@teselagen/bio-parsers 0.3.10 → 0.4.1

package/index.js

@@ -6170,7 +6170,9 @@ lodash.exports;
 })(lodash, lodash.exports);
 var lodashExports = lodash.exports;
 const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
+const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
+const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
 const aminoAcidToDegenerateDnaMap = {
   "-": "---",
   ".": "...",
@@ -11273,20 +11275,91 @@ const annotationTypes = [
   "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,
+  includeStopCodon
+} = {}) {
+  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);
+    }
+  });
+  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: ${invalidChars.slice(0, 100).join(", ")} `
     );
-  } else {
-    return sequenceString;
   }
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach((warning) => {
+      window.toastr.warning(warning);
+    });
+  }
+  return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
+function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna,
+  includeStopCodon
+} = {}) {
+  return isProtein ? `${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()
+  );
+}
+__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,
@@ -11415,14 +11488,6 @@ 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("");
 }
@@ -11434,11 +11499,10 @@ function tidyUpSequenceData(pSeqData, options = {}) {
     removeUnwantedChars,
     additionalValidChars,
     noTranslationData,
-    charOverrides,
     doNotProvideIdsForAnnotations,
-    proteinFilterOptions,
     noCdsTranslations,
-    convertAnnotationsFromAAIndices
+    convertAnnotationsFromAAIndices,
+    topLevelSeqData
   } = options;
   let seqData = lodashExports.cloneDeep(pSeqData);
   const response = {
@@ -11468,16 +11532,15 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   }
   if (removeUnwantedChars) {
     if (seqData.isProtein) {
-      seqData.proteinSequence = filterAminoAcidSequenceString(
-        seqData.proteinSequence,
-        __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-      );
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
+        includeStopCodon: true
+      }, 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) {
@@ -19312,7 +19375,8 @@ function validateSequence(sequence, options = {}) {
     inclusive1BasedEnd,
     additionalValidChars,
     allowOverflowAnnotations,
-    coerceFeatureTypes
+    coerceFeatureTypes,
+    includeStopCodon
   } = options;
   [
     "isDNA",
@@ -19362,7 +19426,6 @@ function validateSequence(sequence, options = {}) {
     response.messages.push("No sequence detected");
     sequence.sequence = "";
   }
-  let validChars;
   if (sequence.isProtein === void 0 && guessIfProtein) {
     sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
@@ -19370,12 +19433,15 @@ function validateSequence(sequence, options = {}) {
     );
   }
   if (sequence.isProtein) {
-    validChars = filterAminoAcidSequenceString(sequence.sequence);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, {
+      name: sequence.name,
+      isProtein: true,
+      additionalValidChars,
+      includeStopCodon
+    });
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from amino acid sequence. Allowed characters are: xtgalmfwkqespvicyhrndu"
-      );
+      response.messages.push(...warnings);
     }
     sequence.type = "PROTEIN";
     sequence.isProtein = true;
@@ -19397,12 +19463,12 @@ function validateSequence(sequence, options = {}) {
     } else {
       sequence.type = "DNA";
     }
-    validChars = filterSequenceString(sequence.sequence, additionalValidChars);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, __spreadValues({
+      additionalValidChars
+    }, sequence));
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from sequence. Allowed characters are: atgcyrswkmbvdhn"
-      );
+      response.messages.push(...warnings);
     }
   }
   if (!sequence.size) {

