@teselagen/sequence-utils 0.3.38-beta.2 → 0.3.41

package/src/getAminoAcidDataForEachBaseOfDna.ts

@@ -1,305 +0,0 @@
-import {
-  translateRange,
-  getSequenceWithinRange,
-  flipContainedRange,
-  isPositionWithinRange,
-  Range
-} from "@teselagen/range-utils";
-import revComp from "./getReverseComplementSequenceString";
-import getAA from "./getAminoAcidFromSequenceTriplet";
-
-//
-import proteinAlphabet from "./proteinAlphabet";
-
-/**
- * @private
- * Gets the next triplet of bases in the sequenceString
- * @param  {Number} index The index of the sequenceString to start at
- * @param  {String} sequenceString The dna sequenceString.
- * @param  {Object[]} exonRange Array of ranges of the sequenceString that contains the positions of bases corresponding to exons.
- * @return {Object} The triplet of bases, the number of bases read, and the positions of the codon bases in the sequenceString
- * @property {String} triplet The triplet of bases
- * @property {Number} basesRead The number of bases read
- * @property {Number[]} codonPositions The positions of the codon bases in the sequenceString
- */
-function getNextTriplet(
-  index: number,
-  sequenceString: string,
-  exonRange: Range[]
-) {
-  let triplet = "";
-  let internalIndex;
-  // Positions of codons relative to the coding sequence start
-  // including introns.
-  const codonPositions = [];
-
-  // A function to check if a base is within an exon
-  const isBaseInExon = (baseIndex: number) =>
-    exonRange.some(r =>
-      isPositionWithinRange(baseIndex, r, sequenceString.length, true, false)
-    );
-
-  for (
-    internalIndex = index;
-    internalIndex < sequenceString.length;
-    internalIndex++
-  ) {
-    // We have read three bases into the triplet (this has to be at the top of the loop)
-    if (triplet.length === 3) {
-      break;
-    }
-    // TODO: ask about ranges
-    // The base corresponds to an intron
-    if (isBaseInExon(internalIndex)) {
-      // We read a base from the sequenceString
-      triplet += sequenceString[internalIndex];
-      codonPositions.push(internalIndex);
-    }
-  }
-
-  return { triplet, basesRead: internalIndex - index, codonPositions };
-}
-
-/**
-  * @private
-  * Returns a series of derived properties from the arguments to getAminoAcidDataForEachBaseOfDna
-  * @param  {String} originalSequenceString The dna sequenceString.
-  * @param  {boolean} forward Whether the translation is in the forward direction.
-  * @param  {Object} optionalSubrangeRange The range of the sequenceString to translate.
-  * @param  {boolean} isProteinSequence Whether the sequenceString is a protein sequence.
-  * @return {Object} The derived properties
-  * @property {String} sequenceString
-  * - If !isProtein: The subsequence within originalSequenceString that will be translated, defined by transaltionRange. If
-  *   !forward, this will be the reverse complement of the subsequence.
-  * - If isProtein: The originalSequenceString.
-  * @property {Object} translationRange The range of the originalSequenceString that we're translating (if !isProtein), or getting DNA-level
-    info for (if isProtein).
-  * @property {Number} originalSequenceStringLength The length of the full DNA sequence. If !isProtein it's the length of originalSequenceString
-  * @property {Number} sequenceStringLength The length of the DNA sequence that would give the translation.
-  * @property {Object[]} exonRange Array of ranges of the sequenceString that contains the positions of bases corresponding to exons.
-*/
