@teselagen/bio-parsers 0.3.8 → 0.3.10

package/src/gffToJson.js

@@ -6,7 +6,7 @@ function gffToJson(string) {
   const results = [];
   const sequences = [];
   const features = {};
-  arrayOfThings.forEach((featureOrSeq) => {
+  arrayOfThings.forEach(featureOrSeq => {
     if (featureOrSeq.sequence) {
       sequences.push(featureOrSeq);
     } else {
@@ -19,11 +19,11 @@ function gffToJson(string) {
         start: feature.start,
         end: feature.end,
         strand: feature.strand === "+" ? 1 : -1,
-        type: feature.type,
+        type: feature.type
       });
     }
   });
-  sequences.forEach((sequence) => {
+  sequences.forEach(sequence => {
     const sequenceId = sequence.id;
     const result = {
       messages: [],
@@ -32,8 +32,8 @@ function gffToJson(string) {
         name: sequenceId,
         sequence: sequence.sequence,
         circular: false,
-        features: features[sequence.id],
-      },
+        features: features[sequence.id]
+      }
     };
     results.push(result);
   });

package/src/jbeiXmlToJson.js

@@ -25,14 +25,14 @@ async function jbeiXmlToJson(string, options) {
     if (!jbeiSeq) {
       return onFileParsed({
         success: false,
-        messages: ["Error: XML is not valid jbei format"],
+        messages: ["Error: XML is not valid jbei format"]
       });
     }
 
     const response = {
       parsedSequence: null,
       messages: [],
-      success: true,
+      success: true
     };
     try {
       response.parsedSequence = parseJbeiXml(jbeiSeq, options);
@@ -42,21 +42,18 @@ async function jbeiXmlToJson(string, options) {
       console.error("error.stack: ", e.stack);
       resultArray.push({
         success: false,
-        messages: ["Error while parsing JBEI format"],
+        messages: ["Error while parsing JBEI format"]
       });
     }
 
-    const toRet = filter(
-      resultArray,
-      (r) => r?.parsedSequence?.sequence?.length
-    );
+    const toRet = filter(resultArray, r => r?.parsedSequence?.sequence?.length);
     if (toRet.length) return toRet;
     return onFileParsed(resultArray);
   } catch (e) {
     console.error(`e:`, e);
     return onFileParsed({
       success: false,
-      messages: ["Error parsing jbei to JSON"],
+      messages: ["Error parsing jbei to JSON"]
     });
   }
 }
@@ -65,7 +62,7 @@ function parseJbeiXml(jbeiJson) {
     "seq:sequence": sequence,
     "seq:name": name,
     "seq:circular": circular,
-    "seq:features": { "seq:feature": features },
+    "seq:features": { "seq:feature": features }
   } = jbeiJson;
   return {
     sequence,
@@ -76,7 +73,7 @@ function parseJbeiXml(jbeiJson) {
         "seq:complement": complement,
         "seq:label": label,
         "seq:type": type,
-        "seq:location": jbeiLocations,
+        "seq:location": jbeiLocations
       }) => {
         let start, end;
         const locs = Array.isArray(jbeiLocations)
@@ -88,7 +85,7 @@ function parseJbeiXml(jbeiJson) {
             if (i === locs.length - 1) end = normEnd - 1;
             return {
               start: gbStart - 1,
-              end: normEnd - 1,
+              end: normEnd - 1
             };
           }
         );
@@ -99,10 +96,10 @@ function parseJbeiXml(jbeiJson) {
           locations: locations.length > 1 ? locations : undefined,
           name: label,
           type,
-          strand: complement ? -1 : 1,
+          strand: complement ? -1 : 1
         };
       }
-    ),
+    )
   };
 }
 

package/src/jsonToBed.js

@@ -15,7 +15,7 @@ function jsonToBed(jsonSequence, options = {}) {
   let outString = "";
   outString += `track name="${sequenceNameToUse}" description="${name} Annotations" itemRgb="On"\n`;
 
