@teselagen/sequence-utils 0.3.14 → 0.3.15

package/getAminoAcidStringFromSequenceString.d.ts

@@ -1 +1,3 @@
-export default function getAminoAcidStringFromSequenceString(sequenceString: any): string;
+export default function getAminoAcidStringFromSequenceString(sequenceString: any, { doNotExcludeAsterisk }?: {
+    doNotExcludeAsterisk: any;
+}): string;

package/index.js

@@ -21349,7 +21349,7 @@ function escapeStringRegexp(string) {
   return string.replace(/[|\\{}()[\]^$+*?.]/g, "\\$&").replace(/-/g, "\\x2d");
 }
 __name(escapeStringRegexp, "escapeStringRegexp");
-function getAminoAcidStringFromSequenceString(sequenceString) {
+function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
   const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
     sequenceString,
     true
@@ -21360,7 +21360,7 @@ function getAminoAcidStringFromSequenceString(sequenceString) {
     if (!aa.fullCodon) {
       return;
     }
-    if (index === aminoAcidsPerBase.length - 1 && aa.aminoAcid.value === "*") {
+    if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
       return;
     }
     aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
@@ -21417,18 +21417,22 @@ function findSequenceMatchesTopStrand(sequence, searchString, options = {}) {
   if (isProteinSearch) {
     sequencesToCheck = [
       {
-        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse),
+        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse, {
+          doNotExcludeAsterisk: true
+        }),
         offset: 0
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(1)
+          sequenceToUse.substr(1),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 1
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(2)
+          sequenceToUse.substr(2),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 2
       }
@@ -21522,7 +21526,7 @@ function getCodonRangeForAASliver(aminoAcidPositionInSequence, aminoAcidSliver,
 }
 __name(getCodonRangeForAASliver, "getCodonRangeForAASliver");
 function getComplementAminoAcidStringFromSequenceString(sequenceString) {
-  const aaString = getAminoAcidStringFromSequenceString(sequenceString);
+  const aaString = getAminoAcidStringFromSequenceString(sequenceString, true);
   return aaString.split("").reverse().join("");
 }
 __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");

package/index.mjs

@@ -21347,7 +21347,7 @@ function escapeStringRegexp(string) {
   return string.replace(/[|\\{}()[\]^$+*?.]/g, "\\$&").replace(/-/g, "\\x2d");
 }
 __name(escapeStringRegexp, "escapeStringRegexp");
-function getAminoAcidStringFromSequenceString(sequenceString) {
+function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
   const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
     sequenceString,
     true
@@ -21358,7 +21358,7 @@ function getAminoAcidStringFromSequenceString(sequenceString) {
     if (!aa.fullCodon) {
       return;
     }
-    if (index === aminoAcidsPerBase.length - 1 && aa.aminoAcid.value === "*") {
+    if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
       return;
     }
     aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
@@ -21415,18 +21415,22 @@ function findSequenceMatchesTopStrand(sequence, searchString, options = {}) {
   if (isProteinSearch) {
     sequencesToCheck = [
       {
-        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse),
+        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse, {
+          doNotExcludeAsterisk: true
+        }),
         offset: 0
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(1)
+          sequenceToUse.substr(1),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 1
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(2)
+          sequenceToUse.substr(2),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 2
       }
@@ -21520,7 +21524,7 @@ function getCodonRangeForAASliver(aminoAcidPositionInSequence, aminoAcidSliver,
 }
 __name(getCodonRangeForAASliver, "getCodonRangeForAASliver");
 function getComplementAminoAcidStringFromSequenceString(sequenceString) {
-  const aaString = getAminoAcidStringFromSequenceString(sequenceString);
+  const aaString = getAminoAcidStringFromSequenceString(sequenceString, true);
   return aaString.split("").reverse().join("");
 }
 __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");

