@teselagen/bio-parsers 0.4.15 → 0.4.16

package/genbankToJson.d.ts

@@ -1,3 +1,3 @@
-export function parseFeatureLocation(locStr: any, isProtein: any, inclusive1BasedStart: any, inclusive1BasedEnd: any, isCircular: any, sequenceLength: any): any[];
+export function parseFeatureLocation(locStr: any, isProtein: any, inclusive1BasedStart: any, inclusive1BasedEnd: any, isCircular: any, sequenceLength: any): any;
 export default genbankToJson;
 declare function genbankToJson(string: any, options?: {}): any;

package/index.js

@@ -11506,6 +11506,26 @@ function getDegenerateDnaStringFromAAString(aaString) {
   return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
 }
 __name(getDegenerateDnaStringFromAAString, "getDegenerateDnaStringFromAAString");
+function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
+  const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
+    sequenceString,
+    true
+  );
+  const aaArray = [];
+  let aaString = "";
+  aminoAcidsPerBase.forEach((aa, index) => {
+    if (!aa.fullCodon) {
+      return;
+    }
+    if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
+      return;
+    }
+    aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
+  });
+  aaString = aaArray.join("");
+  return aaString;
+}
+__name(getAminoAcidStringFromSequenceString, "getAminoAcidStringFromSequenceString");
 function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
@@ -11513,6 +11533,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
     doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
+    includeProteinSequence,
     doNotProvideIdsForAnnotations,
     noCdsTranslations,
     convertAnnotationsFromAAIndices,
@@ -11546,7 +11567,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   }
   if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadProps(__spreadValues({}, topLevelSeqData || seqData), {
+        isProtein: true
+      }));
       seqData.proteinSequence = newSeq;
     } else {
       const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
@@ -11567,6 +11590,10 @@ function tidyUpSequenceData(pSeqData, options = {}) {
       null,
       true
     );
+  } else if (includeProteinSequence) {
+    seqData.proteinSequence = getAminoAcidStringFromSequenceString(
+      seqData.sequence
+    );
   }
   seqData.size = seqData.noSequence ? seqData.size : seqData.sequence.length;
   seqData.proteinSize = seqData.noSequence ? seqData.proteinSize : seqData.proteinSequence.length;
@@ -19787,19 +19814,38 @@ function flattenSequenceArray(parsingResultArray, opts) {
   return parsingResultArray;
 }
 __name(flattenSequenceArray, "flattenSequenceArray");
+function wrapOriginSpanningFeatures(locArrayInput, sequenceLength, inclusive1BasedStart, inclusive1BasedEnd) {
+  const locArrayOutput = locArrayInput.map((loc) => __spreadValues({}, loc));
+  for (let i = 0; i < locArrayOutput.length - 1; i++) {
+    const firstFeature = locArrayOutput[i];
+    const secondFeature = locArrayOutput[i + 1];
+    if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
+      locArrayOutput[i] = {
+        start: firstFeature.start,
+        end: secondFeature.end
+      };
+      locArrayOutput.splice(i + 1, 1);
+    }
+  }
+  return locArrayOutput;
+}
+__name(wrapOriginSpanningFeatures, "wrapOriginSpanningFeatures");
 function parseFeatureLocation(locStr, isProtein, inclusive1BasedStart, inclusive1BasedEnd, isCircular, sequenceLength) {
   locStr = locStr.trim();
-  const locArr = [];
-  locStr.replace(/(\d+)/g, function(string, match) {
-    locArr.push(match);
+  const positionsArray = [];
+  const locationParts = locStr.split(",");
+  locationParts.forEach((locPart) => {
+    const extractedPositions = locPart.match(/(\d+)/g);
+    if (extractedPositions === null) {
+      return;
+    }
+    positionsArray.push(extractedPositions[0]);
+    positionsArray.push(extractedPositions[1] || extractedPositions[0]);
