@teselagen/sequence-utils 0.3.7 → 0.3.9

package/src/deleteSequenceDataAtRange.test.js

@@ -1,10 +1,9 @@
 //tnr: half finished test.
 
-
 import chai from "chai";
 
-import {getRangeLength} from "@teselagen/range-utils";
-import {cloneDeep} from "lodash";
+import { getRangeLength } from "@teselagen/range-utils";
+import { cloneDeep } from "lodash";
 import chaiSubset from "chai-subset";
 
 import deleteSequenceDataAtRange from "./deleteSequenceDataAtRange";
@@ -18,7 +17,10 @@ describe("deleteSequenceDataAtRange", () => {
       sequence: "atagatag"
     };
     const range = { start: 0, end: 7 };
-    const postDeleteSeqData = deleteSequenceDataAtRange(existingSequence, range);
+    const postDeleteSeqData = deleteSequenceDataAtRange(
+      existingSequence,
+      range
+    );
     postDeleteSeqData.sequence.length.should.equal(
       existingSequence.sequence.length - getRangeLength(range)
     );
@@ -28,7 +30,10 @@ describe("deleteSequenceDataAtRange", () => {
       sequence: "atagatag"
     };
     const range = { start: 4, end: 3 };
-    const postDeleteSeqData = deleteSequenceDataAtRange(existingSequence, range);
+    const postDeleteSeqData = deleteSequenceDataAtRange(
+      existingSequence,
+      range
+    );
     postDeleteSeqData.sequence.length.should.equal(
       existingSequence.sequence.length -
         getRangeLength(range, existingSequence.sequence.length)
@@ -39,7 +44,10 @@ describe("deleteSequenceDataAtRange", () => {
       sequence: "atagatag"
     };
     const range = { start: 3, end: 5 };
-    const postDeleteSeqData = deleteSequenceDataAtRange(existingSequence, range);
+    const postDeleteSeqData = deleteSequenceDataAtRange(
+      existingSequence,
+      range
+    );
     postDeleteSeqData.sequence.length.should.equal(
       existingSequence.sequence.length - getRangeLength(range)
     );
@@ -48,7 +56,7 @@ describe("deleteSequenceDataAtRange", () => {
     const existingSequence = {
       sequence: "atagatag",
       features: {
-        "1": {
+        1: {
           start: 7,
           end: 7
         }
@@ -56,7 +64,10 @@ describe("deleteSequenceDataAtRange", () => {
     };
     const clonedExistingSeq = cloneDeep(existingSequence);
     const range = { start: 3, end: 5 };
-    const postDeleteSeqData = deleteSequenceDataAtRange(existingSequence, range);
+    const postDeleteSeqData = deleteSequenceDataAtRange(
+      existingSequence,
+      range
+    );
     existingSequence.should.deep.equal(clonedExistingSeq);
     postDeleteSeqData.sequence.length.should.equal(
       existingSequence.sequence.length - getRangeLength(range)
@@ -78,7 +89,10 @@ describe("deleteSequenceDataAtRange", () => {
       ]
     };
     const range = { start: -1, end: -1 };
-    const postDeleteSeqData = deleteSequenceDataAtRange(existingSequence, range);
+    const postDeleteSeqData = deleteSequenceDataAtRange(
+      existingSequence,
+      range
+    );
     postDeleteSeqData.should.containSubset({
       sequence: "atgagagaga",
       features: [

package/src/diffUtils.js

@@ -13,7 +13,7 @@ const getDiffFromSeqs = (oldData, newData, { ignoreKeys = [] } = {}) => {
     noTranslationData: true
   });
 
