@teselagen/sequence-utils 0.3.32-beta.2 → 0.3.35

package/package.json

@@ -1,14 +1,14 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.32-beta.2",
+  "version": "0.3.35",
   "type": "module",
   "dependencies": {
-    "@teselagen/range-utils": "0.3.14-beta.1",
     "escape-string-regexp": "5.0.0",
-    "jsondiffpatch": "0.4.1",
+    "jsondiffpatch": "0.7.3",
+    "string-splice": "^1.3.0",
     "lodash-es": "^4.17.21",
-    "nanoid": "^5.1.5",
-    "string-splice": "^1.3.0"
+    "shortid": "2.2.16",
+    "@teselagen/range-utils": "0.3.13"
   },
   "exports": {
     ".": {
@@ -16,9 +16,5 @@
       "require": "./index.cjs"
     }
   },
-  "volta": {
-    "node": "18.18.0",
-    "yarn": "1.22.22"
-  },
   "license": "MIT"
 }

package/proteinAlphabet.d.ts

@@ -108,6 +108,14 @@ declare const proteinAlphabet: {
         color: string;
         mass: number;
     };
+    O: {
+        value: string;
+        name: string;
+        threeLettersName: string;
+        colorByFamily: string;
+        color: string;
+        mass: number;
+    };
     M: {
         value: string;
         name: string;

package/src/computeDigestFragments.js

@@ -1,4 +1,4 @@
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 import { flatMap, cloneDeep } from "lodash-es";
 import {
   normalizePositionByRangeLength,
@@ -27,7 +27,7 @@ function computeDigestFragments({
   });
   if (!circular && cutsites.length) {
     sortedCutsites.push({
-      id: "seqTerm_" + nanoid(),
+      id: "seqTerm_" + shortid(),
       start: 0,
       end: 0,
       overhangBps: "",

package/src/cutSequenceByRestrictionEnzyme.js

@@ -1,5 +1,5 @@
 import { assign } from "lodash-es";
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 import getReverseComplementSequenceString from "./getReverseComplementSequenceString";
 
 import {
@@ -268,7 +268,7 @@ function cutSequence(
       const overhangBps = getSequenceWithinRange(cutRange, originalSequence);
 
       restrictionCutSite = {
-        id: nanoid(),
+        id: shortid(),
         start,
         end,
         topSnipPosition,

package/src/diffUtils.js

@@ -1,5 +1,5 @@
 import { cloneDeep, forEach } from "lodash-es";
-import { diff, patch, reverse } from "jsondiffpatch/dist/jsondiffpatch.umd";
+import { diff, patch, reverse } from "jsondiffpatch";
 
 import tidyUpSequenceData from "./tidyUpSequenceData";
 

package/src/filterSequenceString.js

@@ -103,7 +103,7 @@ export function getAcceptedChars({
   isMixedRnaAndDna
 } = {}) {
   return isProtein
-    ? `${extended_protein_letters.toLowerCase()}}`
+    ? `${extended_protein_letters.toLowerCase()}`
     : isOligo
       ? ambiguous_rna_letters.toLowerCase() + "t"
       : isRna

package/src/generateAnnotations.js

@@ -1,5 +1,5 @@
 import { generateRandomRange } from "@teselagen/range-utils";
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 
 function generateAnnotations(
   numberOfAnnotationsToGenerate,
@@ -21,7 +21,7 @@ function generateAnnotation(start, end, maxLength) {
     ...range,
     name: getRandomInt(0, 100000).toString(),
     type: "misc_feature",
-    id: nanoid(),
+    id: shortid(),
     forward: Math.random() > 0.5,
     notes: {}
   };

package/src/getAminoAcidDataForEachBaseOfDna.js

@@ -186,6 +186,9 @@ export default function getAminoAcidDataForEachBaseOfDna(
   optionalSubrangeRange,
   isProteinSequence
 ) {
+  if (!originalSequenceString) {
+    return [];
+  }
   // Obtain derived properties, see getTranslatedSequenceProperties
   const {
     sequenceString,
@@ -205,7 +208,7 @@ export default function getAminoAcidDataForEachBaseOfDna(
   // Iterate over the DNA sequence length in increments of 3
   for (let index = 0; index < sequenceStringLength; index += 3) {
     let aminoAcid;
-    const aminoAcidIndex = index / 3;
+    const aminoAcidIndex = Math.floor(index / 3);
     let codonPositionsInCDS;
     let basesRead;
 

package/src/getOrfsFromSequence.js

@@ -1,4 +1,4 @@
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 import getReverseComplementSequenceString from "./getReverseComplementSequenceString";
 