-function getTranslatedSequenceProperties(
-  originalSequenceString: string,
-  forward: boolean,
-  optionalSubrangeRange: Range | null,
-  isProteinSequence: boolean
-) {
-  const originalSequenceStringLength = isProteinSequence
-    ? originalSequenceString.length * 3
-    : originalSequenceString.length;
-
-  let sequenceString = originalSequenceString;
-  const translationRange = { start: 0, end: originalSequenceStringLength - 1 };
-
-  if (optionalSubrangeRange) {
-    sequenceString = getSequenceWithinRange(
-      optionalSubrangeRange,
-      originalSequenceString
-    ) as string;
-    translationRange.start = optionalSubrangeRange.start;
-    translationRange.end = optionalSubrangeRange.end;
-  }
-
-  const sequenceStringLength = isProteinSequence
-    ? sequenceString.length * 3
-    : sequenceString.length;
-
-  if (!isProteinSequence && !forward) {
-    sequenceString = revComp(sequenceString);
-  }
-
-  // TODO: what to do with protein if this is true?
-  const absoluteExonRange =
-    !isProteinSequence &&
-      optionalSubrangeRange &&
-      optionalSubrangeRange.locations
-      ? optionalSubrangeRange.locations
-      : [translationRange];
-  const exonRange = absoluteExonRange.map(range => {
-    let outputRange = translateRange(
-      range,
-      -translationRange.start,
-      originalSequenceStringLength
-    );
-    if (!forward) {
-      outputRange = flipContainedRange(
-        outputRange,
-        { start: 0, end: sequenceStringLength - 1 },
-        sequenceStringLength
-      );
-    }
-    return outputRange;
-  });
-
-  return {
-    sequenceString,
-    translationRange,
-    sequenceStringLength,
-    originalSequenceStringLength,
-    exonRange
-  };
-}
-
-/**
- * Function to convert the position within the CDS (where A in ATG is 0, and T in ATG is 1)
- * to the position in the main sequence
- *
- * @param  {Number} index The index of the sequenceString to start at
- * @param  {boolean} forward Whether the translation is in the forward direction.
- * @param  {Object} translationRange The range of the originalSequenceString that we're translating (if !isProtein), or getting DNA-level
- * info for (if isProtein).
- * @param  {Number} mainSequenceLength The length of the full DNA sequence. If !isProtein it's the length of originalSequenceString
- * @return {Number} The position in the main sequence
- *
- */
-function positionInCdsToPositionInMainSequence(
-  index: number,
-  forward: boolean,
-  translationRange: Range,
-  mainSequenceLength: number
-) {
-  let outputRange = translateRange(
-    { start: index, end: index },
-    translationRange.start,
-    mainSequenceLength
-  );
-  if (!forward) {
-    outputRange = flipContainedRange(
-      outputRange,
-      translationRange,
-      mainSequenceLength
-    );
-  }
-  return outputRange.start;
-}
-
-/**
- * @private
- * Gets aminoAcid data, including position in string and position in codon
- * from the sequenceString and the direction of the translation
- * @param  {String} sequenceString The dna sequenceString.
- * @param  {boolean} forward Should we find forward facing orfs or reverse facing orfs
- * @param  {boolean} isProteinSequence We're passing in a sequence of AA chars instead of DNA chars (slightly confusing but we'll still use the dna indexing for rendering in OVE)
- * @return [{
-        aminoAcid:
-        positionInCodon:
-      }]
- */
-export default function getAminoAcidDataForEachBaseOfDna(
-  originalSequenceString: string,
-  forward: boolean,
-  optionalSubrangeRange: Range | null,
