|
@@ -11494,7 +11491,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
|
|
|
11494
11491
|
const {
|
|
11495
11492
|
annotationsAsObjects,
|
|
11496
11493
|
logMessages,
|
|
11497
|
-
|
|
11494
|
+
doNotRemoveInvalidChars,
|
|
11498
11495
|
additionalValidChars,
|
|
11499
11496
|
noTranslationData,
|
|
11500
11497
|
doNotProvideIdsForAnnotations,
|
|
@@ -11528,11 +11525,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
|
|
|
11528
11525
|
if (seqData.isRna) {
|
|
11529
11526
|
seqData.sequence = seqData.sequence.replace(/t/gi, "u");
|
|
11530
11527
|
}
|
|
11531
|
-
if (
|
|
11528
|
+
if (!doNotRemoveInvalidChars) {
|
|
11532
11529
|
if (seqData.isProtein) {
|
|
11533
|
-
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
|
|
11534
|
-
includeStopCodon: true
|
|
11535
|
-
}, topLevelSeqData || seqData));
|
|
11530
|
+
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
|
|
11536
11531
|
seqData.proteinSequence = newSeq;
|
|
11537
11532
|
} else {
|
|
11538
11533
|
const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
|
|
@@ -19373,8 +19368,7 @@ function validateSequence(sequence, options = {}) {
|
|
|
19373
19368
|
inclusive1BasedEnd,
|
|
19374
19369
|
additionalValidChars,
|
|
19375
19370
|
allowOverflowAnnotations,
|
|
19376
|
-
coerceFeatureTypes
|
|
19377
|
-
includeStopCodon
|
|
19371
|
+
coerceFeatureTypes
|
|
19378
19372
|
} = options;
|
|
19379
19373
|
[
|
|
19380
19374
|
"isDNA",
|
|
@@ -19434,8 +19428,7 @@ function validateSequence(sequence, options = {}) {
|
|
|
19434
19428
|
const [validChars, warnings] = filterSequenceString(sequence.sequence, {
|
|
19435
19429
|
name: sequence.name,
|
|
19436
19430
|
isProtein: true,
|
|
19437
|
-
additionalValidChars
|
|
19438
|
-
includeStopCodon
|
|
19431
|
+
additionalValidChars
|
|
19439
19432
|
});
|
|
19440
19433
|
if (validChars !== sequence.sequence) {
|
|
19441
19434
|
sequence.sequence = validChars;
|
package/index.umd.js
CHANGED
|
@@ -6172,7 +6172,7 @@ var __async = (__this, __arguments, generator) => {
|
|
|
6172
6172
|
})(lodash, lodash.exports);
|
|
6173
6173
|
var lodashExports = lodash.exports;
|
|
6174
6174
|
const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
|
|
6175
|
-
const
|
|
6175
|
+
const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
|
|
6176
6176
|
const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
|
|
6177
6177
|
const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
|
|
6178
6178
|
const aminoAcidToDegenerateDnaMap = {
|
|
@@ -11283,15 +11283,13 @@ var __async = (__this, __arguments, generator) => {
|
|
|
11283
11283
|
name: name2,
|
|
11284
11284
|
isProtein,
|
|
11285
11285
|
isRna,
|
|
11286
|
-
isMixedRnaAndDna
|
|
11287
|
-
includeStopCodon
|
|
11286
|
+
isMixedRnaAndDna
|
|
11288
11287
|
} = {}) {
|
|
11289
11288
|
const acceptedChars = getAcceptedChars({
|
|
11290
11289
|
isOligo,
|
|
11291
11290
|
isProtein,
|
|
11292
11291
|
isRna,
|
|
11293
|
-
isMixedRnaAndDna
|
|
11294
|
-
includeStopCodon
|
|
11292
|
+
isMixedRnaAndDna
|
|
11295
11293
|
});
|
|
11296
11294
|
const replaceChars = getReplaceChars({
|
|
11297
11295
|
isOligo,
|
|
@@ -11341,10 +11339,9 @@ var __async = (__this, __arguments, generator) => {
|
|
|
11341
11339
|
isOligo,
|
|
11342
11340
|
isProtein,
|
|
11343
11341
|
isRna,
|
|
11344
|
-
isMixedRnaAndDna
