@teselagen/sequence-utils 0.3.9 → 0.3.10

package/bioData.d.ts

@@ -1,6 +1,6 @@
 export const protein_letters: "ACDEFGHIKLMNPQRSTVWY";
 export const protein_letters_withUandX: "ACDEFGHIKLMNPQRSTVWYUX";
-export const extended_protein_letters: "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+export const extended_protein_letters: "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 export const ambiguous_dna_letters: "GATCRYWSMKHBVDN";
 export const unambiguous_dna_letters: "GATC";
 export const ambiguous_rna_letters: "GAUCRYWSMKHBVDN";

package/filterSequenceString.d.ts

@@ -1,18 +1,16 @@
-export default function filterSequenceString(sequenceString: any, { additionalValidChars, isOligo, name, isProtein, isRna, isMixedRnaAndDna, includeStopCodon }?: {
+export default function filterSequenceString(sequenceString: any, { additionalValidChars, isOligo, name, isProtein, isRna, isMixedRnaAndDna, }?: {
     additionalValidChars?: string | undefined;
     isOligo: any;
     name: any;
     isProtein: any;
     isRna: any;
     isMixedRnaAndDna: any;
-    includeStopCodon: any;
 }): (string | string[])[];
-export function getAcceptedChars({ isOligo, isProtein, isRna, isMixedRnaAndDna, includeStopCodon }?: {
+export function getAcceptedChars({ isOligo, isProtein, isRna, isMixedRnaAndDna, }?: {
     isOligo: any;
     isProtein: any;
     isRna: any;
     isMixedRnaAndDna: any;
-    includeStopCodon: any;
 }): string;
 export function getReplaceChars({ isOligo, isProtein, isRna, isMixedRnaAndDna }?: {
     isOligo: any;

package/index.js

@@ -6000,7 +6000,7 @@ lodash.exports;
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -12329,15 +12329,13 @@ function filterSequenceString(sequenceString, {
   name,
   isProtein,
   isRna,
-  isMixedRnaAndDna,
-  includeStopCodon
+  isMixedRnaAndDna
 } = {}) {
   const acceptedChars = getAcceptedChars({
     isOligo,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
-    includeStopCodon
+    isMixedRnaAndDna
   });
   const replaceChars = getReplaceChars({
     isOligo,
@@ -12387,10 +12385,9 @@ function getAcceptedChars({
   isOligo,
   isProtein,
   isRna,
-  isMixedRnaAndDna,
-  includeStopCodon
+  isMixedRnaAndDna
 } = {}) {
-  return isProtein ? `${protein_letters_withUandX.toLowerCase()}${includeStopCodon ? "*." : ""}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
+  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() : (
     //just plain old dna
     ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
   );
@@ -12544,7 +12541,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
     doNotProvideIdsForAnnotations,
@@ -12578,11 +12575,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   if (seqData.isRna) {
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
-        includeStopCodon: true
-      }, topLevelSeqData || seqData));
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
       seqData.proteinSequence = newSeq;
     } else {
       const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({

package/index.mjs

@@ -5998,7 +5998,7 @@ lodash.exports;
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -12327,15 +12327,13 @@ function filterSequenceString(sequenceString, {
   name,
   isProtein,
   isRna,
-  isMixedRnaAndDna,
-  includeStopCodon
+  isMixedRnaAndDna
 } = {}) {
   const acceptedChars = getAcceptedChars({
     isOligo,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
-    includeStopCodon
+    isMixedRnaAndDna
   });
   const replaceChars = getReplaceChars({
     isOligo,
@@ -12385,10 +12383,9 @@ function getAcceptedChars({
   isOligo,
   isProtein,
   isRna,
-  isMixedRnaAndDna,
-  includeStopCodon
+  isMixedRnaAndDna
 } = {}) {
-  return isProtein ? `${protein_letters_withUandX.toLowerCase()}${includeStopCodon ? "*." : ""}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
+  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() : (
     //just plain old dna
     ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
   );
@@ -12542,7 +12539,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
     doNotProvideIdsForAnnotations,
@@ -12576,11 +12573,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   if (seqData.isRna) {
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
-        includeStopCodon: true
-      }, topLevelSeqData || seqData));
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
       seqData.proteinSequence = newSeq;
     } else {
       const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({