 /**
@@ -61,7 +61,7 @@ export default function getOrfsFromSequence(options) {
           forward: forward,
           annotationTypePlural: "orfs",
           isOrf: true,
-          id: nanoid()
+          id: shortid()
         });
       }
     }

package/src/getSequenceDataBetweenRange.test.js

@@ -225,22 +225,14 @@ describe("getSequenceDataBetweenRange", () => {
         end: 3
       }
     );
-    res.should.containSubset({
-      sequence: "gc",
-      features: [
-        {
-          start: 0,
-          end: 1,
-          locations: [
-            {
-              start: 0,
-              end: 1
-            }
-          ],
-          name: "happy"
-        }
-      ]
-    });
+    res.features.should.containSubset([
+      {
+        start: 0,
+        end: 1,
+        name: "happy"
+      }
+    ]);
+    res.sequence.should.equal("gc");
   });
   it("feature with locations, non circular enclosing range", () => {
     const res = getSequenceDataBetweenRange(
@@ -283,7 +275,7 @@ describe("getSequenceDataBetweenRange", () => {
       ]
     });
   });
-  it.only("feature with locations, non circular, non-fully enclosing range - it should trim the start/end correctly to match the location", () => {
+  it("feature with locations, non circular, non-fully enclosing range - it should trim the start/end correctly to match the location", () => {
     const res = getSequenceDataBetweenRange(
       {
         sequence: "gggatgcatgca",

package/src/insertSequenceDataAtPositionOrRange.js

@@ -27,9 +27,10 @@ export default function insertSequenceDataAtPositionOrRange(
     ...options
   });
   const newSequenceData = cloneDeep(existingSequenceData);
-  const insertLength = sequenceDataToInsert.proteinSequence
-    ? sequenceDataToInsert.proteinSequence.length * 3
-    : sequenceDataToInsert.sequence.length;
+  const insertLength =
+    sequenceDataToInsert.isProtein && sequenceDataToInsert.proteinSequence
+      ? sequenceDataToInsert.proteinSequence.length * 3
+      : sequenceDataToInsert.sequence.length;
   let caretPosition = caretPositionOrRange;
 
   const isInsertSameLengthAsSelection =
@@ -187,7 +188,7 @@ function adjustAnnotationsToDelete(annotationsToBeAdjusted, range, maxLength) {
         ...newRange,
         start: newLocations[0].start,
         end: newLocations[newLocations.length - 1].end,
-        ...(newLocations.length > 1 && { locations: newLocations })
+        ...(newLocations.length > 0 && { locations: newLocations })
       };
     } else {
       return newRange;

package/src/proteinAlphabet.js

@@ -112,6 +112,15 @@ const proteinAlphabet = {
     mass: 128.17228
   },
 
+  O: {
+    value: "O",
+    name: "Pyrrolysine",
+    threeLettersName: "Pyl",
+    colorByFamily: "#FFC0CB",
+    color: "hsl(264.7, 100%, 69%)",
+    mass: 255.313
+  },
+
   M: {
     value: "M",
     name: "Methionine",

package/src/threeLetterSequenceStringToAminoAcidMap.js

@@ -1,6 +1,6 @@
 import proteinAlphabet from "./proteinAlphabet";
 
-const threeLetterSequenceStringToAminoAcidMap = {
+const initThreeLetterSequenceStringToAminoAcidMap = {
   gct: proteinAlphabet.A,
   gcc: proteinAlphabet.A,
   gca: proteinAlphabet.A,
@@ -99,8 +99,80 @@ const threeLetterSequenceStringToAminoAcidMap = {
   taa: proteinAlphabet["*"],
   tag: proteinAlphabet["*"],
   tga: proteinAlphabet["*"],
+  uaa: proteinAlphabet["*"],
+  uag: proteinAlphabet["*"],
+  uga: proteinAlphabet["*"],
   "...": proteinAlphabet["."],
   "---": proteinAlphabet["-"]
 };
 
