@teselagen/bio-parsers 0.3.3 → 0.3.5

package/index.js

@@ -19285,9 +19285,7 @@ const reformatName = /* @__PURE__ */ __name(function(pName) {
   return pName.toString().replace(/ /g, "_");
 }, "reformatName");
 function validateSequence(sequence, options = {}) {
-  let {
-    isProtein,
-    isOligo,
+  const {
     guessIfProtein,
     guessIfProteinOptions,
     reformatSeqName,
@@ -19297,6 +19295,19 @@ function validateSequence(sequence, options = {}) {
     allowOverflowAnnotations,
     coerceFeatureTypes
   } = options;
+  [
+    "isDNA",
+    "isOligo",
+    "isRNA",
+    "isDoubleStrandedDNA",
+    "isSingleStrandedDNA",
+    "isDoubleStrandedRNA",
+    "isProtein"
+  ].forEach((k) => {
+    if (options[k] !== void 0 && sequence[k] === void 0) {
+      sequence[k] = options[k];
+    }
+  });
   const response = {
     validatedAndCleanedSequence: {},
     messages: []
@@ -19333,13 +19344,13 @@ function validateSequence(sequence, options = {}) {
     sequence.sequence = "";
   }
   let validChars;
-  if (isProtein === void 0 && guessIfProtein) {
-    isProtein = !guessIfSequenceIsDnaAndNotProtein(
+  if (sequence.isProtein === void 0 && guessIfProtein) {
+    sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
       guessIfProteinOptions
     );
   }
-  if (isProtein) {
+  if (sequence.isProtein) {
     validChars = filterAminoAcidSequenceString(sequence.sequence);
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
@@ -19355,14 +19366,15 @@ function validateSequence(sequence, options = {}) {
     sequence.proteinSize = sequence.proteinSequence.length;
   } else {
     const temp = sequence.sequence;
-    if (!isOligo) {
+    if (!sequence.isOligo) {
       sequence.sequence = sequence.sequence.replace(
         /u/gi,
         (u) => u === "U" ? "T" : "t"
       );
     }
-    if (temp !== sequence.sequence) {
+    if (temp !== sequence.sequence && !sequence.isDNA && !sequence.isProtein) {
       sequence.type = "RNA";
+      sequence.sequence = temp;
     } else {
       sequence.type = "DNA";
     }
@@ -19375,7 +19387,7 @@ function validateSequence(sequence, options = {}) {
     }
   }
   if (!sequence.size) {
-    sequence.size = isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
+    sequence.size = sequence.isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
   }
   let circularityExplicitlyDefined;
   if (sequence.circular === false || sequence.circular === "false" || sequence.circular === -1) {
@@ -19948,7 +19960,13 @@ function genbankToJson(string, options = {}) {
         }
         options.sequenceTypeFromLocus = item;
         if (item.match(/ss-dna/i)) {
+          options.isDNA = true;
           options.isSingleStrandedDNA = true;
+        } else if (item.match(/rna/i)) {
+          options.isRna = true;
+        } else if (item.match(/ds-dna/i) || item.match(/dna/i)) {
+          options.isDNA = true;
+          options.isDoubleStrandedDNA = true;
         }
         if (item.match(/rna/i) && !item.match(/ss-rna/i)) {
           options.isDoubleStrandedRNA = true;
@@ -19963,7 +19981,10 @@ function genbankToJson(string, options = {}) {
     }
     result.parsedSequence.gbDivision = gbDivision;
     result.parsedSequence.sequenceTypeFromLocus = options.sequenceTypeFromLocus;
+    result.parsedSequence.isDNA = options.isDNA;
+    result.parsedSequence.isDoubleStrandedDNA = options.isDoubleStrandedDNA;
     result.parsedSequence.isSingleStrandedDNA = options.isSingleStrandedDNA;
+    result.parsedSequence.isRna = options.isRna;
     result.parsedSequence.isDoubleStrandedRNA = options.isDoubleStrandedRNA;
     result.parsedSequence.date = date;
     result.parsedSequence.circular = circular;