package/index.mjs

@@ -6168,7 +6168,9 @@ lodash.exports;
 })(lodash, lodash.exports);
 var lodashExports = lodash.exports;
 const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
+const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
+const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
 const aminoAcidToDegenerateDnaMap = {
   "-": "---",
   ".": "...",
@@ -11271,20 +11273,91 @@ const annotationTypes = [
   "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,
+  includeStopCodon
+} = {}) {
+  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);
+    }
+  });
+  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: ${invalidChars.slice(0, 100).join(", ")} `
     );
-  } else {
-    return sequenceString;
   }
+  if (typeof window !== "undefined" && window.toastr && warnings.length) {
+    warnings.forEach((warning) => {
+      window.toastr.warning(warning);
+    });
+  }
+  return [sanitizedVal, warnings];
 }
 __name(filterSequenceString, "filterSequenceString");
+function getAcceptedChars({
+  isOligo,
+  isProtein,
+  isRna,
+  isMixedRnaAndDna,
+  includeStopCodon
+} = {}) {
+  return isProtein ? `${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()
+  );
+}
+__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,
@@ -11413,14 +11486,6 @@ 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("");
 }
@@ -11432,11 +11497,10 @@ function tidyUpSequenceData(pSeqData, options = {}) {
     removeUnwantedChars,
     additionalValidChars,
     noTranslationData,
-    charOverrides,
     doNotProvideIdsForAnnotations,
-    proteinFilterOptions,
     noCdsTranslations,
-    convertAnnotationsFromAAIndices
+    convertAnnotationsFromAAIndices,
+    topLevelSeqData
   } = options;
   let seqData = lodashExports.cloneDeep(pSeqData);
   const response = {
@@ -11466,16 +11530,15 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   }
   if (removeUnwantedChars) {
     if (seqData.isProtein) {
-      seqData.proteinSequence = filterAminoAcidSequenceString(
-        seqData.proteinSequence,
-        __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-      );
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
+        includeStopCodon: true
+      }, 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) {
@@ -19310,7 +19373,8 @@ function validateSequence(sequence, options = {}) {
     inclusive1BasedEnd,
     additionalValidChars,
     allowOverflowAnnotations,
-    coerceFeatureTypes
+    coerceFeatureTypes,
+    includeStopCodon
   } = options;
   [
     "isDNA",
@@ -19360,7 +19424,6 @@ function validateSequence(sequence, options = {}) {
     response.messages.push("No sequence detected");
     sequence.sequence = "";
   }
-  let validChars;
   if (sequence.isProtein === void 0 && guessIfProtein) {
     sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
@@ -19368,12 +19431,15 @@ function validateSequence(sequence, options = {}) {
     );
   }
   if (sequence.isProtein) {
-    validChars = filterAminoAcidSequenceString(sequence.sequence);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, {
+      name: sequence.name,
+      isProtein: true,
+      additionalValidChars,
+      includeStopCodon
+    });
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from amino acid sequence. Allowed characters are: xtgalmfwkqespvicyhrndu"
-      );
+      response.messages.push(...warnings);
     }
     sequence.type = "PROTEIN";
     sequence.isProtein = true;
@@ -19395,12 +19461,12 @@ function validateSequence(sequence, options = {}) {
     } else {
       sequence.type = "DNA";
     }
-    validChars = filterSequenceString(sequence.sequence, additionalValidChars);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, __spreadValues({
+      additionalValidChars
+    }, sequence));
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from sequence. Allowed characters are: atgcyrswkmbvdhn"
-      );
+      response.messages.push(...warnings);
     }
   }
   if (!sequence.size) {

package/index.umd.js

@@ -6172,7 +6172,9 @@ var __async = (__this, __arguments, generator) => {
   })(lodash, lodash.exports);
   var lodashExports = lodash.exports;
   const _ = /* @__PURE__ */ getDefaultExportFromCjs(lodashExports);
+  const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
   const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
+  const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
   const aminoAcidToDegenerateDnaMap = {
     "-": "---",
     ".": "...",
@@ -11275,20 +11277,91 @@ var __async = (__this, __arguments, generator) => {
     "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: name2,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna,
+    includeStopCodon
+  } = {}) {
+    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);
+      }
+    });
+    Object.keys(replaceCount).forEach((letter) => {
+      warnings.push(
+        `Replaced "${letter}" with "${replaceChars[letter]}"${replaceCount[letter] > 1 ? ` ${replaceCount[letter]} times` : ""}`
+      );
+    });
+    if (sequenceString.length !== sanitizedVal.length) {
+      warnings.push(
+        `${name2 ? `Sequence ${name2}: ` : ""}Invalid character(s) detected and removed: ${invalidChars.slice(0, 100).join(", ")} `
       );
-    } else {
-      return sequenceString;
     }
+    if (typeof window !== "undefined" && window.toastr && warnings.length) {
+      warnings.forEach((warning) => {
+        window.toastr.warning(warning);
+      });
+    }
+    return [sanitizedVal, warnings];
   }
   __name(filterSequenceString, "filterSequenceString");
+  function getAcceptedChars({
+    isOligo,
+    isProtein,
+    isRna,
+    isMixedRnaAndDna,
+    includeStopCodon
+  } = {}) {
+    return isProtein ? `${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()
+    );
+  }
+  __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,
@@ -11417,14 +11490,6 @@ var __async = (__this, __arguments, generator) => {
     }
   }
   __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("");
   }
@@ -11436,11 +11501,10 @@ var __async = (__this, __arguments, generator) => {
       removeUnwantedChars,
       additionalValidChars,
       noTranslationData,
-      charOverrides,
       doNotProvideIdsForAnnotations,
-      proteinFilterOptions,
       noCdsTranslations,
-      convertAnnotationsFromAAIndices
+      convertAnnotationsFromAAIndices,
+      topLevelSeqData
     } = options;
     let seqData = lodashExports.cloneDeep(pSeqData);
     const response = {
@@ -11470,16 +11534,15 @@ var __async = (__this, __arguments, generator) => {
     }
     if (removeUnwantedChars) {
       if (seqData.isProtein) {
-        seqData.proteinSequence = filterAminoAcidSequenceString(
-          seqData.proteinSequence,
-          __spreadValues({ includeStopCodon: true }, proteinFilterOptions)
-        );
+        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({
+          includeStopCodon: true
+        }, 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) {
@@ -19314,7 +19377,8 @@ var __async = (__this, __arguments, generator) => {
       inclusive1BasedEnd,
       additionalValidChars,
       allowOverflowAnnotations,
-      coerceFeatureTypes
+      coerceFeatureTypes,
+      includeStopCodon
     } = options;
     [
       "isDNA",
@@ -19364,7 +19428,6 @@ var __async = (__this, __arguments, generator) => {
       response.messages.push("No sequence detected");
       sequence.sequence = "";
     }
-    let validChars;
     if (sequence.isProtein === void 0 && guessIfProtein) {
       sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
         sequence.sequence,
@@ -19372,12 +19435,15 @@ var __async = (__this, __arguments, generator) => {
       );
     }
     if (sequence.isProtein) {
-      validChars = filterAminoAcidSequenceString(sequence.sequence);
+      const [validChars, warnings] = filterSequenceString(sequence.sequence, {
+        name: sequence.name,
+        isProtein: true,
+        additionalValidChars,
+        includeStopCodon
+      });
       if (validChars !== sequence.sequence) {
         sequence.sequence = validChars;
-        response.messages.push(
-          "Import Error: Illegal character(s) detected and removed from amino acid sequence. Allowed characters are: xtgalmfwkqespvicyhrndu"
-        );
+        response.messages.push(...warnings);
       }
       sequence.type = "PROTEIN";
       sequence.isProtein = true;
@@ -19399,12 +19465,12 @@ var __async = (__this, __arguments, generator) => {
       } else {
         sequence.type = "DNA";
       }
-      validChars = filterSequenceString(sequence.sequence, additionalValidChars);
+      const [validChars, warnings] = filterSequenceString(sequence.sequence, __spreadValues({
+        additionalValidChars
+      }, sequence));
       if (validChars !== sequence.sequence) {
         sequence.sequence = validChars;
-        response.messages.push(
-          "Import Error: Illegal character(s) detected and removed from sequence. Allowed characters are: atgcyrswkmbvdhn"
-        );
+        response.messages.push(...warnings);
       }
     }
     if (!sequence.size) {

