@teselagen/sequence-utils 0.3.8 → 0.3.10

package/bioData.d.ts

@@ -1,5 +1,6 @@
 export const protein_letters: "ACDEFGHIKLMNPQRSTVWY";
-export const extended_protein_letters: "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+export const protein_letters_withUandX: "ACDEFGHIKLMNPQRSTVWYUX";
+export const extended_protein_letters: "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 export const ambiguous_dna_letters: "GATCRYWSMKHBVDN";
 export const unambiguous_dna_letters: "GATC";
 export const ambiguous_rna_letters: "GAUCRYWSMKHBVDN";

package/filterSequenceString.d.ts

@@ -1 +1,24 @@
-export default function filterSequenceString(sequenceString: any, additionalValidChars: string | undefined, charOverrides: any): any;
+export default function filterSequenceString(sequenceString: any, { additionalValidChars, isOligo, name, isProtein, isRna, isMixedRnaAndDna, }?: {
+    additionalValidChars?: string | undefined;
+    isOligo: any;
+    name: any;
+    isProtein: any;
+    isRna: any;
+    isMixedRnaAndDna: any;
+}): (string | string[])[];
+export function getAcceptedChars({ isOligo, isProtein, isRna, isMixedRnaAndDna, }?: {
+    isOligo: any;
+    isProtein: any;
+    isRna: any;
+    isMixedRnaAndDna: any;
+}): string;
+export function getReplaceChars({ isOligo, isProtein, isRna, isMixedRnaAndDna }?: {
+    isOligo: any;
+    isProtein: any;
+    isRna: any;
+    isMixedRnaAndDna: any;
+}): {
+    t?: undefined;
+} | {
+    t: string;
+};

package/index.d.ts

@@ -20,7 +20,6 @@ export { default as aliasedEnzymesByName } from "./aliasedEnzymesByName";
 export { default as defaultEnzymesByName } from "./defaultEnzymesByName";
 export { default as generateSequenceData } from "./generateSequenceData";
 export { default as generateAnnotations } from "./generateAnnotations";
-export { default as filterAminoAcidSequenceString } from "./filterAminoAcidSequenceString";
 export { default as filterSequenceString } from "./filterSequenceString";
 export { default as findNearestRangeOfSequenceOverlapToPosition } from "./findNearestRangeOfSequenceOverlapToPosition";
 export { default as findOrfsInPlasmid } from "./findOrfsInPlasmid";