-  isProteinSequence: boolean
-) {
-  if (!originalSequenceString) {
-    return [];
-  }
-  // Obtain derived properties, see getTranslatedSequenceProperties
-  const {
-    sequenceString,
-    translationRange,
-    sequenceStringLength,
-    originalSequenceStringLength,
-    exonRange
-  } = getTranslatedSequenceProperties(
-    originalSequenceString,
-    forward,
-    optionalSubrangeRange,
-    isProteinSequence
-  );
-
-  const aminoAcidDataForEachBaseOfDNA = [];
-
-  // Iterate over the DNA sequence length in increments of 3
-  for (let index = 0; index < sequenceStringLength; index += 3) {
-    let aminoAcid;
-    const aminoAcidIndex = Math.floor(index / 3);
-    let codonPositionsInCDS;
-    let basesRead;
-
-    if (isProteinSequence) {
-      codonPositionsInCDS = [0, 1, 2].map(i => index + i);
-      basesRead = 3;
-      // eslint-disable-next-line @typescript-eslint/no-explicit-any
-      aminoAcid = (proteinAlphabet as any)[sequenceString[index / 3].toUpperCase()];
-    } else {
-      // Get the triplet of DNA bases
-      const {
-        triplet,
-        basesRead: _basesRead,
-        codonPositions
-      } = getNextTriplet(index, sequenceString, exonRange);
-      basesRead = _basesRead;
-      codonPositionsInCDS = codonPositions;
-      // If the triplet is not full, we need to add the gap xxx amino acid, start
-      aminoAcid = triplet.length === 3 ? getAA(triplet) : getAA("xxx");
-    }
-
-    const absoluteCodonPositions = codonPositionsInCDS.map(i =>
-      positionInCdsToPositionInMainSequence(
-        i,
-        forward,
-        translationRange,
-        originalSequenceStringLength
-      )
-    );
-
-    // What should the codon range be if it comprises intron bases?
-    const codonRange = forward
-      ? {
-        start: absoluteCodonPositions[0],
-        end: absoluteCodonPositions[codonPositionsInCDS.length - 1]
-      }
-      : {
-        start: absoluteCodonPositions[codonPositionsInCDS.length - 1],
-        end: absoluteCodonPositions[0]
-      };
-
-    // Iterate over the positions read
-    let positionInCodon = 0;
-    for (let i = 0; i < basesRead; i++) {
-      const posInCds = i + index;
-      const sequenceIndex = codonPositionsInCDS.includes(posInCds)
-        ? absoluteCodonPositions[codonPositionsInCDS.indexOf(posInCds)]
-        : positionInCdsToPositionInMainSequence(
-          posInCds,
-          forward,
-          translationRange,
-          originalSequenceStringLength
-        );
-      if (codonPositionsInCDS.includes(posInCds)) {
-        aminoAcidDataForEachBaseOfDNA.push({
-          aminoAcid,
-          positionInCodon,
-          aminoAcidIndex,
-          sequenceIndex,
-          codonRange,
-          fullCodon: codonPositionsInCDS.length === 3
-        });
-        positionInCodon++;
-      } else {
-        // push a null object for intron bases
-        aminoAcidDataForEachBaseOfDNA.push({
-          aminoAcid: null,
-          positionInCodon: null,
-          aminoAcidIndex: null,
-          sequenceIndex,
-          codonRange: null,
-          fullCodon: null
-        });
-      }
-    }
-    // Move the index in case intron bases were read
-    index += basesRead - codonPositionsInCDS.length;
-  }
-
-  if (sequenceStringLength !== aminoAcidDataForEachBaseOfDNA.length) {
-    throw new Error("something went wrong!");
-  }
-
-  // Reverse the array if we're translating in the reverse direction
-  if (!forward) {
-    aminoAcidDataForEachBaseOfDNA.reverse();
-  }
-  return aminoAcidDataForEachBaseOfDNA;
-}