package/index.umd.js

@@ -6002,7 +6002,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   var lodashExports = lodash.exports;
   const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
   const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
   const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
   const unambiguous_dna_letters = "GATC";
   const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -12331,15 +12331,13 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     name,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
-    includeStopCodon
+    isMixedRnaAndDna
   } = {}) {
     const acceptedChars = getAcceptedChars({
       isOligo,
       isProtein,
       isRna,
-      isMixedRnaAndDna,
-      includeStopCodon
+      isMixedRnaAndDna
     });
     const replaceChars = getReplaceChars({
       isOligo,
@@ -12389,10 +12387,9 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     isOligo,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
-    includeStopCodon
+    isMixedRnaAndDna
   } = {}) {
-    return isProtein ? `${protein_letters_withUandX.toLowerCase()}${includeStopCodon ? "*." : ""}}` : isOligo ? ambiguous_rna_letters.toLowerCase() + "t" : isRna ? ambiguous_rna_letters.toLowerCase() + "t" : isMixedRnaAndDna ? ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase() : (
+    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() : (
       //just plain old dna
       ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase()
     );
@@ -12546,7 +12543,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     const {
       annotationsAsObjects,
       logMessages,
-      removeUnwantedChars,
+      doNotRemoveInvalidChars,
       additionalValidChars,
       noTranslationData,
       doNotProvideIdsForAnnotations,
@@ -12580,11 +12577,9 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     if (seqData.isRna) {
       seqData.sequence = seqData.sequence.replace(/t/gi, "u");
     }
-    if (removeUnwantedChars) {
+    if (!doNotRemoveInvalidChars) {
       if (seqData.isProtein) {
-        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
-          includeStopCodon: true
-        }, topLevelSeqData || seqData));
+        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
         seqData.proteinSequence = newSeq;
       } else {
         const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.9",
+  "version": "0.3.10",
   "dependencies": {
     "@teselagen/range-utils": "0.3.7",
     "bson-objectid": "^2.0.4",

package/src/bioData.js

@@ -2,8 +2,7 @@
 
 export const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 export const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-
-export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 export const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 export const unambiguous_dna_letters = "GATC";
 export const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";

package/src/filterSequenceString.js

@@ -1,7 +1,7 @@
 import {
   ambiguous_dna_letters,
   ambiguous_rna_letters,
-  protein_letters_withUandX
+  extended_protein_letters,
 } from "./bioData";
 
 export default function filterSequenceString(
@@ -13,7 +13,6 @@ export default function filterSequenceString(
     isProtein,
     isRna,
     isMixedRnaAndDna,
-    includeStopCodon
   } = {}
 ) {
   const acceptedChars = getAcceptedChars({
@@ -21,7 +20,6 @@ export default function filterSequenceString(
     isProtein,
     isRna,
     isMixedRnaAndDna,
-    includeStopCodon
   });
   const replaceChars = getReplaceChars({
     isOligo,
@@ -83,12 +81,9 @@ export function getAcceptedChars({
   isProtein,
   isRna,
   isMixedRnaAndDna,
-  includeStopCodon
 } = {}) {
   return isProtein
-    ? `${protein_letters_withUandX.toLowerCase()}${
-        includeStopCodon ? "*." : ""
-      }}`
+    ? `${extended_protein_letters.toLowerCase()}}`
     : isOligo
     ? ambiguous_rna_letters.toLowerCase() + "t"
     : isRna
@@ -106,6 +101,7 @@ export function getReplaceChars({
 } = {}) {
   return isProtein
     ? {}
+    // {".": "*"}
     : isOligo
     ? {}
     : isRna

package/src/filterSequenceString.test.js

@@ -49,10 +49,9 @@ describe("filterSequenceString", () => {
         isProtein: true
       }
     );
-    expect(warnings[0]).toBe(
-      'Invalid character(s) detected and removed: b, b, b, 3, 4, 2, ", ", ", ,, ,, ., ., / '
-    );
-    expect(str).toBe("xtgalmfwkqespvicyhrnd");
+    // expect(warnings[0]).toBe(`Replaced "." with "*" 2 times`);
+    expect(warnings[0]).toBe(      'Invalid character(s) detected and removed: 3, 4, 2, ", ", ", ,, ,, ., ., / ');
+    expect(str).toBe("bbbxtgalmfwkqespvicyhrnd");
   });
   it("when isProtein: true, should handle upper case letters", () => {
     const [str, warnings] = filterSequenceString("xtgalmfWKQEspvicyhrnd", {
@@ -61,12 +60,11 @@ describe("filterSequenceString", () => {
     expect(warnings.length).toBe(0);
     expect(str).toBe("xtgalmfWKQEspvicyhrnd");
   });
-  it("when isProtein: true, should handle the option to includeStopCodon by allowing periods", () => {
-    const [str] = filterSequenceString('bbb342"""xtgalmfwkqespvicyhrnd,,../', {
+  it("when isProtein: true, it should convert . to *", () => {
+    const [str] = filterSequenceString('BXZJUO*bbb342"""xtgalbmfwkqespvicyhrnd,,../', {
       isProtein: true,
-      includeStopCodon: true
     });
 