+// IUPAC nucleotide codes (DNA/RNA) with U awareness
+const IUPAC = {
+  A: ["A"],
+  C: ["C"],
+  G: ["G"],
+  T: ["T"],
+  U: ["U"],
+
+  R: ["A", "G"],
+  Y: ["C", "T", "U"],
+  K: ["G", "T", "U"],
+  M: ["A", "C"],
+  S: ["G", "C"],
+  W: ["A", "T", "U"],
+  B: ["C", "G", "T", "U"],
+  D: ["A", "G", "T", "U"],
+  H: ["A", "C", "T", "U"],
+  V: ["A", "C", "G"],
+  N: ["A", "C", "G", "T", "U"],
+  X: ["A", "C", "G", "T", "U"]
+};
+
+
+function expandAndResolve(threeLetterCodon) {
+  const chars = threeLetterCodon.toUpperCase().split("");
+  const picks = chars.map((c) => IUPAC[c] || [c]);
+
+  let allPossibleThreeLetterCodons = [""];
+  for (const set of picks) {
+    const next = [];
+    for (const prefix of allPossibleThreeLetterCodons) for (const b of set) next.push(prefix + b);
+    allPossibleThreeLetterCodons = next;
+  }
+  let foundAminoAcid = null;
+  for (const codon of allPossibleThreeLetterCodons) {
+    const lowerCodon = codon.toLowerCase();
+    const aminoAcidObj = initThreeLetterSequenceStringToAminoAcidMap[lowerCodon] ?? initThreeLetterSequenceStringToAminoAcidMap[lowerCodon.replace(/u/g, "t")] ?? initThreeLetterSequenceStringToAminoAcidMap[lowerCodon.replace(/t/g, "u")];
+    if (aminoAcidObj) {
+      if (!foundAminoAcid) {
+        foundAminoAcid = aminoAcidObj;
+      } else if (foundAminoAcid.value !== aminoAcidObj.value ) {
+        return null
+      }
+    } else {
+      return null;
+    }
+  }
+  return foundAminoAcid;
+}
+
+function getCodonToAminoAcidMap() {
+  const map = initThreeLetterSequenceStringToAminoAcidMap;
+  // generate all IUPAC 3-mers
+  const codes = Object.keys(IUPAC);
+  for (const a of codes)
+    for (const b of codes)
+      for (const c of codes) {
+        const codon = a + b + c;
+        const lowerCodon = codon.toLowerCase();
+        if (map[lowerCodon]) continue;
+        const aminoAcidObj = expandAndResolve(codon);
+        if (aminoAcidObj) map[lowerCodon] = aminoAcidObj;
+      }
+
+  return map;
+}
+
+const threeLetterSequenceStringToAminoAcidMap = getCodonToAminoAcidMap();
+
 export default threeLetterSequenceStringToAminoAcidMap;

package/src/tidyUpAnnotation.js

@@ -1,6 +1,6 @@
 import { cloneDeep, get, some } from "lodash-es";
 import { getFeatureToColorMap, getFeatureTypes } from "./featureTypesAndColors";
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 
 export default function tidyUpAnnotation(
   _annotation,
@@ -34,10 +34,10 @@ export default function tidyUpAnnotation(
     annotation.name = "Untitled annotation";
   }
   if (provideNewIdsForAnnotations) {
-    annotation.id = nanoid();
+    annotation.id = shortid();
   }
   if (!annotation.id && annotation.id !== 0 && !doNotProvideIdsForAnnotations) {
-    annotation.id = nanoid();
+    annotation.id = shortid();
     messages.push(
       "Unable to detect valid ID for annotation, setting ID to " + annotation.id
     );

package/src/tidyUpSequenceData.js

@@ -1,5 +1,5 @@
 // tnrtodo: figure out where to insert this validation exactly..
-import { nanoid } from "nanoid";
+import shortid from "shortid";
 
 import getAminoAcidDataForEachBaseOfDna from "./getAminoAcidDataForEachBaseOfDna";
 import { cloneDeep, flatMap } from "lodash-es";
@@ -155,7 +155,7 @@ export default function tidyUpSequenceData(pSeqData, options = {}) {
         if (item.id || item.id === 0) {
           itemId = item.id;
         } else {
-          itemId = nanoid();
+          itemId = shortid();
           if (!doNotProvideIdsForAnnotations) {
             item.id = itemId; //assign the newly created id to the item
           }

package/threeLetterSequenceStringToAminoAcidMap.d.ts

@@ -879,6 +879,30 @@ declare const threeLetterSequenceStringToAminoAcidMap: {
         color: string;
         mass: number;
     };
+    uaa: {
+        value: string;
+        name: string;
+        threeLettersName: string;
+        colorByFamily: string;
+        color: string;
+        mass: number;
+    };
+    uag: {
+        value: string;
+        name: string;
+        threeLettersName: string;
+        colorByFamily: string;
+        color: string;
+        mass: number;
+    };
+    uga: {
+        value: string;
+        name: string;
+        threeLettersName: string;
+        colorByFamily: string;
+        color: string;
+        mass: number;
+    };
     "...": {
         value: string;
         name: string;