   });
   const locArray = [];
-  for (let i = 0; i < locArr.length; i += 2) {
-    const start = parseInt(locArr[i], 10) - (inclusive1BasedStart ? 0 : 1);
-    let end = parseInt(locArr[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
-    if (isNaN(end)) {
-      end = start;
-    }
+  for (let i = 0; i < positionsArray.length; i += 2) {
+    const start = parseInt(positionsArray[i], 10) - (inclusive1BasedStart ? 0 : 1);
+    const end = parseInt(positionsArray[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
     const location = {
       start,
       end
@@ -19808,20 +19854,16 @@ function parseFeatureLocation(locStr, isProtein, inclusive1BasedStart, inclusive
       isProtein ? convertAACaretPositionOrRangeToDna(location) : location
     );
   }
-  if (isCircular) {
-    for (let i = 0; i < locArray.length; i += 2) {
-      const firstFeature = locArray[i];
-      const secondFeature = locArray[i + 1];
-      if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
-        locArray[i] = {
-          start: firstFeature.start,
-          end: secondFeature.end
-        };
-        locArray.splice(i + 1, 1);
-      }
-    }
+  if (isCircular && sequenceLength) {
+    return wrapOriginSpanningFeatures(
+      locArray,
+      sequenceLength,
+      inclusive1BasedStart,
+      inclusive1BasedEnd
+    );
+  } else {
+    return locArray;
   }
-  return locArray;
 }
 __name(parseFeatureLocation, "parseFeatureLocation");
 function genbankToJson(string, options = {}) {
@@ -19918,7 +19960,7 @@ function genbankToJson(string, options = {}) {
           parseOrigin(line, key);
           break;
         case genbankAnnotationKey.END_SEQUENCE_TAG:
-          endSeq();
+          endSeq(options);
           break;
         case genbankAnnotationKey.DEFINITION_TAG:
           line = line.replace(/DEFINITION/, "");
@@ -20023,9 +20065,9 @@ function genbankToJson(string, options = {}) {
     }
   });
   return results;
-  function endSeq() {
+  function endSeq(options2) {
     hasFoundLocus = false;
-    postProcessCurSeq();
+    postProcessCurSeq(options2);
     resultsArray.push(result || { success: false });
   }
   __name(endSeq, "endSeq");
@@ -20039,11 +20081,13 @@ function genbankToJson(string, options = {}) {
     }
   }
   __name(addMessage, "addMessage");
-  function postProcessCurSeq() {
+  function postProcessCurSeq(options2) {
     if (result && result.parsedSequence && result.parsedSequence.features) {
       for (let i = 0; i < result.parsedSequence.features.length; i++) {
         result.parsedSequence.features[i] = postProcessGenbankFeature(
-          result.parsedSequence.features[i]
+          result.parsedSequence.features[i],
+          result.parsedSequence,
+          options2
         );
       }
     }
@@ -20289,7 +20333,7 @@ function genbankToJson(string, options = {}) {
     return runon;
   }
   __name(isKeywordRunon, "isKeywordRunon");
-  function postProcessGenbankFeature(feat) {
+  function postProcessGenbankFeature(feat, parsedSequence, options2) {
     if (feat.notes.label) {
       feat.name = feat.notes.label[0];
     } else if (feat.notes.gene) {
@@ -20322,6 +20366,15 @@ function genbankToJson(string, options = {}) {
       feat.arrowheadType = feat.notes.direction[0].toUpperCase() === "BOTH" ? "BOTH" : feat.notes.direction[0].toUpperCase() === "NONE" ? "NONE" : void 0;
       delete feat.notes.direction;
     }
+    if (parsedSequence.circular) {
+      const { inclusive1BasedStart: inclusive1BasedStart2, inclusive1BasedEnd: inclusive1BasedEnd2 } = options2;
+      feat.locations = wrapOriginSpanningFeatures(
+        feat.locations,
+        parsedSequence.sequence.length,
+        inclusive1BasedStart2,
+        inclusive1BasedEnd2
+      );
+    }
     return feat;
   }
   __name(postProcessGenbankFeature, "postProcessGenbankFeature");