package/index.js

@@ -5999,7 +5999,8 @@ lodash.exports;
 })(lodash, lodash.exports);
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -6067,6 +6068,7 @@ const bioData = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.definePrope
   extended_protein_letters,
   extended_protein_values,
   protein_letters,
+  protein_letters_withUandX,
   unambiguous_dna_letters,
   unambiguous_rna_letters
 }, Symbol.toStringTag, { value: "Module" }));
@@ -12321,20 +12323,88 @@ const modifiableTypes = [
   "primers",
   "guides"
 ];
-function filterSequenceString(sequenceString, additionalValidChars = "", charOverrides) {
-  if (sequenceString) {
-    return sequenceString.replace(
-      new RegExp(
-        `[^${charOverrides || `atgcyrswkmbvdhnu${additionalValidChars.split("").join("\\")}`}]`,
-        "gi"
-      ),
-      ""
+function filterSequenceString(sequenceString, {
+  additionalValidChars = "",
+  isOligo,
+  name,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  const acceptedChars = getAcceptedChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  });
+  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);
+    }
+  });
+  Object.keys(replaceCount).forEach((letter) => {
+    warnings.push(
+      `Replaced "${letter}" with "${replaceChars[letter]}"${replaceCount[letter] > 1 ? ` ${replaceCount[letter]} times` : ""}`
     );
-  } else {
-    return sequenceString;
+  });
+  if (sequenceString.length !== sanitizedVal.length) {
+    warnings.push(
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+    );
+  }
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach((warning) => {
+      window.toastr.warning(warning);
+    });
   }
+  return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
+function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  return isProtein ? `${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()
+  );
+}
+__name(getAcceptedChars, "getAcceptedChars");
+function getReplaceChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+    //just plain old dna
+    {}
+  );
+}
+__name(getReplaceChars, "getReplaceChars");
 function tidyUpAnnotation(_annotation, {
   sequenceData = {},
   convertAnnotationsFromAAIndices,
@@ -12463,14 +12533,6 @@ function coerceLocation({
   }
 }
 __name(coerceLocation, "coerceLocation");
-function filterAminoAcidSequenceString(sequenceString, options) {
-  options = options || {};
-  if (options.includeStopCodon) {
-    return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu.*]/gi, "");
-  }
-  return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu]/gi, "");
-}
-__name(filterAminoAcidSequenceString, "filterAminoAcidSequenceString");
 function getDegenerateDnaStringFromAAString(aaString) {
   return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
 }
@@ -12479,14 +12541,13 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
-    charOverrides,
     doNotProvideIdsForAnnotations,
-    proteinFilterOptions,
     noCdsTranslations,
-    convertAnnotationsFromAAIndices
+    convertAnnotationsFromAAIndices,
+    topLevelSeqData
   } = options;
   let seqData = lodashExports.cloneDeep(pSeqData);
   const response = {
@@ -12514,18 +12575,15 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   if (seqData.isRna) {
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      seqData.proteinSequence = filterAminoAcidSequenceString(
-        seqData.proteinSequence,
-        __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-      );
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+      seqData.proteinSequence = newSeq;
     } else {
-      seqData.sequence = filterSequenceString(
-        seqData.sequence,
-        `${additionalValidChars || ""}${seqData.isRna || seqData.isMixedRnaAndDna ? "u" : ""}`,
-        charOverrides
-      );
+      const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
+        additionalValidChars
+      }, topLevelSeqData || seqData));
+      seqData.sequence = newSeq;
     }
   }
   if (seqData.isProtein) {
@@ -22665,7 +22723,6 @@ exports.degenerateRnaToAminoAcidMap = degenerateRnaToAminoAcidMap;
 exports.deleteSequenceDataAtRange = deleteSequenceDataAtRange;
 exports.doesEnzymeChopOutsideOfRecognitionSite = doesEnzymeChopOutsideOfRecognitionSite;
 exports.featureColors = featureColors;
-exports.filterAminoAcidSequenceString = filterAminoAcidSequenceString;
 exports.filterSequenceString = filterSequenceString;
 exports.findNearestRangeOfSequenceOverlapToPosition = findNearestRangeOfSequenceOverlapToPosition;
 exports.findOrfsInPlasmid = findOrfsInPlasmid;

package/index.mjs

@@ -5997,7 +5997,8 @@ lodash.exports;
 })(lodash, lodash.exports);
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -6065,6 +6066,7 @@ const bioData = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.definePrope
   extended_protein_letters,
   extended_protein_values,
   protein_letters,
+  protein_letters_withUandX,
   unambiguous_dna_letters,
   unambiguous_rna_letters
 }, Symbol.toStringTag, { value: "Module" }));
@@ -12319,20 +12321,88 @@ const modifiableTypes = [
   "primers",
   "guides"
 ];
-function filterSequenceString(sequenceString, additionalValidChars = "", charOverrides) {
-  if (sequenceString) {
-    return sequenceString.replace(
-      new RegExp(
-        `[^${charOverrides || `atgcyrswkmbvdhnu${additionalValidChars.split("").join("\\")}`}]`,
-        "gi"
-      ),
-      ""
+function filterSequenceString(sequenceString, {
+  additionalValidChars = "",
+  isOligo,
+  name,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  const acceptedChars = getAcceptedChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  });
+  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);
+    }
+  });
+  Object.keys(replaceCount).forEach((letter) => {
+    warnings.push(
+      `Replaced "${letter}" with "${replaceChars[letter]}"${replaceCount[letter] > 1 ? ` ${replaceCount[letter]} times` : ""}`
     );
-  } else {
-    return sequenceString;
+  });
+  if (sequenceString.length !== sanitizedVal.length) {
+    warnings.push(
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+    );
+  }
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach((warning) => {
+      window.toastr.warning(warning);
+    });
   }
+  return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
+function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  return isProtein ? `${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()
+  );
+}
+__name(getAcceptedChars, "getAcceptedChars");
+function getReplaceChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna
+} = {}) {
+  return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+    //just plain old dna
+    {}
+  );
+}
+__name(getReplaceChars, "getReplaceChars");
 function tidyUpAnnotation(_annotation, {
   sequenceData = {},
   convertAnnotationsFromAAIndices,
@@ -12461,14 +12531,6 @@ function coerceLocation({
   }
 }
 __name(coerceLocation, "coerceLocation");
-function filterAminoAcidSequenceString(sequenceString, options) {
-  options = options || {};
-  if (options.includeStopCodon) {
-    return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu.*]/gi, "");
-  }
-  return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu]/gi, "");
-}
-__name(filterAminoAcidSequenceString, "filterAminoAcidSequenceString");
 function getDegenerateDnaStringFromAAString(aaString) {
   return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
 }
@@ -12477,14 +12539,13 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
-    charOverrides,
     doNotProvideIdsForAnnotations,
-    proteinFilterOptions,
     noCdsTranslations,
-    convertAnnotationsFromAAIndices
+    convertAnnotationsFromAAIndices,
+    topLevelSeqData
   } = options;
   let seqData = lodashExports.cloneDeep(pSeqData);
   const response = {
@@ -12512,18 +12573,15 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   if (seqData.isRna) {
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      seqData.proteinSequence = filterAminoAcidSequenceString(
-        seqData.proteinSequence,
-        __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-      );
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+      seqData.proteinSequence = newSeq;
     } else {
-      seqData.sequence = filterSequenceString(
-        seqData.sequence,
-        `${additionalValidChars || ""}${seqData.isRna || seqData.isMixedRnaAndDna ? "u" : ""}`,
-        charOverrides
-      );
+      const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
+        additionalValidChars
+      }, topLevelSeqData || seqData));
+      seqData.sequence = newSeq;
     }
   }
   if (seqData.isProtein) {
@@ -22664,7 +22722,6 @@ export {
   deleteSequenceDataAtRange,
   doesEnzymeChopOutsideOfRecognitionSite,
   featureColors,
-  filterAminoAcidSequenceString,
   filterSequenceString,
   findNearestRangeOfSequenceOverlapToPosition,
   findOrfsInPlasmid,