-  [oldData, newData].forEach((d) => {
+  [oldData, newData].forEach(d => {
     [
       "cutsites",
       "orfs",
@@ -23,7 +23,7 @@ const getDiffFromSeqs = (oldData, newData, { ignoreKeys = [] } = {}) => {
       "description",
       "materiallyAvailable",
       ...ignoreKeys
-    ].forEach((prop) => {
+    ].forEach(prop => {
       delete d[prop];
     });
     if (d.translations) {
@@ -43,7 +43,7 @@ const getDiffFromSeqs = (oldData, newData, { ignoreKeys = [] } = {}) => {
   return diff(oldData, newData);
 };
 const patchSeqWithDiff = (oldData, diff, { ignoreKeys = [] } = {}) => {
-  ignoreKeys.forEach((k) => {
+  ignoreKeys.forEach(k => {
     delete diff[k];
   });
   return patch(
@@ -51,7 +51,7 @@ const patchSeqWithDiff = (oldData, diff, { ignoreKeys = [] } = {}) => {
     diff
   );
 };
-const reverseSeqDiff = (diff) => {
+const reverseSeqDiff = diff => {
   return reverse(diff);
 };
 

package/src/diffUtils.test.js

@@ -1,8 +1,8 @@
 import chai from "chai";
 import assert from "assert";
-import {map} from "lodash";
+import { map } from "lodash";
 import tidyUpSequenceData from "./tidyUpSequenceData";
-import {getDiffFromSeqs, patchSeqWithDiff, reverseSeqDiff} from "./diffUtils";
+import { getDiffFromSeqs, patchSeqWithDiff, reverseSeqDiff } from "./diffUtils";
 import chaiSubset from "chai-subset";
 
 chai.should();

package/src/doesEnzymeChopOutsideOfRecognitionSite.js

@@ -7,4 +7,4 @@ export default function doesEnzymeChopOutsideOfRecognitionSite(enzyme) {
   } else {
     return false;
   }
-};
+}

package/src/doesEnzymeChopOutsideOfRecognitionSite.test.js

@@ -1,5 +1,3 @@
-
-
 import chai from "chai";
 import doesEnzymeChopOutsideOfRecognitionSite from "./doesEnzymeChopOutsideOfRecognitionSite.js";
 import enzymeList from "./aliasedEnzymesByName";

package/src/featureTypesAndColors.js

@@ -1,4 +1,4 @@
-import {get, keyBy, filter} from "lodash";
+import { get, keyBy, filter } from "lodash";
 
 const genbankFeatureTypes = [
   { name: "-10_signal", color: "#4ECDC4" },
@@ -137,7 +137,7 @@ const getFeatureTypes = ({ includeHidden } = {}) =>
     f => f.name
   );
 
-export {genbankFeatureTypes};
+export { genbankFeatureTypes };
 
 export function getGenbankFeatureToColorMap() {
   const toRet = {};
@@ -147,6 +147,6 @@ export function getGenbankFeatureToColorMap() {
   return toRet;
 }
 
-export {getFeatureToColorMap};
-export {getFeatureTypes};
-export {getMergedFeatureMap};
+export { getFeatureToColorMap };
+export { getFeatureTypes };
+export { getMergedFeatureMap };

package/src/featureTypesAndColors.test.js

@@ -2,7 +2,7 @@ import {
   getFeatureTypes,
   getFeatureToColorMap,
   getMergedFeatureMap,
-  getGenbankFeatureToColorMap,
+  getGenbankFeatureToColorMap
 } from "./featureTypesAndColors";
 
 describe("getFeatureToColorMap", () => {

package/src/filterSequenceString.js

@@ -1,22 +1,117 @@
-// this is throwing a weird eslint error
+import {
+  ambiguous_dna_letters,
+  ambiguous_rna_letters,
+  protein_letters_withUandX
+} from "./bioData";
 