package/index.mjs

@@ -19283,9 +19283,7 @@ const reformatName = /* @__PURE__ */ __name(function(pName) {
   return pName.toString().replace(/ /g, "_");
 }, "reformatName");
 function validateSequence(sequence, options = {}) {
-  let {
-    isProtein,
-    isOligo,
+  const {
     guessIfProtein,
     guessIfProteinOptions,
     reformatSeqName,
@@ -19295,6 +19293,19 @@ function validateSequence(sequence, options = {}) {
     allowOverflowAnnotations,
     coerceFeatureTypes
   } = options;
+  [
+    "isDNA",
+    "isOligo",
+    "isRNA",
+    "isDoubleStrandedDNA",
+    "isSingleStrandedDNA",
+    "isDoubleStrandedRNA",
+    "isProtein"
+  ].forEach((k) => {
+    if (options[k] !== void 0 && sequence[k] === void 0) {
+      sequence[k] = options[k];
+    }
+  });
   const response = {
     validatedAndCleanedSequence: {},
     messages: []
@@ -19331,13 +19342,13 @@ function validateSequence(sequence, options = {}) {
     sequence.sequence = "";
   }
   let validChars;
-  if (isProtein === void 0 && guessIfProtein) {
-    isProtein = !guessIfSequenceIsDnaAndNotProtein(
+  if (sequence.isProtein === void 0 && guessIfProtein) {
+    sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
       guessIfProteinOptions
     );
   }
-  if (isProtein) {
+  if (sequence.isProtein) {
     validChars = filterAminoAcidSequenceString(sequence.sequence);
     if (validChars !== sequence.sequence) {
       sequence.sequence = validChars;
@@ -19353,14 +19364,15 @@ function validateSequence(sequence, options = {}) {
     sequence.proteinSize = sequence.proteinSequence.length;
   } else {
     const temp = sequence.sequence;
-    if (!isOligo) {
+    if (!sequence.isOligo) {
       sequence.sequence = sequence.sequence.replace(
         /u/gi,
         (u) => u === "U" ? "T" : "t"
       );
     }
-    if (temp !== sequence.sequence) {
+    if (temp !== sequence.sequence && !sequence.isDNA && !sequence.isProtein) {
       sequence.type = "RNA";
+      sequence.sequence = temp;
     } else {
       sequence.type = "DNA";
     }
@@ -19373,7 +19385,7 @@ function validateSequence(sequence, options = {}) {
     }
   }
   if (!sequence.size) {
-    sequence.size = isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
+    sequence.size = sequence.isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
   }
   let circularityExplicitlyDefined;
   if (sequence.circular === false || sequence.circular === "false" || sequence.circular === -1) {
@@ -19946,7 +19958,13 @@ function genbankToJson(string, options = {}) {
         }
         options.sequenceTypeFromLocus = item;
         if (item.match(/ss-dna/i)) {
+          options.isDNA = true;
           options.isSingleStrandedDNA = true;
+        } else if (item.match(/rna/i)) {
+          options.isRna = true;
+        } else if (item.match(/ds-dna/i) || item.match(/dna/i)) {
+          options.isDNA = true;
+          options.isDoubleStrandedDNA = true;
         }
         if (item.match(/rna/i) && !item.match(/ss-rna/i)) {
           options.isDoubleStrandedRNA = true;
@@ -19961,7 +19979,10 @@ function genbankToJson(string, options = {}) {
     }
     result.parsedSequence.gbDivision = gbDivision;
     result.parsedSequence.sequenceTypeFromLocus = options.sequenceTypeFromLocus;
+    result.parsedSequence.isDNA = options.isDNA;
+    result.parsedSequence.isDoubleStrandedDNA = options.isDoubleStrandedDNA;
     result.parsedSequence.isSingleStrandedDNA = options.isSingleStrandedDNA;
+    result.parsedSequence.isRna = options.isRna;
     result.parsedSequence.isDoubleStrandedRNA = options.isDoubleStrandedRNA;
     result.parsedSequence.date = date;
     result.parsedSequence.circular = circular;