package/index.umd.js

@@ -6001,7 +6001,8 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   })(lodash, lodash.exports);
   var lodashExports = lodash.exports;
   const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
-  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+  const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
+  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
   const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
   const unambiguous_dna_letters = "GATC";
   const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -6069,6 +6070,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     extended_protein_letters,
     extended_protein_values,
     protein_letters,
+    protein_letters_withUandX,
     unambiguous_dna_letters,
     unambiguous_rna_letters
   }, Symbol.toStringTag, { value: "Module" }));
@@ -12323,20 +12325,88 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     "primers",
     "guides"
   ];
-  function filterSequenceString(sequenceString, additionalValidChars = "", charOverrides) {
-    if (sequenceString) {
-      return sequenceString.replace(
-        new RegExp(
-          `[^${charOverrides || `atgcyrswkmbvdhnu${additionalValidChars.split("").join("\\")}`}]`,
-          "gi"
-        ),
-        ""
+  function filterSequenceString(sequenceString, {
+    additionalValidChars = "",
+    isOligo,
+    name,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  } = {}) {
+    const acceptedChars = getAcceptedChars({
+      isOligo,
+      isProtein,
+      isRna,
+      isMixedRnaAndDna
+    });
+    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);
+      }
+    });
+    Object.keys(replaceCount).forEach((letter) => {
+      warnings.push(
+        `Replaced "${letter}" with "${replaceChars[letter]}"${replaceCount[letter] > 1 ? ` ${replaceCount[letter]} times` : ""}`
       );
-    } else {
-      return sequenceString;
+    });
+    if (sequenceString.length !== sanitizedVal.length) {
+      warnings.push(
+        `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
+      );
+    }
+    if (typeof window !== "undefined" && window.toastr && warnings.length) {
+      warnings.forEach((warning) => {
+        window.toastr.warning(warning);
+      });
     }
+    return [sanitizedVal, warnings];
   }
   __name(filterSequenceString, "filterSequenceString");
+  function getAcceptedChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  } = {}) {
+    return isProtein ? `${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()
+    );
+  }
+  __name(getAcceptedChars, "getAcceptedChars");
+  function getReplaceChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna
+  } = {}) {
+    return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+      //just plain old dna
+      {}
+    );
+  }
+  __name(getReplaceChars, "getReplaceChars");
   function tidyUpAnnotation(_annotation, {
     sequenceData = {},
     convertAnnotationsFromAAIndices,
@@ -12465,14 +12535,6 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     }
   }
   __name(coerceLocation, "coerceLocation");
-  function filterAminoAcidSequenceString(sequenceString, options) {
-    options = options || {};
-    if (options.includeStopCodon) {
-      return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu.*]/gi, "");
-    }
-    return sequenceString == null ? void 0 : sequenceString.replace(/[^xtgalmfwkqespvicyhrndu]/gi, "");
-  }
-  __name(filterAminoAcidSequenceString, "filterAminoAcidSequenceString");
   function getDegenerateDnaStringFromAAString(aaString) {
     return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
   }
@@ -12481,14 +12543,13 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     const {
       annotationsAsObjects,
       logMessages,
-      removeUnwantedChars,
+      doNotRemoveInvalidChars,
       additionalValidChars,
       noTranslationData,
-      charOverrides,
       doNotProvideIdsForAnnotations,
-      proteinFilterOptions,
       noCdsTranslations,
-      convertAnnotationsFromAAIndices
+      convertAnnotationsFromAAIndices,
+      topLevelSeqData
     } = options;
     let seqData = lodashExports.cloneDeep(pSeqData);
     const response = {
@@ -12516,18 +12577,15 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     if (seqData.isRna) {
       seqData.sequence = seqData.sequence.replace(/t/gi, "u");
     }
-    if (removeUnwantedChars) {
+    if (!doNotRemoveInvalidChars) {
       if (seqData.isProtein) {
-        seqData.proteinSequence = filterAminoAcidSequenceString(
-          seqData.proteinSequence,
-          __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-        );
+        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+        seqData.proteinSequence = newSeq;
       } else {
-        seqData.sequence = filterSequenceString(
-          seqData.sequence,
-          `${additionalValidChars || ""}${seqData.isRna || seqData.isMixedRnaAndDna ? "u" : ""}`,
-          charOverrides
-        );
+        const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
+          additionalValidChars
+        }, topLevelSeqData || seqData));
+        seqData.sequence = newSeq;
       }
     }
     if (seqData.isProtein) {
@@ -22667,7 +22725,6 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   exports2.deleteSequenceDataAtRange = deleteSequenceDataAtRange;
   exports2.doesEnzymeChopOutsideOfRecognitionSite = doesEnzymeChopOutsideOfRecognitionSite;
   exports2.featureColors = featureColors;
-  exports2.filterAminoAcidSequenceString = filterAminoAcidSequenceString;
   exports2.filterSequenceString = filterSequenceString;
   exports2.findNearestRangeOfSequenceOverlapToPosition = findNearestRangeOfSequenceOverlapToPosition;
   exports2.findOrfsInPlasmid = findOrfsInPlasmid;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.8",
+  "version": "0.3.10",
   "dependencies": {
     "@teselagen/range-utils": "0.3.7",
     "bson-objectid": "^2.0.4",

