@teselagen/sequence-utils 0.3.18 → 0.3.20

package/bioData.d.ts

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

package/calculateTm.d.ts

@@ -1,2 +1,2 @@
-declare function _default(sequence: string, type: string, A: Double, R: Double, C: any, Na: Double): Double;
+declare function _default(sequence: any, type: any, A: any, R: any, C: any, Na: any): string | 0;
 export default _default;

package/findOrfsInPlasmid.d.ts

@@ -1 +1,11 @@
-export default function findOrfsInPlasmid(sequence: any, circular: any, minimumOrfSize: any, useAdditionalOrfStartCodons: any): Teselagen.bio.orf.ORF[];
+export default function findOrfsInPlasmid(sequence: any, circular: any, minimumOrfSize: any, useAdditionalOrfStartCodons: any): {
+    start: number;
+    end: number;
+    length: number;
+    internalStartCodonIndices: never[];
+    frame: number;
+    forward: any;
+    annotationTypePlural: string;
+    isOrf: boolean;
+    id: any;
+}[];

package/getOrfsFromSequence.d.ts

@@ -1,10 +1,20 @@
 /**
  * @private
  * Finds ORFs in a given DNA forward in a given frame.
- * @param  {Int} frame The frame to look in.
- * @param  {String}sequence The dna sequence.
- * @param  {Int} minimumOrfSize The minimum length of ORF to return.
- * @param  {boolean} forward Should we find forward facing orfs or reverse facing orfs
- * @return {Teselagen.bio.orf.ORF[]} The list of ORFs found.
+ * frame - The frame to look in.
+ * sequence - The dna sequence.
+ * minimumOrfSize - The minimum length of ORF to return.
+ * forward - Should we find forward facing orfs or reverse facing orfs
+ * return - The list of ORFs found.
  */
-export default function getOrfsFromSequence(options: any): Teselagen.bio.orf.ORF[];
+export default function getOrfsFromSequence(options: any): {
+    start: number;
+    end: number;
+    length: number;
+    internalStartCodonIndices: never[];
+    frame: number;
+    forward: any;
+    annotationTypePlural: string;
+    isOrf: boolean;
+    id: any;
+}[];

package/index.js

@@ -822,7 +822,7 @@ lodash.exports;
         return new LodashWrapper(value);
       }
       __name(lodash2, "lodash");
-      var baseCreate = function() {
+      var baseCreate = /* @__PURE__ */ function() {
         function object() {
         }
         __name(object, "object");
@@ -4447,7 +4447,7 @@ lodash.exports;
       var gte = createRelationalOperation(function(value, other) {
         return value >= other;
       });
-      var isArguments = baseIsArguments(function() {
+      var isArguments = baseIsArguments(/* @__PURE__ */ function() {
         return arguments;
       }()) ? baseIsArguments : function(value) {
         return isObjectLike(value) && hasOwnProperty.call(value, "callee") && !propertyIsEnumerable.call(value, "callee");
@@ -6000,7 +6000,7 @@ lodash.exports;
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -7922,7 +7922,7 @@ __name(requireEmpty, "requireEmpty");
         throw new TypeError("Cannot call a class as a function");
       }
     }, "classCallCheck");
-    var createClass = function() {
+    var createClass = /* @__PURE__ */ function() {
       function defineProperties(target, props) {
         for (var i = 0; i < props.length; i++) {
           var descriptor = props[i];
@@ -7984,7 +7984,7 @@ __name(requireEmpty, "requireEmpty");
       }
       return call && (typeof call === "object" || typeof call === "function") ? call : self2;
     }, "possibleConstructorReturn");
-    var slicedToArray = function() {
+    var slicedToArray = /* @__PURE__ */ function() {
       function sliceIterator(arr, i) {
         var _arr = [];
         var _n = true;
@@ -12384,7 +12384,12 @@ function filterSequenceString(sequenceString = "", {
   });
   if (sequenceString.length !== sanitizedVal.length) {
     warnings.push(
-      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).map((c) => {
+        if (c === " ") {
+          return "space";
+        }
+        return c;
+      }).slice(0, 100).join(", ")} `
     );
   }
   showWarnings(warnings);
@@ -13026,12 +13031,12 @@ const calcTmMethods = {
   // Monovalent salt concentration. 50mM is typical for PCR.
   /**
    * Calculates temperature for DNA sequence using a given algorithm.
-   * @param  {String} sequence The DNA sequence to use.
-   * @param  {String} type Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
-   * @param  {Double} A Helix initation for deltaS. Defaults to -10.8.
-   * @param  {Double} R The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
-   * @param  {Double} Na THe monovalent salt concentration. Defaults to 50e-3M.
-   * @return {Double} Temperature for the given sequence, in Celsius.
+   * sequence - The DNA sequence to use.
+   * type - Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
+   * A - Helix initation for deltaS. Defaults to -10.8.
+   * R - The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
+   * Na - THe monovalent salt concentration. Defaults to 50e-3M.
+   * return - Temperature for the given sequence, in Celsius.
    */
   calculateTemperature: function(sequence, type, A, R, C, Na) {
     if (typeof type === "undefined") {
@@ -21541,6 +21546,8 @@ function getComplementAminoAcidStringFromSequenceString(sequenceString) {
 }
 __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");
 function getComplementSequenceString(sequence, isRna) {
+  if (typeof sequence !== "string")
+    return "";
   let complementSeqString = "";
   const complementMap = lodashExports.merge(
     DNAComplementMap,