package/index.umd.js

@@ -19287,9 +19287,7 @@ var __async = (__this, __arguments, generator) => {
     return pName.toString().replace(/ /g, "_");
   }, "reformatName");
   function validateSequence(sequence, options = {}) {
-    let {
-      isProtein,
-      isOligo,
+    const {
       guessIfProtein,
       guessIfProteinOptions,
       reformatSeqName,
@@ -19299,6 +19297,19 @@ var __async = (__this, __arguments, generator) => {
       allowOverflowAnnotations,
       coerceFeatureTypes
     } = options;
+    [
+      "isDNA",
+      "isOligo",
+      "isRNA",
+      "isDoubleStrandedDNA",
+      "isSingleStrandedDNA",
+      "isDoubleStrandedRNA",
+      "isProtein"
+    ].forEach((k) => {
+      if (options[k] !== void 0 && sequence[k] === void 0) {
+        sequence[k] = options[k];
+      }
+    });
     const response = {
       validatedAndCleanedSequence: {},
       messages: []
@@ -19335,13 +19346,13 @@ var __async = (__this, __arguments, generator) => {
       sequence.sequence = "";
     }
     let validChars;
-    if (isProtein === void 0 && guessIfProtein) {
-      isProtein = !guessIfSequenceIsDnaAndNotProtein(
+    if (sequence.isProtein === void 0 && guessIfProtein) {
+      sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
         sequence.sequence,
         guessIfProteinOptions
       );
     }
-    if (isProtein) {
+    if (sequence.isProtein) {
       validChars = filterAminoAcidSequenceString(sequence.sequence);
       if (validChars !== sequence.sequence) {
         sequence.sequence = validChars;
@@ -19357,14 +19368,15 @@ var __async = (__this, __arguments, generator) => {
       sequence.proteinSize = sequence.proteinSequence.length;
     } else {
       const temp = sequence.sequence;
-      if (!isOligo) {
+      if (!sequence.isOligo) {
         sequence.sequence = sequence.sequence.replace(
           /u/gi,
           (u) => u === "U" ? "T" : "t"
         );
       }
-      if (temp !== sequence.sequence) {
+      if (temp !== sequence.sequence && !sequence.isDNA && !sequence.isProtein) {
         sequence.type = "RNA";
+        sequence.sequence = temp;
       } else {
         sequence.type = "DNA";
       }
@@ -19377,7 +19389,7 @@ var __async = (__this, __arguments, generator) => {
       }
     }
     if (!sequence.size) {
-      sequence.size = isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
+      sequence.size = sequence.isProtein ? sequence.proteinSequence.length * 3 : sequence.sequence.length;
     }
     let circularityExplicitlyDefined;
     if (sequence.circular === false || sequence.circular === "false" || sequence.circular === -1) {
@@ -19950,7 +19962,13 @@ var __async = (__this, __arguments, generator) => {
           }
           options.sequenceTypeFromLocus = item;
           if (item.match(/ss-dna/i)) {
+            options.isDNA = true;
             options.isSingleStrandedDNA = true;
+          } else if (item.match(/rna/i)) {
+            options.isRna = true;
+          } else if (item.match(/ds-dna/i) || item.match(/dna/i)) {
+            options.isDNA = true;
+            options.isDoubleStrandedDNA = true;
           }
           if (item.match(/rna/i) && !item.match(/ss-rna/i)) {
             options.isDoubleStrandedRNA = true;
@@ -19965,7 +19983,10 @@ var __async = (__this, __arguments, generator) => {
       }
       result.parsedSequence.gbDivision = gbDivision;
       result.parsedSequence.sequenceTypeFromLocus = options.sequenceTypeFromLocus;
+      result.parsedSequence.isDNA = options.isDNA;
+      result.parsedSequence.isDoubleStrandedDNA = options.isDoubleStrandedDNA;
       result.parsedSequence.isSingleStrandedDNA = options.isSingleStrandedDNA;
+      result.parsedSequence.isRna = options.isRna;
       result.parsedSequence.isDoubleStrandedRNA = options.isDoubleStrandedRNA;
       result.parsedSequence.date = date;
       result.parsedSequence.circular = circular;