package/src/bioData.js

@@ -1,8 +1,8 @@
 //Adapted from biopython. Check the BIOPYTHON_LICENSE for licensing info
 
 export const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
-
-export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
+export const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
+export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 export const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 export const unambiguous_dna_letters = "GATC";
 export const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -29,7 +29,6 @@ export const ambiguous_dna_values = {
   N: "GATC"
 };
 
-
 export const extended_protein_values = {
   A: "A",
   B: "ND",

package/src/filterSequenceString.js

@@ -1,24 +1,113 @@
-// this is throwing a weird eslint error
+import {
+  ambiguous_dna_letters,
+  ambiguous_rna_letters,
+  extended_protein_letters,
+} from "./bioData";
 
-//
 export default function filterSequenceString(
   sequenceString,
-  additionalValidChars = "",
-  charOverrides
+  {
+    additionalValidChars = "",
+    isOligo,
+    name,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna,
+  } = {}
 ) {
-  // 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,
+  });
+  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: ${invalidChars
+        .slice(0, 100)
+        .join(", ")} `
     );
-  } else {
-    return sequenceString;
   }
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach(warning => {
+      window.toastr.warning(warning);
+    });
+  }
+
+  return [sanitizedVal, warnings];
+}
+
+export function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna,
+} = {}) {
+  return isProtein
+    ? `${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();
+}
+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 +1,70 @@
 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(`Replaced "." with "*" 2 times`);
+    expect(warnings[0]).toBe(      'Invalid character(s) detected and removed: 3, 4, 2, ", ", ", ,, ,, ., ., / ');
+    expect(str).toBe("bbbxtgalmfwkqespvicyhrnd");
+  });
+  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, it should convert . to *", () => {
+    const [str] = filterSequenceString('BXZJUO*bbb342"""xtgalbmfwkqespvicyhrnd,,../', {
+      isProtein: true,
+    });
+
+    expect(str).toBe("BXZJUO*bbbxtgalbmfwkqespvicyhrnd");
   });
 });