package/index.mjs

@@ -11504,6 +11504,26 @@ function getDegenerateDnaStringFromAAString(aaString) {
   return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
 }
 __name(getDegenerateDnaStringFromAAString, "getDegenerateDnaStringFromAAString");
+function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
+  const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
+    sequenceString,
+    true
+  );
+  const aaArray = [];
+  let aaString = "";
+  aminoAcidsPerBase.forEach((aa, index) => {
+    if (!aa.fullCodon) {
+      return;
+    }
+    if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
+      return;
+    }
+    aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
+  });
+  aaString = aaArray.join("");
+  return aaString;
+}
+__name(getAminoAcidStringFromSequenceString, "getAminoAcidStringFromSequenceString");
 function tidyUpSequenceData(pSeqData, options = {}) {
   const {
     annotationsAsObjects,
@@ -11511,6 +11531,7 @@ function tidyUpSequenceData(pSeqData, options = {}) {
     doNotRemoveInvalidChars,
     additionalValidChars,
     noTranslationData,
+    includeProteinSequence,
     doNotProvideIdsForAnnotations,
     noCdsTranslations,
     convertAnnotationsFromAAIndices,
@@ -11544,7 +11565,9 @@ function tidyUpSequenceData(pSeqData, options = {}) {
   }
   if (!doNotRemoveInvalidChars) {
     if (seqData.isProtein) {
-      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+      const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadProps(__spreadValues({}, topLevelSeqData || seqData), {
+        isProtein: true
+      }));
       seqData.proteinSequence = newSeq;
     } else {
       const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
@@ -11565,6 +11588,10 @@ function tidyUpSequenceData(pSeqData, options = {}) {
       null,
       true
     );
+  } else if (includeProteinSequence) {
+    seqData.proteinSequence = getAminoAcidStringFromSequenceString(
+      seqData.sequence
+    );
   }
   seqData.size = seqData.noSequence ? seqData.size : seqData.sequence.length;
   seqData.proteinSize = seqData.noSequence ? seqData.proteinSize : seqData.proteinSequence.length;
@@ -19785,19 +19812,38 @@ function flattenSequenceArray(parsingResultArray, opts) {
   return parsingResultArray;
 }
 __name(flattenSequenceArray, "flattenSequenceArray");
+function wrapOriginSpanningFeatures(locArrayInput, sequenceLength, inclusive1BasedStart, inclusive1BasedEnd) {
+  const locArrayOutput = locArrayInput.map((loc) => __spreadValues({}, loc));
+  for (let i = 0; i < locArrayOutput.length - 1; i++) {
+    const firstFeature = locArrayOutput[i];
+    const secondFeature = locArrayOutput[i + 1];
+    if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
+      locArrayOutput[i] = {
+        start: firstFeature.start,
+        end: secondFeature.end
+      };
+      locArrayOutput.splice(i + 1, 1);
+    }
+  }
+  return locArrayOutput;
+}
+__name(wrapOriginSpanningFeatures, "wrapOriginSpanningFeatures");
 function parseFeatureLocation(locStr, isProtein, inclusive1BasedStart, inclusive1BasedEnd, isCircular, sequenceLength) {
   locStr = locStr.trim();
-  const locArr = [];
-  locStr.replace(/(\d+)/g, function(string, match) {
-    locArr.push(match);
+  const positionsArray = [];
+  const locationParts = locStr.split(",");
+  locationParts.forEach((locPart) => {
+    const extractedPositions = locPart.match(/(\d+)/g);
+    if (extractedPositions === null) {
+      return;
+    }
+    positionsArray.push(extractedPositions[0]);
+    positionsArray.push(extractedPositions[1] || extractedPositions[0]);
   });
   const locArray = [];
-  for (let i = 0; i < locArr.length; i += 2) {
-    const start = parseInt(locArr[i], 10) - (inclusive1BasedStart ? 0 : 1);