-  features.forEach(function(feat) {
+  features.forEach(function (feat) {
     const { start, end, name, type, forward, strand } = feat;
     const label = name ? name : type;
     let orientation;
@@ -30,8 +30,9 @@ function jsonToBed(jsonSequence, options = {}) {
     const color = type === "CDS" ? "230,88,0" : "";
     // chromStart is 0-based, chromEnd of the BED file format is not included in the feature
     // when there is no thick part, thickStart and thickEnd are usually set to the chromStart position
-    outString += `${sequenceNameToUse}\t${start}\t${end +
-      1}\t${label}\t\t${orientation}\t\t\t${color}\n`;
+    outString += `${sequenceNameToUse}\t${start}\t${
+      end + 1
+    }\t${label}\t\t${orientation}\t\t\t${color}\n`;
   });
   return outString;
 }

package/src/jsonToFasta.js

@@ -11,7 +11,7 @@ export default function jsonToFasta(jsonSequence, options) {
     sequence,
     isProtein,
     proteinSize,
-    proteinSequence,
+    proteinSequence
   } = cleanedData;
 
   options = options || {};
@@ -25,7 +25,9 @@ export default function jsonToFasta(jsonSequence, options) {
   let fastaString = "";
   fastaString += `>${name || "Untitled Sequence"}|`;
   fastaString += "|" + sizeToUse;
-  fastaString += description ? "|" + mangleOrStripUrls(description, options) : "";
+  fastaString += description
+    ? "|" + mangleOrStripUrls(description, options)
+    : "";
   fastaString += "|" + (circular ? "circular" : "linear");
   fastaString += "\n";
   fastaString += (seqToUse.match(/.{1,80}/g) || []).join("\n");

package/src/jsonToGenbank.js

@@ -49,7 +49,7 @@ const StringUtil = {
     let str = line;
     while (str.length < length) str = str + padString;
     return str;
-  },
+  }
 };
 
 const DIGEST_PART_EXPORT_FIELD_MAP = {
@@ -64,7 +64,7 @@ const DIGEST_PART_EXPORT_FIELD_MAP = {
   "re3Prime.recognitionRegex": "re3PrimePattern",
   re3PrimeOverhang: "re3PrimeOverhang",
   re3PrimeOverhangStrand: "re3PrimeOverhangStrand",
-  re3PrimeRecognitionTypeCode: "re3PrimeRecognitionTypeCode",
+  re3PrimeRecognitionTypeCode: "re3PrimeRecognitionTypeCode"
 };
 
 function cutUpArray(val, start, end) {
@@ -129,7 +129,7 @@ export default function (_serSeq, options) {
 
     serSeq.features = map(serSeq.features).concat(
       flatMap(pragmasAndTypes, ({ pragma, type }) => {
-        return flatMap(serSeq[type], (ann) => {
+        return flatMap(serSeq[type], ann => {
           if (!isObject(ann)) {
             return [];
           }
@@ -142,7 +142,7 @@ export default function (_serSeq, options) {
           ann.notes = pragma
             ? {
                 ...ann.notes,
-                pragma: [pragma],
+                pragma: [pragma]
               }
             : ann.notes;
           return ann;
@@ -164,7 +164,7 @@ export default function (_serSeq, options) {
       lines.push(
         featureToGenbankString(feat, {
           ...options,
-          featurePadLength: longestFeatureTypeLength + 1,
+          featurePadLength: longestFeatureTypeLength + 1
         })
       );
     });
@@ -200,22 +200,23 @@ function createGenbankLocus(serSeq, options) {
     serSeq.sequence = serSeq.sequence.symbols.split("");
   }
 