-//
 export default function filterSequenceString(
   sequenceString,
-  additionalValidChars = "",
-  charOverrides
+  {
+    additionalValidChars = "",
+    isOligo,
+    name,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna,
+    includeStopCodon
+  } = {}
 ) {
-  // ac.throw(ac.string,sequenceString);
-  if (sequenceString) {
-    return sequenceString.replace(
-      new RegExp(
-        `[^${charOverrides ||
-          `atgcyrswkmbvdhnu${additionalValidChars.split("").join("\\")}`}]`,
-        "gi"
-      ),
-      ""
+  const acceptedChars = getAcceptedChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna,
+    includeStopCodon
+  });
+  const replaceChars = getReplaceChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  });
+
+  let sanitizedVal = "";
+  const invalidChars = [];
+  const chars = `${acceptedChars}${additionalValidChars.split("").join("\\")}`;
+  const warnings = [];
+  const replaceCount = {};
+  sequenceString.split("").forEach(letter => {
+    const lowerLetter = letter.toLowerCase();
+    if (replaceChars && replaceChars[lowerLetter]) {
+      if (!replaceCount[lowerLetter]) {
+        replaceCount[lowerLetter] = 0;
+      }
+      replaceCount[lowerLetter]++;
+      const isUpper = lowerLetter !== letter;
+      sanitizedVal += isUpper
+        ? replaceChars[lowerLetter].toUpperCase()
+        : replaceChars[lowerLetter];
+    } else if (chars.includes(lowerLetter)) {
+      sanitizedVal += letter;
+    } else {
+      invalidChars.push(letter);
+    }
+  });
+  //add replace count warnings
+  Object.keys(replaceCount).forEach(letter => {
+    warnings.push(
+      `Replaced "${letter}" with "${replaceChars[letter]}"${
+        replaceCount[letter] > 1 ? ` ${replaceCount[letter]} times` : ""
+      }`
+    );
+  });
+  if (sequenceString.length !== sanitizedVal.length) {
+    warnings.push(
+      `${
+        name ? `Sequence ${name}: ` : ""
+      }Invalid character(s) detected and removed: ${invalidChars
+        .slice(0, 100)
+        .join(", ")} `
     );
-  } else {
-    return sequenceString;
   }
-};
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach(warning => {
+      window.toastr.warning(warning);
+    });
+  }
+
+  return [sanitizedVal, warnings];
+}
+
+export function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna,
+  includeStopCodon
+} = {}) {
+  return isProtein
+    ? `${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()
+    : //just plain old dna
+      ambiguous_rna_letters.toLowerCase() + ambiguous_dna_letters.toLowerCase();
+}
+export function getReplaceChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  return isProtein
+    ? {}
+    : isOligo
+    ? {}
+    : isRna
+    ? { t: "u" }
+    : isMixedRnaAndDna
+    ? {}
+    : //just plain old dna
+      {};
+}

package/src/filterSequenceString.test.js

@@ -1,13 +1,72 @@
 import filterSequenceString from "./filterSequenceString";
+import { expect } from "vitest";
 