-    let end = parseInt(locArr[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
-    if (isNaN(end)) {
-      end = start;
-    }
+  for (let i = 0; i < positionsArray.length; i += 2) {
+    const start = parseInt(positionsArray[i], 10) - (inclusive1BasedStart ? 0 : 1);
+    const end = parseInt(positionsArray[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
     const location = {
       start,
       end
@@ -19806,20 +19852,16 @@ function parseFeatureLocation(locStr, isProtein, inclusive1BasedStart, inclusive
       isProtein ? convertAACaretPositionOrRangeToDna(location) : location
     );
   }
-  if (isCircular) {
-    for (let i = 0; i < locArray.length; i += 2) {
-      const firstFeature = locArray[i];
-      const secondFeature = locArray[i + 1];
-      if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
-        locArray[i] = {
-          start: firstFeature.start,
-          end: secondFeature.end
-        };
-        locArray.splice(i + 1, 1);
-      }
-    }
+  if (isCircular && sequenceLength) {
+    return wrapOriginSpanningFeatures(
+      locArray,
+      sequenceLength,
+      inclusive1BasedStart,
+      inclusive1BasedEnd
+    );
+  } else {
+    return locArray;
   }
-  return locArray;
 }
 __name(parseFeatureLocation, "parseFeatureLocation");
 function genbankToJson(string, options = {}) {
@@ -19916,7 +19958,7 @@ function genbankToJson(string, options = {}) {
           parseOrigin(line, key);
           break;
         case genbankAnnotationKey.END_SEQUENCE_TAG:
-          endSeq();
+          endSeq(options);
           break;
         case genbankAnnotationKey.DEFINITION_TAG:
           line = line.replace(/DEFINITION/, "");
@@ -20021,9 +20063,9 @@ function genbankToJson(string, options = {}) {
     }
   });
   return results;
-  function endSeq() {
+  function endSeq(options2) {
     hasFoundLocus = false;
-    postProcessCurSeq();
+    postProcessCurSeq(options2);
     resultsArray.push(result || { success: false });
   }
   __name(endSeq, "endSeq");
@@ -20037,11 +20079,13 @@ function genbankToJson(string, options = {}) {
     }
   }
   __name(addMessage, "addMessage");
-  function postProcessCurSeq() {
+  function postProcessCurSeq(options2) {
     if (result && result.parsedSequence && result.parsedSequence.features) {
       for (let i = 0; i < result.parsedSequence.features.length; i++) {
         result.parsedSequence.features[i] = postProcessGenbankFeature(
-          result.parsedSequence.features[i]
+          result.parsedSequence.features[i],
+          result.parsedSequence,
+          options2
         );
       }
     }
@@ -20287,7 +20331,7 @@ function genbankToJson(string, options = {}) {
     return runon;
   }
   __name(isKeywordRunon, "isKeywordRunon");
-  function postProcessGenbankFeature(feat) {
+  function postProcessGenbankFeature(feat, parsedSequence, options2) {
     if (feat.notes.label) {
       feat.name = feat.notes.label[0];
     } else if (feat.notes.gene) {
@@ -20320,6 +20364,15 @@ function genbankToJson(string, options = {}) {
       feat.arrowheadType = feat.notes.direction[0].toUpperCase() === "BOTH" ? "BOTH" : feat.notes.direction[0].toUpperCase() === "NONE" ? "NONE" : void 0;
       delete feat.notes.direction;
     }
+    if (parsedSequence.circular) {
+      const { inclusive1BasedStart: inclusive1BasedStart2, inclusive1BasedEnd: inclusive1BasedEnd2 } = options2;
+      feat.locations = wrapOriginSpanningFeatures(
+        feat.locations,
+        parsedSequence.sequence.length,
+        inclusive1BasedStart2,
+        inclusive1BasedEnd2
+      );
+    }
     return feat;
   }
   __name(postProcessGenbankFeature, "postProcessGenbankFeature");