-  let tmp;
   let dnaType;
   if (serSeq.isProtein) {
     dnaType = "";
   } else if (serSeq.type === "RNA") {
-    dnaType = serSeq?.doubleStranded ? 'RNA' : serSeq?.sequenceTypeFromLocus ?? "ss-RNA";
+    dnaType = serSeq?.doubleStranded
+      ? "RNA"
+      : serSeq?.sequenceTypeFromLocus ?? "ss-RNA";
   } else {
-    dnaType = serSeq?.doubleStranded ? 'DNA' : serSeq?.sequenceTypeFromLocus ?? "DNA";
+    dnaType = serSeq?.doubleStranded
+      ? "DNA"
+      : serSeq?.sequenceTypeFromLocus ?? "DNA";
   }
   const date = getCurrentDateString();
 
   let line = StringUtil.rpad("LOCUS", " ", 12);
   let nameToUse = serSeq.name || "Untitled_Sequence";
-  nameToUse = options.reformatSeqName
-    ? reformatName(nameToUse)
-    : nameToUse;
+  nameToUse = options.reformatSeqName ? reformatName(nameToUse) : nameToUse;
   line += StringUtil.rpad(nameToUse, " ", 16);
   line += " "; // T.H line 2778 of GenbankFormat.as col 29 space
   line += StringUtil.lpad(String(serSeq.sequence.length), " ", 11);
@@ -223,7 +224,7 @@ function createGenbankLocus(serSeq, options) {
   // if (strandType !== "") {
   // 	tmp =  strandType + "-";
   // } else {
-  tmp = "";
+  const tmp = "";
   // }
   line += StringUtil.lpad(tmp, " ", 3);
   line += StringUtil.rpad(dnaType, " ", 6);

package/src/jsonToJsonString.js

@@ -1,6 +1,6 @@
 import { omit } from "lodash";
 
-import cleanUpTeselagenJsonForExport from "./utils/cleanUpTeselagenJsonForExport"
+import cleanUpTeselagenJsonForExport from "./utils/cleanUpTeselagenJsonForExport";
 import { tidyUpSequenceData } from "@teselagen/sequence-utils";
 
 /**

package/src/sbolXmlToJson.js

@@ -2,7 +2,7 @@
 import validateSequenceArray from "./utils/validateSequenceArray";
 import searchWholeObjByName, {
   searchWholeObjByNameSimple,
-  searchWholeObjByNameSimpleArray,
+  searchWholeObjByNameSimpleArray
 } from "./utils/searchWholeObjByName";
 
 import { XMLParser } from "fast-xml-parser";
@@ -23,12 +23,12 @@ async function sbolXmlToJson(string, options) {
   let response = {
     parsedSequence: null,
     messages: [],
-    success: true,
+    success: true
   };
   try {
     const result = new XMLParser({
       isArray: () => true,
-      ignoreAttributes: false,
+      ignoreAttributes: false
     }).parse(string);
     const sbolJsonMatches = searchWholeObjByName("DnaComponent", result);
     if (sbolJsonMatches[0]) {
@@ -38,7 +38,7 @@ async function sbolXmlToJson(string, options) {
           response = {
             parsedSequence: null,
             messages: [],
-            success: true,
+            success: true
           };
           response.parsedSequence = parseSbolJson(
             sbolJsonMatches[0].value[i],
@@ -49,7 +49,7 @@ async function sbolXmlToJson(string, options) {
           console.error("error.stack: ", e.stack);
           resultArray.push({
             success: false,
-            messages: ["Error while parsing Sbol format"],
+            messages: ["Error while parsing Sbol format"]
           });
         }
         if (response.parsedSequence.features.length > 0) {
@@ -63,13 +63,13 @@ async function sbolXmlToJson(string, options) {
     } else {
       return onFileParsed({
         success: false,
-        messages: ["Error: XML is not valid Jbei or Sbol format"],
+        messages: ["Error: XML is not valid Jbei or Sbol format"]
       });
     }
   } catch (e) {
     return onFileParsed({
       success: false,
-      messages: ["Error parsing XML to JSON"],
+      messages: ["Error parsing XML to JSON"]
     });
   }
 }
@@ -124,11 +124,11 @@ function parseSbolJson(sbolJson, options) {
           end: parseInt(
             get(feature, "bioEnd[0]") - (options.inclusive1BasedEnd ? 0 : 1)
           ),
-          strand: get(feature, "strand[0]"), //+ or -
+          strand: get(feature, "strand[0]") //+ or -
           // notes: feature['seq:label'],
         };
       }
-    }),
+    })
   };
 }
 

package/src/snapgeneToJson.js

@@ -13,7 +13,7 @@ import { get } from "lodash";
 import { XMLParser } from "fast-xml-parser";
 import extractFileExtension from "./utils/extractFileExtension";
 