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@teselagen/bio-parsers",
-  "version": "0.3.3",
+  "version": "0.3.5",
   "type": "commonjs",
   "dependencies": {
-    "@teselagen/sequence-utils": "0.3.3",
-    "@teselagen/range-utils": "0.3.3",
+    "@teselagen/sequence-utils": "0.3.5",
+    "@teselagen/range-utils": "0.3.5",
     "@gmod/gff": "^1.2.1",
     "buffer": "^6.0.3",
     "bufferpack": "^0.0.6",

package/src/genbankToJson.js

@@ -1,7 +1,7 @@
 /* eslint-disable no-var*/
 import { convertAACaretPositionOrRangeToDna } from "@teselagen/sequence-utils";
 
-import  { gbDivisions, untitledSequenceName } from "./utils/constants";
+import { gbDivisions, untitledSequenceName } from "./utils/constants";
 import flattenSequenceArray from "./utils/flattenSequenceArray";
 import validateSequenceArray from "./utils/validateSequenceArray";
 import splitStringIntoLines from "./utils/splitStringIntoLines.js";
@@ -11,7 +11,7 @@ import createInitialSequence from "./utils/createInitialSequence";
 function genbankToJson(string, options = {}) {
   const {
     inclusive1BasedStart,
-    inclusive1BasedEnd,
+    inclusive1BasedEnd
     //these are also valid options:
     // primersAsFeatures,
     // sequenceTypeFromLocus,
@@ -43,7 +43,7 @@ function genbankToJson(string, options = {}) {
     BASE_COUNT_TAG: "BASE COUNT",
     //CONTIG_TAG: "CONTIG"
     ORIGIN_TAG: "ORIGIN",
-    END_SEQUENCE_TAG: "//",
+    END_SEQUENCE_TAG: "//"
   };
   let hasFoundLocus = false;
   let featureLocationIndentation;
@@ -214,7 +214,7 @@ function genbankToJson(string, options = {}) {
     console.error("Error trying to parse file as .gb:", e);
     result = {
       success: false,
-      messages: ["Import Error: Invalid File"],
+      messages: ["Import Error: Invalid File"]
     };
   }
 
@@ -338,15 +338,25 @@ function genbankToJson(string, options = {}) {
 
       if (
         j === 4 &&
-        (item.match(/ds-dna/i) || item.match(/ss-dna/i) || item.match(/dna/i) || item.match(/rna/i))
+        (item.match(/ds-dna/i) ||
+          item.match(/ss-dna/i) ||
+          item.match(/dna/i) ||
+          item.match(/rna/i))
       ) {
         if (options.isProtein === undefined) {
           options.isProtein = false;
         }
         options.sequenceTypeFromLocus = item;
         if (item.match(/ss-dna/i)) {
+          options.isDNA = true;
           options.isSingleStrandedDNA = true;
+        } else if (item.match(/rna/i)) {
+          options.isRna = true;
+        } else if (item.match(/ds-dna/i) || item.match(/dna/i)) {
+          options.isDNA = true;
+          options.isDoubleStrandedDNA = true;
         }
+
         if (item.match(/rna/i) && !item.match(/ss-rna/i)) {
           options.isDoubleStrandedRNA = true;
         }
@@ -370,7 +380,10 @@ function genbankToJson(string, options = {}) {
     }
     result.parsedSequence.gbDivision = gbDivision;
     result.parsedSequence.sequenceTypeFromLocus = options.sequenceTypeFromLocus;
+    result.parsedSequence.isDNA = options.isDNA;
+    result.parsedSequence.isDoubleStrandedDNA = options.isDoubleStrandedDNA;
     result.parsedSequence.isSingleStrandedDNA = options.isSingleStrandedDNA;
+    result.parsedSequence.isRna = options.isRna;
     result.parsedSequence.isDoubleStrandedRNA = options.isDoubleStrandedRNA;
     result.parsedSequence.date = date;
     result.parsedSequence.circular = circular;
@@ -462,7 +475,7 @@ function genbankToJson(string, options = {}) {
   function newFeature() {
     result.parsedSequence.features.push({
       locations: [],
-      notes: {},
+      notes: {}
     });
   }
 