package/src/getAminoAcidFromSequenceTriplet.ts

@@ -1,27 +0,0 @@
-import threeLetterSequenceStringToAminoAcidMap from "./threeLetterSequenceStringToAminoAcidMap";
-import proteinAlphabet from "./proteinAlphabet";
-import degenerateDnaToAminoAcidMap from "./degenerateDnaToAminoAcidMap";
-
-//tnrtodo: expand the threeLetterSequenceStringToAminoAcidMap mappings to include RNA characters.
-//currently stop bps aren't all mapped!
-export default function getAminoAcidFromSequenceTriplet(
-  sequenceString: string
-) {
-  sequenceString = sequenceString.toLowerCase();
-  if (sequenceString.length !== 3) {
-    throw new Error("must pass a string of length 3");
-  }
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  const aa = (threeLetterSequenceStringToAminoAcidMap as any)[sequenceString];
-  if (aa) {
-    return aa;
-  }
-  const letter =
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    (degenerateDnaToAminoAcidMap as any)[
-      sequenceString.replace("x", "n") //replace x's with n's as those are equivalent dna chars
-    ] || "x";
-
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  return (proteinAlphabet as any)[letter.toUpperCase()];
-}

package/src/getAminoAcidStringFromSequenceString.ts

@@ -1,36 +0,0 @@
-import getAminoAcidDataForEachBaseOfDna from "./getAminoAcidDataForEachBaseOfDna";
-import { AminoAcidData } from "./types";
-
-export default function getAminoAcidStringFromSequenceString(
-  sequenceString: string,
-  options: { doNotExcludeAsterisk?: boolean } = {}
-): string {
-  const { doNotExcludeAsterisk } = options;
-  const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
-    sequenceString,
-    true,
-    null,
-    false
-  );
-  const aaArray: string[] = [];
-  let aaString = "";
-  aminoAcidsPerBase.forEach((aa: AminoAcidData, index: number) => {
-    if (!aa.fullCodon) {
-      return;
-    }
-    // Check if the current amino acid is the last in the sequence and is a stop codon
-    if (
-      !doNotExcludeAsterisk &&
-      index >= aminoAcidsPerBase.length - 3 &&
-      aa.aminoAcid?.value === "*"
-    ) {
-      return;
-    }
-    if (aa.aminoAcidIndex === null || !aa.aminoAcid) {
-      return;
-    }
-    aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
-  });
-  aaString = aaArray.join("");
-  return aaString;
-}

package/src/getCodonRangeForAASliver.ts

@@ -1,73 +0,0 @@
-import { AminoAcidData } from "./types";
-import { Range } from "@teselagen/range-utils";
-
-export default function getCodonRangeForAASliver(
-  aminoAcidPositionInSequence: number,
-  aminoAcidSliver: AminoAcidData,
-  AARepresentationOfTranslation: AminoAcidData[],
-  relativeAAPositionInTranslation: number
-): Range {
-  const AASliverOneBefore =
-    AARepresentationOfTranslation[relativeAAPositionInTranslation - 1];
-  if (
-    AASliverOneBefore &&
-    AASliverOneBefore.aminoAcidIndex === aminoAcidSliver.aminoAcidIndex
-  ) {
-    const AASliverTwoBefore =
-      AARepresentationOfTranslation[relativeAAPositionInTranslation - 2];
-    if (
-      AASliverTwoBefore &&
-      AASliverTwoBefore.aminoAcidIndex === aminoAcidSliver.aminoAcidIndex
-    ) {
-      return {
-        start: aminoAcidPositionInSequence - 2,
-        end: aminoAcidPositionInSequence
-      };
-    } else {
-      if (aminoAcidSliver.fullCodon === true) {
-        return {
-          start: aminoAcidPositionInSequence - 1,
-          end: aminoAcidPositionInSequence + 1
-        };
-      } else {
-        return {
-          start: aminoAcidPositionInSequence - 1,
-          end: aminoAcidPositionInSequence
-        };
-      }
-    }
-  } else {
-    //no AASliver before with same index
-    if (aminoAcidSliver.fullCodon === true) {
-      //sliver is part of a full codon, so we know the codon will expand 2 more slivers ahead
-      return {
-        start: aminoAcidPositionInSequence,
-        end: aminoAcidPositionInSequence + 2
-      };
-    } else {
-      const AASliverOneAhead =
-        AARepresentationOfTranslation[relativeAAPositionInTranslation - 2]; // Original logic logic seems to check "ahead" but uses -2 index??
-      // Wait, AASliverOneAhead should likely access +1 or +2?
-      // Line 46 in original: AARepresentationOfTranslation[relativeAAPositionInTranslation - 2]
-      // This is weird for "OneAhead".
-      // But I shouldn't change logic unless I'm sure it's a bug fix.
-      // Assuming original code logic is intentional or I should preserve it.
-      // I will preserve the index access but add types.
-
-      if (
-        AASliverOneAhead &&
-        AASliverOneAhead.aminoAcidIndex === aminoAcidSliver.aminoAcidIndex
-      ) {
-        return {
-          start: aminoAcidPositionInSequence,
-          end: aminoAcidPositionInSequence + 1
-        };
-      } else {
-        return {
-          start: aminoAcidPositionInSequence,
-          end: aminoAcidPositionInSequence + 1
-        };
-      }
-    }
-  }
-}

package/src/getComplementAminoAcidStringFromSequenceString.ts

@@ -1,10 +0,0 @@
-import getAminoAcidStringFromSequenceString from "./getAminoAcidStringFromSequenceString";
-
-export default function getComplementAminoAcidStringFromSequenceString(
-  sequenceString: string
-): string {
-  const aaString = getAminoAcidStringFromSequenceString(sequenceString, {
-    doNotExcludeAsterisk: true
-  });
-  return aaString.split("").reverse().join("");
-}