-const Buffer = buffer.Buffer
+const Buffer = buffer.Buffer;
 
 async function snapgeneToJson(fileObj, options = {}) {
   try {
@@ -59,7 +59,7 @@ async function snapgeneToJson(fileObj, options = {}) {
       isDNA: !!(await unpack(2, "H")) && !isProtein,
       exportVersion: await unpack(2, "H"),
       importVersion: await unpack(2, "H"),
-      features: [],
+      features: []
     };
     while (offset <= arrayBuffer.byteLength) {
       // # READ THE WHOLE FILE, BLOCK BY BLOCK, UNTIL THE END
@@ -109,24 +109,24 @@ async function snapgeneToJson(fileObj, options = {}) {
           0: [1, "NONE"], // non-directional feature (in that case, the attribute is generally absent altogether)
           1: [1, "TOP"], // forward strand
           2: [-1, "BOTTOM"], // reverse strand
-          3: [1, "BOTH"], // bi-directional feature
+          3: [1, "BOTH"] // bi-directional feature
         };
         const xml = await read(block_size, "utf8");
         const b = new XMLParser({
           ignoreAttributes: false,
           attributeNamePrefix: "",
-          isArray: (name) => name === "Feature" || name === "Segment",
+          isArray: name => name === "Feature" || name === "Segment"
         }).parse(xml);
         const { Features: { Feature = [] } = {} } = b;
         data.features = [];
-        Feature.forEach((feat) => {
+        Feature.forEach(feat => {
           const { directionality, Segment = [], name, type } = feat;
           // let color;
           let maxStart = 0;
           let maxEnd = 0;
           const locations =
             Segment &&
-            Segment.map((seg) => {
+            Segment.map(seg => {
               if (!seg) throw new Error("invalid feature definition");
               const { range } = seg;
               // color = seg.color;
@@ -137,7 +137,7 @@ async function snapgeneToJson(fileObj, options = {}) {
               maxEnd = Math.max(maxEnd, end);
               return {
                 start,
-                end,
+                end
               };
             });
 
@@ -146,9 +146,11 @@ async function snapgeneToJson(fileObj, options = {}) {
             type,
             ...(locations?.length > 1 && { locations }),
             strand: directionality ? strand_dict[directionality][0] : 1,
-            arrowheadType: directionality ? strand_dict[directionality][1] : "NONE",
+            arrowheadType: directionality
+              ? strand_dict[directionality][1]
+              : "NONE",
             start: maxStart,
-            end: maxEnd,
+            end: maxEnd
             // color,
           });
         });
@@ -183,8 +185,8 @@ async function snapgeneToJson(fileObj, options = {}) {
     return [
       {
         success: false,
-        messages: ["Import Error: Invalid File"],
-      },
+        messages: ["Import Error: Invalid File"]
+      }
     ];
   }
 }
@@ -193,7 +195,7 @@ function getStartAndEndFromRangeString(rangestring) {
   const [start, end] = rangestring.split("-");
   return {
     start: start - 1,
-    end: end - 1,
+    end: end - 1
   };
 }
 

package/src/utils/NameUtils.js

@@ -6,5 +6,5 @@
  * @returns {string} New name.
  */
 export const reformatName = function (pName) {
-  return pName.toString().replace(/ /g, '_');
+  return pName.toString().replace(/ /g, "_");
 };