package/index.umd.js

@@ -11508,6 +11508,26 @@ var __async = (__this, __arguments, generator) => {
     return aaString.split("").map((char) => aminoAcidToDegenerateDnaMap[char.toLowerCase()] || "nnn").join("");
   }
   __name(getDegenerateDnaStringFromAAString, "getDegenerateDnaStringFromAAString");
+  function getAminoAcidStringFromSequenceString(sequenceString, { doNotExcludeAsterisk } = {}) {
+    const aminoAcidsPerBase = getAminoAcidDataForEachBaseOfDna(
+      sequenceString,
+      true
+    );
+    const aaArray = [];
+    let aaString = "";
+    aminoAcidsPerBase.forEach((aa, index) => {
+      if (!aa.fullCodon) {
+        return;
+      }
+      if (!doNotExcludeAsterisk && index >= aminoAcidsPerBase.length - 3 && aa.aminoAcid.value === "*") {
+        return;
+      }
+      aaArray[aa.aminoAcidIndex] = aa.aminoAcid.value;
+    });
+    aaString = aaArray.join("");
+    return aaString;
+  }
+  __name(getAminoAcidStringFromSequenceString, "getAminoAcidStringFromSequenceString");
   function tidyUpSequenceData(pSeqData, options = {}) {
     const {
       annotationsAsObjects,
@@ -11515,6 +11535,7 @@ var __async = (__this, __arguments, generator) => {
       doNotRemoveInvalidChars,
       additionalValidChars,
       noTranslationData,
+      includeProteinSequence,
       doNotProvideIdsForAnnotations,
       noCdsTranslations,
       convertAnnotationsFromAAIndices,
@@ -11548,7 +11569,9 @@ var __async = (__this, __arguments, generator) => {
     }
     if (!doNotRemoveInvalidChars) {
       if (seqData.isProtein) {
-        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadValues({}, topLevelSeqData || seqData));
+        const [newSeq] = filterSequenceString(seqData.proteinSequence, __spreadProps(__spreadValues({}, topLevelSeqData || seqData), {
+          isProtein: true
+        }));
         seqData.proteinSequence = newSeq;
       } else {
         const [newSeq] = filterSequenceString(seqData.sequence, __spreadValues({
@@ -11569,6 +11592,10 @@ var __async = (__this, __arguments, generator) => {
         null,
         true
       );
+    } else if (includeProteinSequence) {
+      seqData.proteinSequence = getAminoAcidStringFromSequenceString(
+        seqData.sequence
+      );
     }
     seqData.size = seqData.noSequence ? seqData.size : seqData.sequence.length;
     seqData.proteinSize = seqData.noSequence ? seqData.proteinSize : seqData.proteinSequence.length;
@@ -19789,19 +19816,38 @@ var __async = (__this, __arguments, generator) => {
     return parsingResultArray;
   }
   __name(flattenSequenceArray, "flattenSequenceArray");
+  function wrapOriginSpanningFeatures(locArrayInput, sequenceLength, inclusive1BasedStart, inclusive1BasedEnd) {
+    const locArrayOutput = locArrayInput.map((loc) => __spreadValues({}, loc));
+    for (let i2 = 0; i2 < locArrayOutput.length - 1; i2++) {
+      const firstFeature = locArrayOutput[i2];
+      const secondFeature = locArrayOutput[i2 + 1];
+      if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
+        locArrayOutput[i2] = {
+          start: firstFeature.start,
+          end: secondFeature.end
+        };
+        locArrayOutput.splice(i2 + 1, 1);
+      }
+    }
+    return locArrayOutput;
+  }
+  __name(wrapOriginSpanningFeatures, "wrapOriginSpanningFeatures");
   function parseFeatureLocation(locStr, isProtein, inclusive1BasedStart, inclusive1BasedEnd, isCircular, sequenceLength) {
     locStr = locStr.trim();
-    const locArr = [];
-    locStr.replace(/(\d+)/g, function(string, match) {
-      locArr.push(match);
+    const positionsArray = [];
+    const locationParts = locStr.split(",");
+    locationParts.forEach((locPart) => {
+      const extractedPositions = locPart.match(/(\d+)/g);
+      if (extractedPositions === null) {
+        return;
+      }
+      positionsArray.push(extractedPositions[0]);
+      positionsArray.push(extractedPositions[1] || extractedPositions[0]);
     });
     const locArray = [];
-    for (let i2 = 0; i2 < locArr.length; i2 += 2) {
-      const start = parseInt(locArr[i2], 10) - (inclusive1BasedStart ? 0 : 1);