 describe("filterSequenceString", () => {
+  it("should not filter u's and should convert t's to u's from isOligo=true seqs", () => {
+    const [str, warnings] = filterSequenceString("tatuuag--a", {
+      isOligo: true
+    });
+    expect(str).toBe("tatuuaga");
+    // expect(warnings[0]).toBe('Replaced "t" with "u" 2 times');
+    expect(warnings[0]).toBe(
+      "Invalid character(s) detected and removed: -, - "
+    );
+  });
+  it("should not convert u's to t's for isDna (default isDna=true) seqs", () => {
+    const [str, warnings] = filterSequenceString("tatuuag--a", {});
+    // expect(warnings[0]).toBe('Replaced "u" with "t" 2 times');
+    expect(warnings[0]).toBe(
+      "Invalid character(s) detected and removed: -, - "
+    );
+    expect(str).toBe("tatuuaga");
+  });
   it("should filter out unwanted chars", () => {
-    expect(filterSequenceString("tatag--a")).toBe("tataga");
+    const [str, warnings] = filterSequenceString("tatag--a");
+    expect(warnings[0]).toBe(
+      "Invalid character(s) detected and removed: -, - "
+    );
+    expect(str).toBe("tataga");
   });
   it("should handle additional chars option", () => {
-    expect(filterSequenceString("tatag--a", "-")).toBe("tatag--a");
+    const [str, warnings] = filterSequenceString("tatag--a", {
+      additionalValidChars: "-"
+    });
+    expect(warnings.length).toBe(0);
+    expect(str).toBe("tatag--a");
   });
   it("should handle additional chars option", () => {
-    expect(filterSequenceString("tatag--a", "f-q")).toBe("tatag--a");
+    const [str, warnings] = filterSequenceString("tatag--a", {
+      additionalValidChars: "f-q"
+    });
+    expect(warnings.length).toBe(0);
+    expect(str).toBe("tatag--a");
+  });
+
+  it("when isProtein: true, should filter only valid amino acids by default", () => {
+    const [str, warnings] = filterSequenceString(
+      'bbb342"""xtgalmfwkqespvicyhrnd,,../',
+      {
+        isProtein: true
+      }
+    );
+    expect(warnings[0]).toBe(
+      'Invalid character(s) detected and removed: b, b, b, 3, 4, 2, ", ", ", ,, ,, ., ., / '
+    );
+    expect(str).toBe("xtgalmfwkqespvicyhrnd");
+  });
+  it("when isProtein: true, should handle upper case letters", () => {
+    const [str, warnings] = filterSequenceString("xtgalmfWKQEspvicyhrnd", {
+      isProtein: true
+    });
+    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,,../', {
+      isProtein: true,
+      includeStopCodon: true
+    });
+
+    expect(str).toBe("xtgalmfwkqespvicyhrnd..");
   });
 });

package/src/findNearestRangeOfSequenceOverlapToPosition.js

@@ -1,4 +1,4 @@
-import {normalizeRange} from "@teselagen/range-utils";
+import { normalizeRange } from "@teselagen/range-utils";
 function findNearestRangeOfSequenceOverlapToPosition(
   sequenceToSearch,
   overlapSequence,

package/src/findOrfsInPlasmid.js

@@ -23,4 +23,4 @@ export default function findOrfsInPlasmid(
     useAdditionalOrfStartCodons
   });
   return forwardOrfs.concat(reverseOrfs);
-};
+}

package/src/findSequenceMatches.js

@@ -1,8 +1,11 @@
-import {modulateRangeBySequenceLength, flipContainedRange} from "@teselagen/range-utils";
-import {reduce, uniqBy} from "lodash";
+import {
+  modulateRangeBySequenceLength,
+  flipContainedRange
+} from "@teselagen/range-utils";
+import { reduce, uniqBy } from "lodash";
 import escapeStringRegexp from "escape-string-regexp";
 import getAminoAcidStringFromSequenceString from "./getAminoAcidStringFromSequenceString";
-import {ambiguous_dna_values, extended_protein_values} from "./bioData";
+import { ambiguous_dna_values, extended_protein_values } from "./bioData";
 import getReverseComplementSequenceString from "./getReverseComplementSequenceString";
 
 export default function findSequenceMatches(
@@ -34,15 +37,11 @@ export default function findSequenceMatches(
     matches = [...matches, ...flippedReverseMatches];
   }
   return matches;
-};
+}
 
 function findSequenceMatchesTopStrand(sequence, searchString, options = {}) {
-  const {
-    isCircular,
-    isAmbiguous,
-    isProteinSequence,
-    isProteinSearch
-  } = options;
+  const { isCircular, isAmbiguous, isProteinSequence, isProteinSearch } =
+    options;
   let searchStringToUse = escapeStringRegexp(searchString);
   if (isAmbiguous) {
     if (isProteinSearch || isProteinSequence) {

package/src/generateAnnotations.js

@@ -1,4 +1,4 @@
-import {generateRandomRange} from "@teselagen/range-utils";
+import { generateRandomRange } from "@teselagen/range-utils";
 import shortid from "shortid";
 
 function generateAnnotations(

package/src/generateSequenceData.js

@@ -46,7 +46,7 @@ export default function generateSequenceData({
       sequenceLength / 3
     )
   };
-};
+}
 