package/src/utils/ParserUtil.js

@@ -1,93 +1,91 @@
 const ParserUtil = {};
-ParserUtil.postProcessGenbankFeature = function(feat) {
-	let name = null;
-	// let nameIndex = null;
-
-	// let hasName = false;
-	let usingLabel = false;
-	let usingGene = false;
-
-	for (let j = 0; j < feat.notes.length; j++) {
-		const note = feat.notes[j];
-		const key = note.name;
-		const value = note.value;
-
-		// SET THE LABEL FIELD. DO NOT STORE AS AN ATTRIBUTE
-
-		if (this.isAGenbankFeatureLabel(key)) {
-			// Priority for name attributes is: 'label' > 'gene' > 'organism'.
-			// We check to see if the current name is from a lower-priority
-			// attribute. If it is, we store it as an attribute and then
-			// replace it with the current higher-priority attribute.
-
-			if (key === "label") {
-				// Label has top priority.
-
-				name = value;
-				// nameIndex = j;
-
-				usingLabel = true;
-			}
-			else if (key === "gene") {
-
-				// If we're not using the label for the name, use the
-				// current 'gene' attribute. If we are using label for
-				// the name, just save the current attribute as a normal
-				// attribute.
-				if (!usingLabel) {
-
-					name = value;
-					// nameIndex = j;
-
-					usingGene = true;
-				}
-			}
-			else if (!usingLabel && !usingGene) {
-				// If we don't have a label from either a 'gene' or a
-				// 'label' field, use the current field as the name.
-
-				name = value;
-				// nameIndex = j;
-
-			}
-
-			// hasName = true;
-		}
-	}
-
-	feat.name = name || "";
-	// if(nameIndex !== null) {
-	// 	feat.notes.splice(nameIndex, 1);
-	// }
-	//
-	// if(feat.locations.length > 0) {
-	// 	var loc = feat.locations[0];
-	// 	feat.start = loc.start;
-	// 	feat.end = loc.end;
-	// }
-	// else {
-	// 	feat.start = null;
-	// 	feat.end = null;
-	// }
-
-	return feat;
+ParserUtil.postProcessGenbankFeature = function (feat) {
+  let name = null;
+  // let nameIndex = null;
+
+  // let hasName = false;
+  let usingLabel = false;
+  let usingGene = false;
+
+  for (let j = 0; j < feat.notes.length; j++) {
+    const note = feat.notes[j];
+    const key = note.name;
+    const value = note.value;
+
+    // SET THE LABEL FIELD. DO NOT STORE AS AN ATTRIBUTE
+
+    if (this.isAGenbankFeatureLabel(key)) {
+      // Priority for name attributes is: 'label' > 'gene' > 'organism'.
+      // We check to see if the current name is from a lower-priority
+      // attribute. If it is, we store it as an attribute and then
+      // replace it with the current higher-priority attribute.
+
+      if (key === "label") {
+        // Label has top priority.
+
+        name = value;
+        // nameIndex = j;
+
+        usingLabel = true;
+      } else if (key === "gene") {
+        // If we're not using the label for the name, use the
+        // current 'gene' attribute. If we are using label for
+        // the name, just save the current attribute as a normal
+        // attribute.
+        if (!usingLabel) {
+          name = value;
+          // nameIndex = j;
+
+          usingGene = true;
+        }
+      } else if (!usingLabel && !usingGene) {
+        // If we don't have a label from either a 'gene' or a
+        // 'label' field, use the current field as the name.
+
+        name = value;
+        // nameIndex = j;
+      }
+
+      // hasName = true;
+    }
+  }
+
+  feat.name = name || "";
+  // if(nameIndex !== null) {
+  // 	feat.notes.splice(nameIndex, 1);
+  // }
+  //
+  // if(feat.locations.length > 0) {
+  // 	var loc = feat.locations[0];
+  // 	feat.start = loc.start;
+  // 	feat.end = loc.end;
+  // }
+  // else {
+  // 	feat.start = null;
+  // 	feat.end = null;
+  // }
+
+  return feat;
 };
 