@@ -500,7 +513,7 @@ function genbankToJson(string, options = {}) {
       }
       const location = {
         start: start,
-        end: end,
+        end: end
       };
       const feat = getCurrentFeature();
       feat.locations.push(

package/src/utils/validateSequence.js

@@ -3,7 +3,7 @@ import { getFeatureTypes } from "@teselagen/sequence-utils";
 import {
   filterAminoAcidSequenceString,
   filterSequenceString,
-  guessIfSequenceIsDnaAndNotProtein,
+  guessIfSequenceIsDnaAndNotProtein
 } from "@teselagen/sequence-utils";
 import { filter, some, upperFirst } from "lodash";
 import pragmasAndTypes from "./pragmasAndTypes.js";
@@ -22,9 +22,7 @@ import { reformatName } from "./NameUtils.js";
   };
  */
 export default function validateSequence(sequence, options = {}) {
-  let {
-    isProtein,
-    isOligo,
+  const {
     guessIfProtein,
     guessIfProteinOptions,
     reformatSeqName,
@@ -32,11 +30,25 @@ export default function validateSequence(sequence, options = {}) {
     inclusive1BasedEnd,
     additionalValidChars,
     allowOverflowAnnotations,
-    coerceFeatureTypes,
+    coerceFeatureTypes
   } = options;
+  [
+    "isDNA",
+    "isOligo",
+    "isRNA",
+    "isDoubleStrandedDNA",
+    "isSingleStrandedDNA",
+    "isDoubleStrandedRNA",
+    "isProtein"
+  ].forEach((k) => {
+    if (options[k] !== undefined && sequence[k] === undefined) {
+      sequence[k] = options[k];
+    }
+  });
+
   const response = {
     validatedAndCleanedSequence: {},
-    messages: [],
+    messages: []
   };
   if (!sequence || typeof sequence !== "object") {
     throw new Error("Invalid sequence");
@@ -73,13 +85,13 @@ export default function validateSequence(sequence, options = {}) {
     sequence.sequence = "";
   }
   let validChars;
-  if (isProtein === undefined && guessIfProtein) {
-    isProtein = !guessIfSequenceIsDnaAndNotProtein(
+  if (sequence.isProtein === undefined && guessIfProtein) {
+    sequence.isProtein = !guessIfSequenceIsDnaAndNotProtein(
       sequence.sequence,
       guessIfProteinOptions
     );
   }
-  if (isProtein) {
+  if (sequence.isProtein) {
     //tnr: add code to strip invalid protein data..
     validChars = filterAminoAcidSequenceString(sequence.sequence);
     if (validChars !== sequence.sequence) {
@@ -97,13 +109,14 @@ export default function validateSequence(sequence, options = {}) {
   } else {
     //todo: this logic won't catch every case of RNA, so we should probably handle RNA conversion at another level..
     const temp = sequence.sequence;
-    if (!isOligo) {
+    if (!sequence.isOligo) {
       sequence.sequence = sequence.sequence.replace(/u/gi, (u) =>
         u === "U" ? "T" : "t"
       );
     }
-    if (temp !== sequence.sequence) {
+    if (temp !== sequence.sequence && !sequence.isDNA && !sequence.isProtein) {
       sequence.type = "RNA";
+      sequence.sequence = temp;
     } else {
       sequence.type = "DNA";
     }
@@ -118,7 +131,7 @@ export default function validateSequence(sequence, options = {}) {
   }
 
   if (!sequence.size) {
-    sequence.size = isProtein
+    sequence.size = sequence.isProtein
       ? sequence.proteinSequence.length * 3
       : sequence.sequence.length;
   }