-      let end = parseInt(locArr[i2 + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
-      if (isNaN(end)) {
-        end = start;
-      }
+    for (let i2 = 0; i2 < positionsArray.length; i2 += 2) {
+      const start = parseInt(positionsArray[i2], 10) - (inclusive1BasedStart ? 0 : 1);
+      const end = parseInt(positionsArray[i2 + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
       const location = {
         start,
         end
@@ -19810,20 +19856,16 @@ var __async = (__this, __arguments, generator) => {
         isProtein ? convertAACaretPositionOrRangeToDna(location) : location
       );
     }
-    if (isCircular) {
-      for (let i2 = 0; i2 < locArray.length; i2 += 2) {
-        const firstFeature = locArray[i2];
-        const secondFeature = locArray[i2 + 1];
-        if (firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) && secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)) {
-          locArray[i2] = {
-            start: firstFeature.start,
-            end: secondFeature.end
-          };
-          locArray.splice(i2 + 1, 1);
-        }
-      }
+    if (isCircular && sequenceLength) {
+      return wrapOriginSpanningFeatures(
+        locArray,
+        sequenceLength,
+        inclusive1BasedStart,
+        inclusive1BasedEnd
+      );
+    } else {
+      return locArray;
     }
-    return locArray;
   }
   __name(parseFeatureLocation, "parseFeatureLocation");
   function genbankToJson(string, options = {}) {
@@ -19920,7 +19962,7 @@ var __async = (__this, __arguments, generator) => {
             parseOrigin(line, key);
             break;
           case genbankAnnotationKey.END_SEQUENCE_TAG:
-            endSeq();
+            endSeq(options);
             break;
           case genbankAnnotationKey.DEFINITION_TAG:
             line = line.replace(/DEFINITION/, "");
@@ -20025,9 +20067,9 @@ var __async = (__this, __arguments, generator) => {
       }
     });
     return results;
-    function endSeq() {
+    function endSeq(options2) {
       hasFoundLocus = false;
-      postProcessCurSeq();
+      postProcessCurSeq(options2);
       resultsArray.push(result || { success: false });
     }
     __name(endSeq, "endSeq");
@@ -20041,11 +20083,13 @@ var __async = (__this, __arguments, generator) => {
       }
     }
     __name(addMessage, "addMessage");
-    function postProcessCurSeq() {
+    function postProcessCurSeq(options2) {
       if (result && result.parsedSequence && result.parsedSequence.features) {
         for (let i2 = 0; i2 < result.parsedSequence.features.length; i2++) {
           result.parsedSequence.features[i2] = postProcessGenbankFeature(
-            result.parsedSequence.features[i2]
+            result.parsedSequence.features[i2],
+            result.parsedSequence,
+            options2
           );
         }
       }
@@ -20291,7 +20335,7 @@ var __async = (__this, __arguments, generator) => {
       return runon;
     }
     __name(isKeywordRunon, "isKeywordRunon");
-    function postProcessGenbankFeature(feat) {
+    function postProcessGenbankFeature(feat, parsedSequence, options2) {
       if (feat.notes.label) {
         feat.name = feat.notes.label[0];
       } else if (feat.notes.gene) {
@@ -20324,6 +20368,15 @@ var __async = (__this, __arguments, generator) => {
         feat.arrowheadType = feat.notes.direction[0].toUpperCase() === "BOTH" ? "BOTH" : feat.notes.direction[0].toUpperCase() === "NONE" ? "NONE" : void 0;
         delete feat.notes.direction;
       }
+      if (parsedSequence.circular) {
+        const { inclusive1BasedStart: inclusive1BasedStart2, inclusive1BasedEnd: inclusive1BasedEnd2 } = options2;
+        feat.locations = wrapOriginSpanningFeatures(
+          feat.locations,
+          parsedSequence.sequence.length,
+          inclusive1BasedStart2,
+          inclusive1BasedEnd2
+        );
+      }
       return feat;
     }
     __name(postProcessGenbankFeature, "postProcessGenbankFeature");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/bio-parsers",
-  "version": "0.4.15",
+  "version": "0.4.16",
   "dependencies": {
     "@teselagen/sequence-utils": "0.3.24",
     "@teselagen/range-utils": "0.3.7",