 // export default tidyUpSequenceData(exampleData)
 

package/src/generateSequenceData.test.js

@@ -1,7 +1,7 @@
 import generateSequenceData from "./generateSequenceData";
 import chai from "chai";
 import chaiSubset from "chai-subset";
-import {map} from "lodash";
+import { map } from "lodash";
 
 chai.should();
 chai.use(chaiSubset);

package/src/getAllInsertionsInSeqReads.js

@@ -52,7 +52,7 @@ export default function getAllInsertionsInSeqReads(seqReads) {
   }
   // sortedInsertions is an array of objects [{bpPos: bp pos of insertion, number: # of insertions}, {bpPos, number}, ...]
   return sortedInsertions;
-};
+}
 
 // function getAllInsertionsInSeqReads(seqReads) {
 //   let allInsertionBpPosInSeqReads = [];

package/src/getAminoAcidDataForEachBaseOfDna.js

@@ -1,4 +1,4 @@
-import {translateRange, getSequenceWithinRange} from "@teselagen/range-utils";
+import { translateRange, getSequenceWithinRange } from "@teselagen/range-utils";
 import revComp from "./getReverseComplementSequenceString";
 import getAA from "./getAminoAcidFromSequenceTriplet";
 
@@ -160,4 +160,4 @@ export default function getAminoAcidDataForEachBaseOfDna(
     throw new Error("something went wrong!");
   }
   return aminoAcidDataForEachBaseOfDNA;
-};
+}

package/src/getAminoAcidDataForEachBaseOfDna.test.js

@@ -1,5 +1,3 @@
-
-
 import getAminoAcidDataForEachBaseOfDna from "./getAminoAcidDataForEachBaseOfDna.js";
 
 import getAA from "./getAminoAcidFromSequenceTriplet";

package/src/getAminoAcidFromSequenceTriplet.js

@@ -19,4 +19,4 @@ export default function getAminoAcidFromSequenceTriplet(sequenceString) {
     ] || "x";
 
   return proteinAlphabet[letter.toUpperCase()];
-};
+}

package/src/getAminoAcidStringFromSequenceString.js

@@ -15,4 +15,4 @@ export default function getAminoAcidStringFromSequenceString(sequenceString) {
   });
   aaString = aaArray.join("");
   return aaString;
-};
+}

package/src/getCodonRangeForAASliver.js

@@ -60,4 +60,4 @@ export default function getCodonRangeForAASliver(
       }
     }
   }
-};
+}

package/src/getComplementAminoAcidStringFromSequenceString.js

@@ -4,8 +4,5 @@ export default function getComplementAminoAcidStringFromSequenceString(
   sequenceString
 ) {
   const aaString = getAminoAcidStringFromSequenceString(sequenceString, true);
-  return aaString
-    .split("")
-    .reverse()
-    .join("");
-};
+  return aaString.split("").reverse().join("");
+}

package/src/getComplementSequenceAndAnnotations.js

@@ -1,7 +1,6 @@
 import getComplementSequenceString from "./getComplementSequenceString";
 import tidyUpSequenceData from "./tidyUpSequenceData";
 
-
 import getSequenceDataBetweenRange from "./getSequenceDataBetweenRange";
 
 // ac.throw([ac.string,ac.bool],arguments);
@@ -17,4 +16,4 @@ export default function getComplementSequenceAndAnnotations(
     sequence: getComplementSequenceString(seqObj.sequence, seqObj.isRna)
   });
   return tidyUpSequenceData(newSeqObj, options);
-};
+}

package/src/getComplementSequenceString.js

@@ -1,12 +1,14 @@
 import DNAComplementMap from "./DNAComplementMap";
 import { merge } from "lodash";
 
