@teselagen/sequence-utils 0.3.14 → 0.3.17

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

@@ -12323,6 +12323,20 @@ const modifiableTypes = [
   "primers",
   "guides"
 ];
+let allWarnings = [];
+let makeToast = /* @__PURE__ */ __name(() => {
+  if (typeof window !== "undefined" && window.toastr && allWarnings.length) {
+    window.toastr.warning(allWarnings.join("\n"));
+  }
+  allWarnings = [];
+}, "makeToast");
+makeToast = lodashExports.debounce(makeToast, 200);
+function showWarnings(warnings) {
+  allWarnings = allWarnings.concat(warnings);
+  makeToast.cancel();
+  makeToast();
+}
+__name(showWarnings, "showWarnings");
 function filterSequenceString(sequenceString = "", {
   additionalValidChars = "",
   isOligo,
@@ -12370,14 +12384,10 @@ function filterSequenceString(sequenceString = "", {
   });
   if (sequenceString.length !== sanitizedVal.length) {
     warnings.push(
-      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
     );
   }
-  if (typeof window !== "undefined" && window.toastr && warnings.length) {
-    warnings.forEach((warning) => {
-      window.toastr.warning(warning);
-    });
-  }
+  showWarnings(warnings);
   return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
@@ -21349,7 +21359,7 @@ 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 +21370,7 @@ 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 +21427,22 @@ 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 +21536,7 @@ 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

@@ -12321,6 +12321,20 @@ const modifiableTypes = [
   "primers",
   "guides"
 ];
+let allWarnings = [];
+let makeToast = /* @__PURE__ */ __name(() => {
+  if (typeof window !== "undefined" && window.toastr && allWarnings.length) {
+    window.toastr.warning(allWarnings.join("\n"));
+  }
+  allWarnings = [];
+}, "makeToast");
+makeToast = lodashExports.debounce(makeToast, 200);
+function showWarnings(warnings) {
+  allWarnings = allWarnings.concat(warnings);
+  makeToast.cancel();
+  makeToast();
+}
+__name(showWarnings, "showWarnings");
 function filterSequenceString(sequenceString = "", {
   additionalValidChars = "",
   isOligo,
@@ -12368,14 +12382,10 @@ function filterSequenceString(sequenceString = "", {
   });
   if (sequenceString.length !== sanitizedVal.length) {
     warnings.push(
-      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
     );
   }
-  if (typeof window !== "undefined" && window.toastr && warnings.length) {
-    warnings.forEach((warning) => {
-      window.toastr.warning(warning);
-    });
-  }
+  showWarnings(warnings);
   return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
@@ -21347,7 +21357,7 @@ 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 +21368,7 @@ 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 +21425,22 @@ 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 +21534,7 @@ 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

@@ -12325,6 +12325,20 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     "primers",
     "guides"
   ];
+  let allWarnings = [];
+  let makeToast = /* @__PURE__ */ __name(() => {
+    if (typeof window !== "undefined" && window.toastr && allWarnings.length) {
+      window.toastr.warning(allWarnings.join("\n"));
+    }
+    allWarnings = [];
+  }, "makeToast");
+  makeToast = lodashExports.debounce(makeToast, 200);
+  function showWarnings(warnings) {
+    allWarnings = allWarnings.concat(warnings);
+    makeToast.cancel();
+    makeToast();
+  }
+  __name(showWarnings, "showWarnings");
   function filterSequenceString(sequenceString = "", {
     additionalValidChars = "",
     isOligo,
@@ -12372,14 +12386,10 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     });
     if (sequenceString.length !== sanitizedVal.length) {
       warnings.push(
-        `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+        `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
       );
     }
-    if (typeof window !== "undefined" && window.toastr && warnings.length) {
-      warnings.forEach((warning) => {
-        window.toastr.warning(warning);
-      });
-    }
+    showWarnings(warnings);
     return [sanitizedVal, warnings];
   }
   __name(filterSequenceString, "filterSequenceString");
@@ -21351,7 +21361,7 @@ 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 +21372,7 @@ 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 +21429,22 @@ 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 +21538,7 @@ 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": "0.3.17",
   "dependencies": {
     "@teselagen/range-utils": "0.3.7",
     "bson-objectid": "^2.0.4",

package/src/filterSequenceString.js

@@ -1,9 +1,27 @@
+import { debounce, uniq } from "lodash";
 import {
   ambiguous_dna_letters,
   ambiguous_rna_letters,
   extended_protein_letters
 } from "./bioData";
 
+let allWarnings = [];
+
+let makeToast = () => {
+  if (typeof window !== "undefined" && window.toastr && allWarnings.length) {
+    window.toastr.warning(allWarnings.join("\n"));
+  }
+  allWarnings = [];
+};
+
+makeToast = debounce(makeToast, 200);
+
+function showWarnings(warnings) {
+  allWarnings = allWarnings.concat(warnings);
+  makeToast.cancel();
+  makeToast();
+}
+
 export default function filterSequenceString(
   sequenceString = "",
   {
@@ -62,16 +80,12 @@ export default function filterSequenceString(
     warnings.push(
       `${
         name ? `Sequence ${name}: ` : ""
-      }Invalid character(s) detected and removed: ${invalidChars
+      }Invalid character(s) detected and removed: ${uniq(invalidChars)
         .slice(0, 100)
         .join(", ")} `
     );
   }
-  if (typeof window !== "undefined" && window.toastr && warnings.length) {
-    warnings.forEach(warning => {
-      window.toastr.warning(warning);
-    });
-  }
+  showWarnings(warnings);
 
   return [sanitizedVal, warnings];
 }
@@ -85,13 +99,15 @@ export function getAcceptedChars({
   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();
+      ? 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();
 }
 export function getReplaceChars({
   isOligo,
@@ -102,14 +118,14 @@ export function getReplaceChars({
   return isProtein
     ? {}
     : // {".": "*"}
-    isOligo
-    ? {}
-    : isRna
-    ? { t: "u" }
-    : isMixedRnaAndDna
-    ? {}
-    : //just plain old dna
-      {};
+      isOligo
+      ? {}
+      : isRna
+        ? { t: "u" }
+        : isMixedRnaAndDna
+          ? {}
+          : //just plain old dna
+            {};
 }
 
 export const filterRnaString = (s, o) =>

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 +1,9 @@
 import getAminoAcidDataForEachBaseOfDna from "./getAminoAcidDataForEachBaseOfDna";
 
-export default function getAminoAcidStringFromSequenceString(sequenceString) {
+export default function getAminoAcidStringFromSequenceString(
+  sequenceString,
+  { doNotExcludeAsterisk } = {}
+) {
   const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
     sequenceString,
     true
@@ -12,7 +15,11 @@ 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;