package/src/getComplementSequenceAndAnnotations.ts

@@ -1,25 +0,0 @@
-import getComplementSequenceString from "./getComplementSequenceString";
-import tidyUpSequenceData from "./tidyUpSequenceData";
-
-import getSequenceDataBetweenRange from "./getSequenceDataBetweenRange";
-import { SequenceData, Range } from "./types";
-
-// ac.throw([ac.string,ac.bool],arguments);
-export default function getComplementSequenceAndAnnotations(
-  pSeqObj: SequenceData,
-  options: { range?: Range; [key: string]: unknown } = {}
-): SequenceData {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
-  const seqObj = tidyUpSequenceData(
-    getSequenceDataBetweenRange(pSeqObj, options.range || null),
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    options as any
-  );
-  const newSeqObj = Object.assign({}, seqObj, {
-    sequence: getComplementSequenceString(seqObj.sequence, seqObj.isRna)
-  });
-  return tidyUpSequenceData(newSeqObj, {
-    doNotRemoveInvalidChars: true,
-    ...options
-  });
-}

package/src/getComplementSequenceString.ts

@@ -1,23 +0,0 @@
-import DNAComplementMap from "./DNAComplementMap";
-import { merge } from "lodash-es";
-
-export default function getComplementSequenceString(
-  sequence: string,
-  isRna?: boolean
-): string {
-  if (typeof sequence !== "string") return "";
-  let complementSeqString = "";
-  const complementMap: Record<string, string> = 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) {
-      complementChar = sequence[i];
-      // throw new Error('trying to get the reverse compelement of an invalid base');
-    }
-    complementSeqString += complementChar;
-  }
-  return complementSeqString;
-}

package/src/getCutsiteType.ts

@@ -1,18 +0,0 @@
-import { RestrictionEnzyme } from "./types";
-
-export default function getCutsiteType(
-  restrictionEnzyme: RestrictionEnzyme
-): string {
-  const { topSnipOffset, bottomSnipOffset } = restrictionEnzyme;
-  if (topSnipOffset === bottomSnipOffset) {
-    return "blunt";
-  } else if (
-    topSnipOffset !== undefined &&
-    bottomSnipOffset !== undefined &&
-    topSnipOffset < bottomSnipOffset
-  ) {
-    return "5' overhang";
-  } else {
-    return "3' overhang";
-  }
-}

package/src/getCutsitesFromSequence.ts

@@ -1,22 +0,0 @@
-import { flatMap } from "lodash-es";
-import cutSequenceByRestrictionEnzyme from "./cutSequenceByRestrictionEnzyme";
-import { CutSite, RestrictionEnzyme } from "./types";
-
-export default function getCutsitesFromSequence(
-  sequence: string,
-  circular: boolean,
-  contextEnzymes: RestrictionEnzyme[]
-): Record<string, CutSite[]> {
-  const cutsites = flatMap(contextEnzymes, enzyme => {
-    return cutSequenceByRestrictionEnzyme(sequence, circular, enzyme);
-  });
-  const cutsitesByNameMap: Record<string, CutSite[]> = {};
-  cutsites.forEach(cutsite => {
-    const name = cutsite.name || "";
-    if (!cutsitesByNameMap[name]) {
-      cutsitesByNameMap[name] = [];
-    }
-    cutsitesByNameMap[name].push(cutsite);
-  });
-  return cutsitesByNameMap;
-}

package/src/getDegenerateDnaStringFromAAString.ts

@@ -1,15 +0,0 @@
-import aminoAcidToDegenerateDnaMap from "./aminoAcidToDegenerateDnaMap";
-
-export default function getDegenerateDnaStringFromAAString(
-  aaString: string
-): string {
-  return aaString
-    .split("")
-    .map(
-      char =>
-        (aminoAcidToDegenerateDnaMap as Record<string, string>)[
-          char.toLowerCase()
-        ] || "nnn"
-    )
-    .join("");
-}

package/src/getDegenerateRnaStringFromAAString.ts

@@ -1,15 +0,0 @@
-import aminoAcidToDegenerateRnaMap from "./aminoAcidToDegenerateRnaMap";
-
-export default function getDegenerateRnaStringFromAAString(
-  aaString: string
-): string {
-  return aaString
-    .split("")
-    .map(
-      char =>
-        (aminoAcidToDegenerateRnaMap as Record<string, string>)[
-          char.toLowerCase()
-        ] || "nnn"
-    )
-    .join("");
-}