package/index.mjs

@@ -820,7 +820,7 @@ lodash.exports;
         return new LodashWrapper(value);
       }
       __name(lodash2, "lodash");
-      var baseCreate = function() {
+      var baseCreate = /* @__PURE__ */ function() {
         function object() {
         }
         __name(object, "object");
@@ -4445,7 +4445,7 @@ lodash.exports;
       var gte = createRelationalOperation(function(value, other) {
         return value >= other;
       });
-      var isArguments = baseIsArguments(function() {
+      var isArguments = baseIsArguments(/* @__PURE__ */ function() {
         return arguments;
       }()) ? baseIsArguments : function(value) {
         return isObjectLike(value) && hasOwnProperty.call(value, "callee") && !propertyIsEnumerable.call(value, "callee");
@@ -5998,7 +5998,7 @@ lodash.exports;
 var lodashExports = lodash.exports;
 const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO";
+const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 const unambiguous_dna_letters = "GATC";
 const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -7920,7 +7920,7 @@ __name(requireEmpty, "requireEmpty");
         throw new TypeError("Cannot call a class as a function");
       }
     }, "classCallCheck");
-    var createClass = function() {
+    var createClass = /* @__PURE__ */ function() {
       function defineProperties(target, props) {
         for (var i = 0; i < props.length; i++) {
           var descriptor = props[i];
@@ -7982,7 +7982,7 @@ __name(requireEmpty, "requireEmpty");
       }
       return call && (typeof call === "object" || typeof call === "function") ? call : self2;
     }, "possibleConstructorReturn");
-    var slicedToArray = function() {
+    var slicedToArray = /* @__PURE__ */ function() {
       function sliceIterator(arr, i) {
         var _arr = [];
         var _n = true;
@@ -12382,7 +12382,12 @@ function filterSequenceString(sequenceString = "", {
   });
   if (sequenceString.length !== sanitizedVal.length) {
     warnings.push(
-      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
+      `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).map((c) => {
+        if (c === " ") {
+          return "space";
+        }
+        return c;
+      }).slice(0, 100).join(", ")} `
     );
   }
   showWarnings(warnings);
@@ -13024,12 +13029,12 @@ const calcTmMethods = {
   // Monovalent salt concentration. 50mM is typical for PCR.
   /**
    * Calculates temperature for DNA sequence using a given algorithm.
-   * @param  {String} sequence The DNA sequence to use.
-   * @param  {String} type Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
-   * @param  {Double} A Helix initation for deltaS. Defaults to -10.8.
-   * @param  {Double} R The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
-   * @param  {Double} Na THe monovalent salt concentration. Defaults to 50e-3M.
-   * @return {Double} Temperature for the given sequence, in Celsius.
+   * sequence - The DNA sequence to use.
+   * type - Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
+   * A - Helix initation for deltaS. Defaults to -10.8.
+   * R - The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
+   * Na - THe monovalent salt concentration. Defaults to 50e-3M.
+   * return - Temperature for the given sequence, in Celsius.
    */
   calculateTemperature: function(sequence, type, A, R, C, Na) {
     if (typeof type === "undefined") {
@@ -21539,6 +21544,8 @@ function getComplementAminoAcidStringFromSequenceString(sequenceString) {
 }
 __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");
 function getComplementSequenceString(sequence, isRna) {
+  if (typeof sequence !== "string")
+    return "";
   let complementSeqString = "";
   const complementMap = lodashExports.merge(
     DNAComplementMap,