-
 // ac.throw([ac.string,ac.bool],arguments);
 export default function getComplementSequenceString(sequence, isRna) {
   // ac.throw([ac.string],arguments);
   let complementSeqString = "";
-  const complementMap = merge(DNAComplementMap, isRna ? { a: 'u', A: 'U'} : {a: 't', A: 'T'});
+  const complementMap = merge(
+    DNAComplementMap,
+    isRna ? { a: "u", A: "U" } : { a: "t", A: "T" }
+  );
   for (let i = 0; i < sequence.length; i++) {
     let complementChar = complementMap[sequence[i]];
     if (!complementChar) {
@@ -16,4 +18,4 @@ export default function getComplementSequenceString(sequence, isRna) {
     complementSeqString += complementChar;
   }
   return complementSeqString;
-};
+}

package/src/getComplementSequenceString.test.js

@@ -2,12 +2,12 @@ import getComplementSequenceString from "./getComplementSequenceString";
 
 import assert from "assert";
 
-describe('complement base should be shown correctly', () => {
-  it('complement base should be shown correctly for RNA sequence', () => {
-    assert.equal('UUA', getComplementSequenceString('AAU', true))
+describe("complement base should be shown correctly", () => {
+  it("complement base should be shown correctly for RNA sequence", () => {
+    assert.equal("UUA", getComplementSequenceString("AAU", true));
   });
 
-  it('complement base should be shown correctly for DNA sequence', () => {
-    assert.equal('TTA', getComplementSequenceString('AAT'))
+  it("complement base should be shown correctly for DNA sequence", () => {
+    assert.equal("TTA", getComplementSequenceString("AAT"));
   });
-});
+});

package/src/getCutsiteType.js

@@ -7,4 +7,4 @@ export default function getCutsiteType(restrictionEnzyme) {
   } else {
     return "3' overhang";
   }
-};
+}

package/src/getCutsitesFromSequence.js

@@ -14,4 +14,4 @@ export default function getCutsitesFromSequence(
     }
   }
   return cutsitesByName;
-};
+}

package/src/getDegenerateDnaStringFromAAString.js

@@ -5,4 +5,4 @@ export default function getDegenerateDnaStringFromAAString(aaString) {
     .split("")
     .map(char => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn")
     .join("");
-};
+}

package/src/getDegenerateRnaStringFromAAString.js

@@ -5,4 +5,4 @@ export default function getDegenerateRnaStringFromAAString(aaString) {
     .split("")
     .map(char => aminoAcidToDegenerateRnaMap[char.toLowerCase()] || "nnn")
     .join("");
-};
+}

package/src/getDigestFragmentsForCutsites.js

@@ -1,4 +1,7 @@
-import {normalizePositionByRangeLength, getRangeLength} from "@teselagen/range-utils";
+import {
+  normalizePositionByRangeLength,
+  getRangeLength
+} from "@teselagen/range-utils";
 
 export default function getDigestFragmentsForCutsites(
   sequenceLength,
@@ -102,4 +105,4 @@ export default function getDigestFragmentsForCutsites(
     return true;
   });
   return fragments;
-};
+}

package/src/getDigestFragmentsForRestrictionEnzymes.js

@@ -1,6 +1,6 @@
 import getDigestFragmentsForCutsites from "./getDigestFragmentsForCutsites";
 import cutSequenceByRestrictionEnzyme from "./cutSequenceByRestrictionEnzyme";
-import {flatMap} from "lodash";
+import { flatMap } from "lodash";
 
 export default function getDigestFragmentsForRestrictionEnzymes(
   sequence,
@@ -24,4 +24,4 @@ export default function getDigestFragmentsForRestrictionEnzymes(
     cutsites,
     opts
   );
-};
+}

package/src/getInsertBetweenVals.js

@@ -1,4 +1,4 @@
-import {normalizePositionByRangeLength1Based} from "@teselagen/range-utils";
+import { normalizePositionByRangeLength1Based } from "@teselagen/range-utils";
 
 export default function getInsertBetweenVals(
   caretPosition,
@@ -25,4 +25,4 @@ export default function getInsertBetweenVals(
   } else {
     return [sequenceLength, 1];
   }
-};
+}