package/src/index.js

@@ -51,7 +51,6 @@ export { default as aliasedEnzymesByName } from "./aliasedEnzymesByName";
 export { default as defaultEnzymesByName } from "./defaultEnzymesByName";
 export { default as generateSequenceData } from "./generateSequenceData";
 export { default as generateAnnotations } from "./generateAnnotations";
-export { default as filterAminoAcidSequenceString } from "./filterAminoAcidSequenceString";
 export { default as filterSequenceString } from "./filterSequenceString";
 export { default as findNearestRangeOfSequenceOverlapToPosition } from "./findNearestRangeOfSequenceOverlapToPosition";
 export { default as findOrfsInPlasmid } from "./findOrfsInPlasmid";

package/src/proteinAlphabet.js

@@ -1,4 +1,3 @@
-
 const proteinAlphabet = {
   A: {
     value: "A",
@@ -18,7 +17,7 @@ const proteinAlphabet = {
     color: "hsl(258.1, 100%, 69%)",
     mass: 156.18568
   },
-  
+
   N: {
     value: "N",
     name: "Asparagine",
@@ -46,7 +45,7 @@ const proteinAlphabet = {
     color: "hsl(335.1, 100%, 69%)",
     mass: 103.1429
   },
-  
+
   E: {
     value: "E",
     name: "Glutamic acid",
@@ -75,7 +74,6 @@ const proteinAlphabet = {
     mass: 57.05132
   },
 
-
   H: {
     value: "H",
     name: "Histidine",
@@ -114,7 +112,6 @@ const proteinAlphabet = {
     mass: 128.17228
   },
 
-  
   M: {
     value: "M",
     name: "Methionine",

package/src/tidyUpSequenceData.js

@@ -6,7 +6,6 @@ import { cloneDeep, flatMap } from "lodash";
 import { annotationTypes } from "./annotationTypes";
 import filterSequenceString from "./filterSequenceString";
 import tidyUpAnnotation from "./tidyUpAnnotation";
-import filterAminoAcidSequenceString from "./filterAminoAcidSequenceString";
 import getDegenerateDnaStringFromAaString from "./getDegenerateDnaStringFromAAString";
 import { getFeatureTypes } from "./featureTypesAndColors";
 
@@ -14,14 +13,13 @@ export default function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
     logMessages,
-    removeUnwantedChars,
+    doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
-    charOverrides,
     doNotProvideIdsForAnnotations,
-    proteinFilterOptions,
     noCdsTranslations,
-    convertAnnotationsFromAAIndices
+    convertAnnotationsFromAAIndices,
+    topLevelSeqData
   } = options;
   let seqData = cloneDeep(pSeqData); //sequence is usually immutable, so we clone it and return it
   const response = {
@@ -54,20 +52,18 @@ export default function tidyUpSequenceData(pSeqData, options = {}) {
     //flip all t's to u's
     seqData.sequence = seqData.sequence.replace(/t/gi, "u");
   }
-  if (removeUnwantedChars) {
+  if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      seqData.proteinSequence = filterAminoAcidSequenceString(
-        seqData.proteinSequence,
-        { includeStopCodon: true, ...proteinFilterOptions }
-      );
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, {
+        ...(topLevelSeqData || seqData)
+      });
+      seqData.proteinSequence = newSeq;
     } else {
-      seqData.sequence = filterSequenceString(
-        seqData.sequence,
-        `${additionalValidChars || ""}${
-          seqData.isRna || seqData.isMixedRnaAndDna ? "u" : "" //if it is rna or mixed, allow u's
-        }`,
-        charOverrides
-      );
+      const [newSeq] = filterSequenceString(seqData.sequence, {
+        additionalValidChars,
+        ...(topLevelSeqData || seqData)
+      });
+      seqData.sequence = newSeq;
     }
   }
   if (seqData.isProtein) {

package/src/tidyUpSequenceData.test.js

@@ -5,7 +5,7 @@ import chaiSubset from "chai-subset";
 chai.use(chaiSubset);
 chai.should();
 describe("tidyUpSequenceData", () => {
-  it("should remove unwanted chars if passed that option, while handling annotation start,end (and location start,end) truncation correctly", () => {
+  it("should remove invalid chars by default, while handling annotation start,end (and location start,end) truncation correctly", () => {
     const res = tidyUpSequenceData(
       {
         sequence: "http://localhost:3344/Standalone",
@@ -26,7 +26,7 @@ describe("tidyUpSequenceData", () => {
           }
         ]
       },
-      { removeUnwantedChars: true }
+      
     );
     res.should.containSubset({
       sequence: "httcahstStandan",
@@ -49,15 +49,6 @@ describe("tidyUpSequenceData", () => {
       ]
     });
   });
-  // const res = tidyUpSequenceData(
-  //   {
-  //     isProtein: true,
-  //     circular: true,
-  //     proteinSequence: "gagiuhwgagalasjglj*.",
-  //     features: [{ start: 3, end: 10 }, { start: 10, end: 20 }]
-  //   },
-  //   { convertAnnotationsFromAAIndices: true, removeUnwantedChars: true }
-  // );
 