-    expect(str).toBe("xtgalmfwkqespvicyhrnd..");
+    expect(str).toBe("BXZJUO*bbbxtgalbmfwkqespvicyhrnd");
   });
 });

package/src/tidyUpSequenceData.js

@@ -13,7 +13,7 @@ export default function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
     doNotProvideIdsForAnnotations,
@@ -52,10 +52,9 @@ export default function tidyUpSequenceData(pSeqData, options = {}) {
     //flip all t's to u's
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
       const [newSeq] = filterSequenceString(seqData.proteinSequence, {
-        includeStopCodon: true,
         ...(topLevelSeqData || seqData)
       });
       seqData.proteinSequence = newSeq;

package/src/tidyUpSequenceData.test.js

@@ -5,7 +5,7 @@ import chaiSubset from "chai-subset";
 chai.use(chaiSubset);
 chai.should();
 describe("tidyUpSequenceData", () => {
-  it("should remove unwanted chars if passed that option, while handling annotation start,end (and location start,end) truncation correctly", () => {
+  it("should remove invalid chars by default, while handling annotation start,end (and location start,end) truncation correctly", () => {
     const res = tidyUpSequenceData(
       {
         sequence: "http://localhost:3344/Standalone",
@@ -26,7 +26,7 @@ describe("tidyUpSequenceData", () => {
           }
         ]
       },
-      { removeUnwantedChars: true }
+      
     );
     res.should.containSubset({
       sequence: "httcahstStandan",
@@ -49,15 +49,6 @@ describe("tidyUpSequenceData", () => {
       ]
     });
   });
-  // const res = tidyUpSequenceData(
-  //   {
-  //     isProtein: true,
-  //     circular: true,
-  //     proteinSequence: "gagiuhwgagalasjglj*.",
-  //     features: [{ start: 3, end: 10 }, { start: 10, end: 20 }]
-  //   },
-  //   { convertAnnotationsFromAAIndices: true, removeUnwantedChars: true }
-  // );
 
   it("should handle a protein sequence being passed in with isProtein set to true", () => {
     const res = tidyUpSequenceData(
@@ -71,69 +62,24 @@ describe("tidyUpSequenceData", () => {
           { name: "iDon'tFit", start: 25, end: 35 }
         ]
       },
-      { convertAnnotationsFromAAIndices: true, removeUnwantedChars: true }
+      { convertAnnotationsFromAAIndices: true }
     );
+    
     res.should.containSubset({
-      aminoAcidDataForEachBaseOfDNA: [
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 0,
-          aminoAcidIndex: 17,
-          sequenceIndex: 51,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        },
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 1,
-          aminoAcidIndex: 17,
-          sequenceIndex: 52,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        },
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 2,
-          aminoAcidIndex: 17,
-          sequenceIndex: 53,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        }
-      ],
+      aminoAcidDataForEachBaseOfDNA: [],
       isProtein: true,
-      size: 54, //size should refer to the DNA length
-      proteinSize: 18, //proteinSize should refer to the amino acid length
-      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnggnytntrr...", //degenerate sequence
-      proteinSequence: "gagiuhwgagalasgl*.",
+      size: 57, //size should refer to the DNA length
+      proteinSize: 19, //proteinSize should refer to the amino acid length
+      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnhtnggnytnhtntrr", //degenerate sequence
+      proteinSequence: "gagiuhwgagalasjglj*",
       circular: false,
       features: [
         { start: 9, end: 32, forward: true },
-        { start: 30, end: 53, forward: true },
+        { start: 30, end: 56, forward: true },
         {
           name: "iDon'tFit",
-          start: 51,
-          end: 53,
+          start: 54,
+          end: 56,
           forward: true
         }
       ]