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "@teselagen/bio-parsers",
-  "version": "0.3.10",
+  "version": "0.4.1",
   "dependencies": {
-    "@teselagen/sequence-utils": "0.3.8",
+    "@teselagen/sequence-utils": "0.3.9",
     "@teselagen/range-utils": "0.3.7",
     "@gmod/gff": "^1.2.1",
     "buffer": "^6.0.3",

package/src/utils/validateSequence.js

@@ -1,7 +1,6 @@
 import areNonNegativeIntegers from "validate.io-nonnegative-integer-array";
 import { getFeatureTypes } from "@teselagen/sequence-utils";
 import {
-  filterAminoAcidSequenceString,
   filterSequenceString,
   guessIfSequenceIsDnaAndNotProtein
 } from "@teselagen/sequence-utils";
@@ -30,7 +29,8 @@ export default function validateSequence(sequence, options = {}) {
     inclusive1BasedEnd,
     additionalValidChars,
     allowOverflowAnnotations,
-    coerceFeatureTypes
+    coerceFeatureTypes,
+    includeStopCodon
   } = options;
   [
     "isDNA",
@@ -84,7 +84,7 @@ export default function validateSequence(sequence, options = {}) {
     response.messages.push("No sequence detected");
     sequence.sequence = "";
   }
-  let validChars;
+
   if (sequence.isProtein === undefined && guessIfProtein) {
     sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
@@ -93,12 +93,15 @@ export default function validateSequence(sequence, options = {}) {
   }
   if (sequence.isProtein) {
     //tnr: add code to strip invalid protein data..
-    validChars = filterAminoAcidSequenceString(sequence.sequence);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, {
+      name: sequence.name,
+      isProtein: true,
+      additionalValidChars,
+      includeStopCodon
+    });
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from amino acid sequence. Allowed characters are: xtgalmfwkqespvicyhrndu"
-      );
+      response.messages.push(...warnings);
     }
     sequence.type = "PROTEIN";
     sequence.isProtein = true;
@@ -126,12 +129,13 @@ export default function validateSequence(sequence, options = {}) {
       sequence.type = "DNA";
     }
 
-    validChars = filterSequenceString(sequence.sequence, additionalValidChars);
+    const [validChars, warnings] = filterSequenceString(sequence.sequence, {
+      additionalValidChars,
+      ...sequence
+    });
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
-      response.messages.push(
-        "Import Error: Illegal character(s) detected and removed from sequence. Allowed characters are: atgcyrswkmbvdhn"
-      );
+      response.messages.push(...warnings);
     }
   }