   it("should handle a protein sequence being passed in with isProtein set to true", () => {
     const res = tidyUpSequenceData(
@@ -71,69 +62,24 @@ describe("tidyUpSequenceData", () => {
           { name: "iDon'tFit", start: 25, end: 35 }
         ]
       },
-      { convertAnnotationsFromAAIndices: true, removeUnwantedChars: true }
+      { convertAnnotationsFromAAIndices: true }
     );
+    
     res.should.containSubset({
-      aminoAcidDataForEachBaseOfDNA: [
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 0,
-          aminoAcidIndex: 17,
-          sequenceIndex: 51,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        },
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 1,
-          aminoAcidIndex: 17,
-          sequenceIndex: 52,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        },
-        {
-          aminoAcid: {
-            value: ".",
-            name: "Gap",
-            threeLettersName: "Gap"
-          },
-          positionInCodon: 2,
-          aminoAcidIndex: 17,
-          sequenceIndex: 53,
-          codonRange: {
-            start: 51,
-            end: 53
-          },
-          fullCodon: true
-        }
-      ],
+      aminoAcidDataForEachBaseOfDNA: [],
       isProtein: true,
-      size: 54, //size should refer to the DNA length
-      proteinSize: 18, //proteinSize should refer to the amino acid length
-      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnggnytntrr...", //degenerate sequence
-      proteinSequence: "gagiuhwgagalasgl*.",
+      size: 57, //size should refer to the DNA length
+      proteinSize: 19, //proteinSize should refer to the amino acid length
+      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnhtnggnytnhtntrr", //degenerate sequence
+      proteinSequence: "gagiuhwgagalasjglj*",
       circular: false,
       features: [
         { start: 9, end: 32, forward: true },
-        { start: 30, end: 53, forward: true },
+        { start: 30, end: 56, forward: true },
         {
           name: "iDon'tFit",
-          start: 51,
-          end: 53,
+          start: 54,
+          end: 56,
           forward: true
         }
       ]

package/filterAminoAcidSequenceString.d.ts

@@ -1 +0,0 @@
-export default function filterAminoAcidSequenceString(sequenceString: any, options: any): any;

package/filterAminoAcidSequenceString.test.d.ts

@@ -1 +0,0 @@
-export {};

package/src/filterAminoAcidSequenceString.js

@@ -1,10 +0,0 @@
-//
-export default function filterAminoAcidSequenceString(sequenceString, options) {
-  options = options || {};
-  if (options.includeStopCodon) {
-    //tnrtodo this maybe needs the stop codon char in it?
-    return sequenceString?.replace(/[^xtgalmfwkqespvicyhrndu.*]/gi, "");
-  }
-  // ac.throw(ac.string, sequenceString);
-  return sequenceString?.replace(/[^xtgalmfwkqespvicyhrndu]/gi, "");
-}

package/src/filterAminoAcidSequenceString.test.js

@@ -1,24 +0,0 @@
-import assert from "assert";
-import filterAminoAcidSequenceString from "./filterAminoAcidSequenceString";
-describe("filterAminoAcidSequenceString", () => {
-  it("should filter only valid amino acids by default", () => {
-    const filteredString = filterAminoAcidSequenceString(
-      'bbb342"""xtgalmfwkqespvicyhrnd,,../'
-    );
-    assert.equal(filteredString, "xtgalmfwkqespvicyhrnd");
-  });
-  it("should handle upper case letters", () => {
-    const filteredString = filterAminoAcidSequenceString(
-      "xtgalmfWKQEspvicyhrnd"
-    );
-    assert.equal(filteredString, "xtgalmfWKQEspvicyhrnd");
-  });
-  it("should handle the option to includeStopCodon by allowing periods", () => {
-    const options = { includeStopCodon: true };
-    const filteredString = filterAminoAcidSequenceString(
-      'bbb342"""xtgalmfwkqespvicyhrnd,,../',
-      options
-    );
-    assert.equal(filteredString, "xtgalmfwkqespvicyhrnd..");
-  });
-});