-
-
 /**
  * isAFeatureLabel
  * @param {string} name Name of a attribute or qualifier
  * @return {boolean} isALabel
  */
-ParserUtil.isAGenbankFeatureLabel = function(name) {
-	if (name === "label" || name === "name" || name === "ApEinfo_label" ||
-		name === "note" || name === "gene" || name === "organism" || name === "locus_tag") {
-
-		return true;
-	}
-	else {
-		return false;
-	}
+ParserUtil.isAGenbankFeatureLabel = function (name) {
+  if (
+    name === "label" ||
+    name === "name" ||
+    name === "ApEinfo_label" ||
+    name === "note" ||
+    name === "gene" ||
+    name === "organism" ||
+    name === "locus_tag"
+  ) {
+    return true;
+  } else {
+    return false;
+  }
 };
 export default ParserUtil;

package/src/utils/cleanUpTeselagenJsonForExport.js

@@ -1,13 +1,12 @@
 import { cloneDeep, forEach } from "lodash";
 
 export default function cleanUpTeselagenJsonForExport(tgJson) {
-	const seqData = cloneDeep(tgJson);
-	if (!seqData) return seqData
-	delete seqData.cutsites;
-	delete seqData.orfs;
-	forEach(seqData.translations,(t)=>{
-		delete t.aminoAcids
-	})
-	return seqData
+  const seqData = cloneDeep(tgJson);
+  if (!seqData) return seqData;
+  delete seqData.cutsites;
+  delete seqData.orfs;
+  forEach(seqData.translations, t => {
+    delete t.aminoAcids;
+  });
+  return seqData;
 }
-

package/src/utils/constants.js

@@ -1,24 +1,24 @@
-export const untitledSequenceName = 'Untitled Sequence';
+export const untitledSequenceName = "Untitled Sequence";
 
 export const gbDivisions = {
-    // https://www.ncbi.nlm.nih.gov/Sitemap/samplerecord.html#GenBankDivisionB
-    PRI: true,  //- primate sequences
-    ROD: true,  //- rodent sequences
-    MAM: true,  //- other mammalian sequences
-    VRT: true,  //- other vertebrate sequences
-    INV: true,  //- invertebrate sequences
-    PLN: true,  //- plant, fungal, and algal sequences
-    BCT: true,  //- bacterial sequences
-    VRL: true,  //- viral sequences
-    PHG: true,  //- bacteriophage sequences
-    SYN: true,  //- synthetic sequences
-    UNA: true,  //- unannotated sequences
-    EST: true,  //- EST sequences (expressed sequence tags)
-    PAT: true,  //- patent sequences
-    STS: true,  //- STS sequences (sequence tagged sites)
-    GSS: true,  //- GSS sequences (genome survey sequences)
-    HTG: true,  //- HTG sequences (high-throughput genomic sequences)
-    HTC: true,  //- unfinished high-throughput cDNA sequencing
-    ENV: true,  //- environmental sampling sequences
-    CON: true,  //- sequence assembly instructions on how to construct contigs from multiple GenBank records.
-  }
+  // https://www.ncbi.nlm.nih.gov/Sitemap/samplerecord.html#GenBankDivisionB
+  PRI: true, //- primate sequences
+  ROD: true, //- rodent sequences
+  MAM: true, //- other mammalian sequences
+  VRT: true, //- other vertebrate sequences
+  INV: true, //- invertebrate sequences
+  PLN: true, //- plant, fungal, and algal sequences
+  BCT: true, //- bacterial sequences
+  VRL: true, //- viral sequences
+  PHG: true, //- bacteriophage sequences
+  SYN: true, //- synthetic sequences
+  UNA: true, //- unannotated sequences
+  EST: true, //- EST sequences (expressed sequence tags)
+  PAT: true, //- patent sequences
+  STS: true, //- STS sequences (sequence tagged sites)
+  GSS: true, //- GSS sequences (genome survey sequences)
+  HTG: true, //- HTG sequences (high-throughput genomic sequences)
+  HTC: true, //- unfinished high-throughput cDNA sequencing
+  ENV: true, //- environmental sampling sequences
+  CON: true //- sequence assembly instructions on how to construct contigs from multiple GenBank records.
+};