package/src/genbankToJson.js

@@ -8,6 +8,40 @@ import splitStringIntoLines from "./utils/splitStringIntoLines.js";
 
 import createInitialSequence from "./utils/createInitialSequence";
 
+function wrapOriginSpanningFeatures(
+  locArrayInput,
+  sequenceLength,
+  inclusive1BasedStart,
+  inclusive1BasedEnd
+) {
+  // In genbank files, locations of origin-spanning features are represented as follows:
+  // complement(join(490883..490885,1..879)) (for a circular sequence of length 490885)
+  // Then, for locations in locArray we check if there is a location that ends at sequenceLength
+  // joined with a location that starts at 1. If so, we merge them into a single location.
+  // (see https://github.com/TeselaGen/tg-oss/issues/35)
+
+  // make a deep copy of the array to avoid modifying the original
+  const locArrayOutput = locArrayInput.map(loc => ({ ...loc }));
+
+  // Iterate by pairs of features
+  for (let i = 0; i < locArrayOutput.length - 1; i++) {
+    const firstFeature = locArrayOutput[i];
+    const secondFeature = locArrayOutput[i + 1];
+    if (
+      firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) &&
+      secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)
+    ) {
+      // Merge the two features
+      locArrayOutput[i] = {
+        start: firstFeature.start,
+        end: secondFeature.end
+      };
+      locArrayOutput.splice(i + 1, 1);
+    }
+  }
+  return locArrayOutput;
+}
+
 export function parseFeatureLocation(
   locStr,
   isProtein,
@@ -17,22 +51,37 @@ export function parseFeatureLocation(
   sequenceLength
 ) {
   locStr = locStr.trim();
-  const locArr = [];
-  locStr.replace(/(\d+)/g, function (string, match) {
-    locArr.push(match);
+  const positionsArray = [];
+  // Genbank feature locations can be:
+  // 4 -> single base (equivalent to 4..4)
+  // 4..8 -> range
+  // complement(4..8) -> complement of range
+  // join(4..8, 10..12) -> join of ranges
+  // complement(join(4..8, 10..12)) -> complement of join of ranges
+  // but also
+  // join(4, 10..12) -> join of single base and range
+  // First we split with commas to obtain pairs of positions
+  const locationParts = locStr.split(",");
+  locationParts.forEach(locPart => {
+    // Extract two integers from loc, if only one is present
+    // we push the same one as the end (e.g. if location is `4` we push
+    // 4 twice
+    const extractedPositions = locPart.match(/(\d+)/g);
+    // Sometimes the location is split between two lines and has a trailing comma
+    if (extractedPositions === null) {
+      return;
+    }
+    positionsArray.push(extractedPositions[0]);
+    positionsArray.push(extractedPositions[1] || extractedPositions[0]);
   });
+
   const locArray = [];
-  for (let i = 0; i < locArr.length; i += 2) {
-    const start = parseInt(locArr[i], 10) - (inclusive1BasedStart ? 0 : 1);
-    let end = parseInt(locArr[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
-    if (isNaN(end)) {
-      //if no end is supplied, assume that the end should be set to whatever the start is
-      //this makes a feature location passed as:
-      //147
-      //function like:
-      //147..147
-      end = start;
-    }
+  for (let i = 0; i < positionsArray.length; i += 2) {
+    const start =
+      parseInt(positionsArray[i], 10) - (inclusive1BasedStart ? 0 : 1);
+    const end =
+      parseInt(positionsArray[i + 1], 10) - (inclusive1BasedEnd ? 0 : 1);
+
     const location = {
       start: start,
       end: end
@@ -41,31 +90,21 @@ export function parseFeatureLocation(
       isProtein ? convertAACaretPositionOrRangeToDna(location) : location
     );
   }
-  // In genbank files, origin-spanning features are represented as follows:
-  // complement(join(490883..490885,1..879)) (for a circular sequence of length 490885)
-  // Then, for locations in locArray we check if there is a feature that ends at sequenceLength
-  // joined with a feature that starts at 1. If so, we merge them into a single feature.
-  // (see https://github.com/TeselaGen/tg-oss/issues/35)
 