|
|
11345
|
-
includeStopCodon
|
|
11342
|
+
isMixedRnaAndDna
|
|
11346
11343
|
} = {}) {
|
|
11347
|
-
return isProtein ? `${
|
|
11344
|
+
return isProtein ? `${extended_protein_letters.toLowerCase()}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
|
|
11348
11345
|
//just plain old dna
|
|
11349
11346
|
ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
|
|
11350
11347
|
);
|
|
@@ -11498,7 +11495,7 @@ var __async = (__this, __arguments, generator) => {
|
|
|
11498
11495
|
const {
|
|
11499
11496
|
annotationsAsObjects,
|
|
11500
11497
|
logMessages,
|
|
11501
|
-
|
|
11498
|
+
doNotRemoveInvalidChars,
|
|
11502
11499
|
additionalValidChars,
|
|
11503
11500
|
noTranslationData,
|
|
11504
11501
|
doNotProvideIdsForAnnotations,
|
|
@@ -11532,11 +11529,9 @@ var __async = (__this, __arguments, generator) => {
|
|
|
11532
11529
|
if (seqData.isRna) {
|
|
11533
11530
|
seqData.sequence = seqData.sequence.replace(/t/gi, "u");
|
|
11534
11531
|
}
|
|
11535
|
-
if (
|
|
11532
|
+
if (!doNotRemoveInvalidChars) {
|
|
11536
11533
|
if (seqData.isProtein) {
|
|
11537
|
-
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
|
|
11538
|
-
includeStopCodon: true
|
|
11539
|
-
}, topLevelSeqData || seqData));
|
|
11534
|
+
const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
|
|
11540
11535
|
seqData.proteinSequence = newSeq;
|
|
11541
11536
|
} else {
|
|
11542
11537
|
const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
|
|
@@ -19377,8 +19372,7 @@ var __async = (__this, __arguments, generator) => {
|
|
|
19377
19372
|
inclusive1BasedEnd,
|
|
19378
19373
|
additionalValidChars,
|
|
19379
19374
|
allowOverflowAnnotations,
|
|
19380
|
-
coerceFeatureTypes
|
|
19381
|
-
includeStopCodon
|
|
19375
|
+
coerceFeatureTypes
|
|
19382
19376
|
} = options;
|
|
19383
19377
|
[
|
|
19384
19378
|
"isDNA",
|
|
@@ -19438,8 +19432,7 @@ var __async = (__this, __arguments, generator) => {
|
|
|
19438
19432
|
const [validChars, warnings] = filterSequenceString(sequence.sequence, {
|
|
19439
19433
|
name: sequence.name,
|
|
19440
19434
|
isProtein: true,
|
|
19441
|
-
additionalValidChars
|
|
19442
|
-
includeStopCodon
|
|
19435
|
+
additionalValidChars
|
|
19443
19436
|
});
|
|
19444
19437
|
if (validChars !== sequence.sequence) {
|
|
19445
19438
|
sequence.sequence = validChars;
|
package/package.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@teselagen/bio-parsers",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.2",
|
|
4
4
|
"dependencies": {
|
|
5
|
-
"@teselagen/sequence-utils": "0.3.
|
|
5
|
+
"@teselagen/sequence-utils": "0.3.10",
|
|
6
6
|
"@teselagen/range-utils": "0.3.7",
|
|
7
7
|
"@gmod/gff": "^1.2.1",
|
|
8
8
|
"buffer": "^6.0.3",
|
|
@@ -30,7 +30,6 @@ export default function validateSequence(sequence, options = {}) {
|
|
|
30
30
|
additionalValidChars,
|
|
31
31
|
allowOverflowAnnotations,
|
|
32
32
|
coerceFeatureTypes,
|
|
33
|
-
includeStopCodon
|
|
34
33
|
} = options;
|
|
35
34
|
[
|
|
36
35
|
"isDNA",
|
|
@@ -97,7 +96,6 @@ export default function validateSequence(sequence, options = {}) {
|
|
|
97
96
|
name: sequence.name,
|
|
98
97
|
isProtein: true,
|
|
99
98
|
additionalValidChars,
|
|
100
|
-
includeStopCodon
|
|
101
99
|
});
|
|
102
100
|
if (validChars !== sequence.sequence) {
|
|
103
101
|
sequence.sequence = validChars;
|