package/index.umd.js

@@ -824,7 +824,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
           return new LodashWrapper(value);
         }
         __name(lodash2, "lodash");
-        var baseCreate = function() {
+        var baseCreate = /* @__PURE__ */ function() {
           function object() {
           }
           __name(object, "object");
@@ -4449,7 +4449,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
         var gte = createRelationalOperation(function(value, other) {
           return value >= other;
         });
-        var isArguments = baseIsArguments(function() {
+        var isArguments = baseIsArguments(/* @__PURE__ */ function() {
           return arguments;
         }()) ? baseIsArguments : function(value) {
           return isObjectLike(value) && hasOwnProperty.call(value, "callee") && !propertyIsEnumerable.call(value, "callee");
@@ -6002,7 +6002,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   var lodashExports = lodash.exports;
   const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
   const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO";
+  const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
   const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
   const unambiguous_dna_letters = "GATC";
   const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
@@ -7924,7 +7924,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
           throw new TypeError("Cannot call a class as a function");
         }
       }, "classCallCheck");
-      var createClass = function() {
+      var createClass = /* @__PURE__ */ function() {
         function defineProperties(target, props) {
           for (var i = 0; i < props.length; i++) {
             var descriptor = props[i];
@@ -7986,7 +7986,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
         }
         return call && (typeof call === "object" || typeof call === "function") ? call : self2;
       }, "possibleConstructorReturn");
-      var slicedToArray = function() {
+      var slicedToArray = /* @__PURE__ */ function() {
         function sliceIterator(arr, i) {
           var _arr = [];
           var _n = true;
@@ -12386,7 +12386,12 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     });
     if (sequenceString.length !== sanitizedVal.length) {
       warnings.push(
-        `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).slice(0, 100).join(", ")} `
+        `${name ? `Sequence ${name}: ` : ""}Invalid character(s) detected and removed: ${lodashExports.uniq(invalidChars).map((c) => {
+          if (c === " ") {
+            return "space";
+          }
+          return c;
+        }).slice(0, 100).join(", ")} `
       );
     }
     showWarnings(warnings);
@@ -13028,12 +13033,12 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     // Monovalent salt concentration. 50mM is typical for PCR.
     /**
      * Calculates temperature for DNA sequence using a given algorithm.
-     * @param  {String} sequence The DNA sequence to use.
-     * @param  {String} type Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
-     * @param  {Double} A Helix initation for deltaS. Defaults to -10.8.
-     * @param  {Double} R The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
-     * @param  {Double} Na THe monovalent salt concentration. Defaults to 50e-3M.
-     * @return {Double} Temperature for the given sequence, in Celsius.
+     * sequence - The DNA sequence to use.
+     * type - Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
+     * A - Helix initation for deltaS. Defaults to -10.8.
+     * R - The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
+     * Na - THe monovalent salt concentration. Defaults to 50e-3M.
+     * return - Temperature for the given sequence, in Celsius.
      */
     calculateTemperature: function(sequence, type, A, R, C, Na) {
       if (typeof type === "undefined") {
@@ -21543,6 +21548,8 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
   }
   __name(getComplementAminoAcidStringFromSequenceString, "getComplementAminoAcidStringFromSequenceString");
   function getComplementSequenceString(sequence, isRna) {
+    if (typeof sequence !== "string")
+      return "";
     let complementSeqString = "";
     const complementMap = lodashExports.merge(
       DNAComplementMap,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.18",
+  "version": "0.3.20",
   "dependencies": {
     "@teselagen/range-utils": "0.3.7",
     "bson-objectid": "^2.0.4",

package/src/bioData.js

@@ -2,7 +2,7 @@
 
 export const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
 export const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
-export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO";
+export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO*";
 export const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
 export const unambiguous_dna_letters = "GATC";
 export const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";

package/src/calculateTm.js

@@ -16,12 +16,12 @@ const calcTmMethods = {
 
   /**
    * Calculates temperature for DNA sequence using a given algorithm.
-   * @param  {String} sequence The DNA sequence to use.
-   * @param  {String} type Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
-   * @param  {Double} A Helix initation for deltaS. Defaults to -10.8.
-   * @param  {Double} R The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
-   * @param  {Double} Na THe monovalent salt concentration. Defaults to 50e-3M.
-   * @return {Double} Temperature for the given sequence, in Celsius.
+   * sequence - The DNA sequence to use.
+   * type - Either Teselagen.bio.tools.TemperatureCalculator.TABLE_BRESLAUER, TABLE_SUGIMOTO, or TABLE_UNIFIED
+   * A - Helix initation for deltaS. Defaults to -10.8.
+   * R - The gas constant, in cal/(K*mol). Defaults to 0.5e-6M.
+   * Na - THe monovalent salt concentration. Defaults to 50e-3M.
+   * return - Temperature for the given sequence, in Celsius.
    */
   calculateTemperature: function (sequence, type, A, R, C, Na) {
     if (typeof type === "undefined") {

package/src/filterSequenceString.js

@@ -81,6 +81,12 @@ export default function filterSequenceString(
       `${
         name ? `Sequence ${name}: ` : ""
       }Invalid character(s) detected and removed: ${uniq(invalidChars)
+        .map(c => {
+          if (c === " ") {
+            return "space";
+          }
+          return c;
+        })
         .slice(0, 100)
         .join(", ")} `
     );

package/src/filterSequenceString.test.js

@@ -77,6 +77,6 @@ describe("filterSequenceString", () => {
       }
     );
 