-  if (isCircular) {
-    // Iterate by pairs of features
-    for (let i = 0; i < locArray.length; i += 2) {
-      const firstFeature = locArray[i];
-      const secondFeature = locArray[i + 1];
-      if (
-        firstFeature.end === sequenceLength - (inclusive1BasedEnd ? 0 : 1) &&
-        secondFeature.start === 1 - (inclusive1BasedStart ? 0 : 1)
-      ) {
-        // Merge the two features
-        locArray[i] = {
-          start: firstFeature.start,
-          end: secondFeature.end
-        };
-        locArray.splice(i + 1, 1);
-      }
-    }
+  // sequenceLength will not be set when this is called during genbank parsing,
+  // and the wrapping is done in endSeq > postProcessCurSeq > postProcessGenbankFeature
+  // However, this is useful if the function is used as a standalone parser of
+  // feature locations.
+  if (isCircular && sequenceLength) {
+    return wrapOriginSpanningFeatures(
+      locArray,
+      sequenceLength,
+      inclusive1BasedStart,
+      inclusive1BasedEnd
+    );
+  } else {
+    return locArray;
   }
-  return locArray;
 }
 
 function genbankToJson(string, options = {}) {
@@ -182,7 +221,7 @@ function genbankToJson(string, options = {}) {
           parseOrigin(line, key);
           break;
         case genbankAnnotationKey.END_SEQUENCE_TAG:
-          endSeq();
+          endSeq(options);
           break;
         case genbankAnnotationKey.DEFINITION_TAG:
           line = line.replace(/DEFINITION/, "");
@@ -321,10 +360,10 @@ function genbankToJson(string, options = {}) {
 
   return results;
 
-  function endSeq() {
+  function endSeq(options) {
     //do some post processing clean-up
     hasFoundLocus = false;
-    postProcessCurSeq();
+    postProcessCurSeq(options);
     //push the result into the resultsArray
     resultsArray.push(result || { success: false });
   }
@@ -341,11 +380,13 @@ function genbankToJson(string, options = {}) {
     }
   }
 
-  function postProcessCurSeq() {
+  function postProcessCurSeq(options) {
     if (result && result.parsedSequence && result.parsedSequence.features) {
       for (let i = 0; i < result.parsedSequence.features.length; i++) {
         result.parsedSequence.features[i] = postProcessGenbankFeature(
-          result.parsedSequence.features[i]
+          result.parsedSequence.features[i],
+          result.parsedSequence,
+          options
         );
       }
     }
@@ -656,7 +697,7 @@ function genbankToJson(string, options = {}) {
     return runon;
   }
 
-  function postProcessGenbankFeature(feat) {
+  function postProcessGenbankFeature(feat, parsedSequence, options) {
     if (feat.notes.label) {
       feat.name = feat.notes.label[0];
     } else if (feat.notes.gene) {
@@ -697,6 +738,16 @@ function genbankToJson(string, options = {}) {
             : undefined;
       delete feat.notes.direction;
     }
+    if (parsedSequence.circular) {
+      const { inclusive1BasedStart, inclusive1BasedEnd } = options;
+      feat.locations = wrapOriginSpanningFeatures(
+        feat.locations,
+        parsedSequence.sequence.length,
+        inclusive1BasedStart,
+        inclusive1BasedEnd
+      );
+    }
+
     return feat;
   }
 }