package/index.umd.js

@@ -21351,7 +21351,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     return string.replace(/[|\\{}()[\]^$+*?.]/g, "\\$&").replace(/-/g, "\\x2d");
   }
   __name(escapeStringRegexp, "escapeStringRegexp");
-  function getAminoAcidStringFromSequenceString(sequenceString) {
+  function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
     const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
       sequenceString,
       true
@@ -21362,7 +21362,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
       if (!aa.fullCodon) {
         return;
       }
-      if (index === aminoAcidsPerBase.length - 1 && aa.aminoAcid.value === "*") {
+      if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
         return;
       }
       aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
@@ -21419,18 +21419,22 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     if (isProteinSearch) {
       sequencesToCheck = [
         {
-          seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse),
+          seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse, {
+            doNotExcludeAsterisk: true
+          }),
           offset: 0
         },
         {
           seqToCheck: getAminoAcidStringFromSequenceString(
-            sequenceToUse.substr(1)
+            sequenceToUse.substr(1),
+            { doNotExcludeAsterisk: true }
           ),
           offset: 1
         },
         {
           seqToCheck: getAminoAcidStringFromSequenceString(
-            sequenceToUse.substr(2)
+            sequenceToUse.substr(2),
+            { doNotExcludeAsterisk: true }
           ),
           offset: 2
         }
@@ -21524,7 +21528,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   }
   __name(getCodonRangeForAASliver, "getCodonRangeForAASliver");
   function getComplementAminoAcidStringFromSequenceString(sequenceString) {
-    const aaString = getAminoAcidStringFromSequenceString(sequenceString);
+    const aaString = getAminoAcidStringFromSequenceString(sequenceString, true);
     return aaString.split("").reverse().join("");
   }
   __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.14",
+  "version": "0.3.15",
   "dependencies": {
     "@teselagen/range-utils": "0.3.7",
     "bson-objectid": "^2.0.4",

package/src/findSequenceMatches.js

@@ -64,18 +64,22 @@ function findSequenceMatchesTopStrand(sequence, searchString, options = {}) {
   if (isProteinSearch) {
     sequencesToCheck = [
       {
-        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse),
+        seqToCheck: getAminoAcidStringFromSequenceString(sequenceToUse, {
+          doNotExcludeAsterisk: true
+        }),
         offset: 0
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(1)
+          sequenceToUse.substr(1),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 1
       },
       {
         seqToCheck: getAminoAcidStringFromSequenceString(
-          sequenceToUse.substr(2)
+          sequenceToUse.substr(2),
+          { doNotExcludeAsterisk: true }
         ),
         offset: 2
       }

package/src/findSequenceMatches.test.js

@@ -1,7 +1,7 @@
 import findSequenceMatches from "./findSequenceMatches";
 
 describe("findSequenceMatches", () => {
-  it("ambiguous protein sequence with * as stop codon", () => {
+  it('ambiguous protein sequence with asterisk as stop codon', () => {
     expect(
       findSequenceMatches("mmhlrl*", "Mxxlrl*", {
         isAmbiguous: true,
@@ -29,7 +29,7 @@ describe("findSequenceMatches", () => {
       }
     ]);
   });
-  it("protein sequence with * as stop codon", () => {
+  it('protein sequence with asterisk as stop codon', () => {
     expect(
       findSequenceMatches("mmhlrl*", "mMh", {
         isProteinSequence: true /* isProteinSearch: true */
@@ -132,11 +132,11 @@ describe("findSequenceMatches", () => {
     const matches = findSequenceMatches("atg", "*", { isAmbiguous: true });
     expect(matches).toEqual([]);
   });
-  it("ambiguous, dna searches with *", () => {
+  it('ambiguous, dna searches with asterisk', () => {
     const matches = findSequenceMatches("atg", "", { isAmbiguous: true });
     expect(matches).toEqual([]);
   });
-  it(" AA with * as stop codon", () => {
+  it('AA with asterisk as stop codon in atgtaa', () => {
     expect(
       findSequenceMatches("atgtaa", "M*", { isProteinSearch: true })
     ).toEqual([
@@ -146,7 +146,7 @@ describe("findSequenceMatches", () => {
       }
     ]);
   });
-  it(" AA with * as stop codon", () => {
+  it('AA with asterisk as stop codon in atgtaaccc', () => {
     expect(
       findSequenceMatches("atgtaaccc", "M**", { isProteinSearch: true })
     ).toEqual([]);
@@ -164,7 +164,7 @@ describe("findSequenceMatches", () => {
       }
     ]);
   });
-  it("works with ambiguous AA with * in search string", () => {
+  it('works with ambiguous AA with asterisk in search string', () => {
     expect(
       findSequenceMatches("atgtaa", "M*", {
         isProteinSearch: true,

package/src/getAminoAcidStringFromSequenceString.js

@@ -1,6 +1,6 @@
 import getAminoAcidDataForEachBaseOfDna from "./getAminoAcidDataForEachBaseOfDna";
 
-export default function getAminoAcidStringFromSequenceString(sequenceString) {
+export default function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
   const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
     sequenceString,
     true
@@ -12,7 +12,7 @@ export default function getAminoAcidStringFromSequenceString(sequenceString) {
       return;
     }
     // Check if the current amino acid is the last in the sequence and is a stop codon
-    if (index === aminoAcidsPerBase.length - 1 && aa.aminoAcid.value === '*') {
+    if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === '*') {
       return;
     }
     aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;