-    expect(str).toBe("BXZJUObbbxtgalbmfwkqespvicyhrnd");
+    expect(str).toBe("BXZJUO*bbbxtgalbmfwkqespvicyhrnd");
   });
 });

package/src/getComplementSequenceString.js

@@ -1,9 +1,8 @@
 import DNAComplementMap from "./DNAComplementMap";
 import { merge } from "lodash";
 
-// ac.throw([ac.string,ac.bool],arguments);
 export default function getComplementSequenceString(sequence, isRna) {
-  // ac.throw([ac.string],arguments);
+  if (typeof sequence !== "string") return "";
   let complementSeqString = "";
   const complementMap = merge(
     DNAComplementMap,

package/src/getOrfsFromSequence.js

@@ -4,21 +4,13 @@ import getReverseComplementSequenceString from "./getReverseComplementSequenceSt
 /**
  * @private
  * Finds ORFs in a given DNA forward in a given frame.
- * @param  {Int} frame The frame to look in.
- * @param  {String}sequence The dna sequence.
- * @param  {Int} minimumOrfSize The minimum length of ORF to return.
- * @param  {boolean} forward Should we find forward facing orfs or reverse facing orfs
- * @return {Teselagen.bio.orf.ORF[]} The list of ORFs found.
+ * frame - The frame to look in.
+ * sequence - The dna sequence.
+ * minimumOrfSize - The minimum length of ORF to return.
+ * forward - Should we find forward facing orfs or reverse facing orfs
+ * return - The list of ORFs found.
  */
 export default function getOrfsFromSequence(options) {
-  // ac.throw([ac.shape({
-  //     sequence: ac.string,
-  //     minimumOrfSize: ac.posInt,
-  //     forward: ac.bool,
-  //     circular: ac.bool
-  // })], arguments);
-
-  // const frame = options.frame;
   let sequence = options.sequence;
   const minimumOrfSize = options.minimumOrfSize;
   const forward = options.forward;
@@ -38,7 +30,6 @@ export default function getOrfsFromSequence(options) {
   const re = useAdditionalOrfStartCodons
     ? /(?=((?:A[TU]G|G[TU]G|C[TU]G)(?:.{3})*?(?:[TU]AG|[TU]AA|[TU]GA)))/gi
     : /(?=((?:A[TU]G)(?:.{3})*?(?:[TU]AG|[TU]AA|[TU]GA)))/gi;
-  // const str = 'tatgaatgaatgffffffatgfftaaftaafatgfatgfffffsdfatgffatgfffstaafftaafffffffffffffffatgtaaataa\n\natgffftaaf\n\natgffatgftaafftaa\n\natgatgftaafftaa\n\natgatgtaataa\n\ntttttttttttttaatgatgfffffffffftaa';
   let m;
   const orfRanges = [];
   //loop through orf hits!
@@ -103,8 +94,6 @@ export default function getOrfsFromSequence(options) {
     } else {
       orfEnds[orf.end] = index;
       if (!forward) {
-        // if (originalSequenceLength - orf.end - 1 == 3657) {
-        // }
         //this check needs to come after the above assignment of orfEnds
         //flip the start and ends
         const endHolder = orf.end; //temp variable

package/src/tidyUpSequenceData.test.js

@@ -65,18 +65,18 @@ describe("tidyUpSequenceData", () => {
     res.should.containSubset({
       aminoAcidDataForEachBaseOfDNA: [],
       isProtein: true,
-      size: 54, //size should refer to the DNA length
-      proteinSize: 18, //proteinSize should refer to the amino acid length
-      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnhtnggnytnhtn", //degenerate sequence
-      proteinSequence: "gagiuhwgagalasjglj",
+      size: 57, //size should refer to the DNA length
+      proteinSize: 19, //proteinSize should refer to the amino acid length
+      sequence: "ggngcnggnathtgacaytggggngcnggngcnytngcnwsnhtnggnytnhtntrr", //degenerate sequence
+      proteinSequence: "gagiuhwgagalasjglj*",
       circular: false,
       features: [
         { start: 9, end: 32, forward: true },
-        { start: 30, end: 53, forward: true },
+        { start: 30, end: 56, forward: true },
         {
           name: "iDon'tFit",
-          start: 51,
-          end: 53,
+          start: 54,
+          end: 56,
           forward: true
         }
       ]