@teselagen/sequence-utils 0.3.10 → 0.3.11

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/filterSequenceString.d.ts

@@ -1,4 +1,4 @@
-export default function filterSequenceString(sequenceString: any, { additionalValidChars, isOligo, name, isProtein, isRna, isMixedRnaAndDna, }?: {
+export default function filterSequenceString(sequenceString: any, { additionalValidChars, isOligo, name, isProtein, isRna, isMixedRnaAndDna }?: {
     additionalValidChars?: string | undefined;
     isOligo: any;
     name: any;
@@ -6,7 +6,7 @@ export default function filterSequenceString(sequenceString: any, { additionalVa
     isRna: any;
     isMixedRnaAndDna: any;
 }): (string | string[])[];
-export function getAcceptedChars({ isOligo, isProtein, isRna, isMixedRnaAndDna, }?: {
+export function getAcceptedChars({ isOligo, isProtein, isRna, isMixedRnaAndDna }?: {
     isOligo: any;
     isProtein: any;
     isRna: any;

package/index.js

@@ -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";
@@ -6056,7 +6056,7 @@ const extended_protein_values = {
   Y: "Y",
   Z: "QE",
   "*": "\\*\\.",
-  ".": "\\.\\.",
+  ".": "\\.",
   "-": "\\-"
 };
 const bioData = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.defineProperty({
@@ -12399,9 +12399,12 @@ function getReplaceChars({
   isRna,
   isMixedRnaAndDna
 } = {}) {
-  return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
-    //just plain old dna
-    {}
+  return isProtein ? {} : (
+    // {".": "*"}
+    isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+      //just plain old dna
+      {}
+    )
   );
 }
 __name(getReplaceChars, "getReplaceChars");

package/index.mjs

@@ -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";
@@ -6054,7 +6054,7 @@ const extended_protein_values = {
   Y: "Y",
   Z: "QE",
   "*": "\\*\\.",
-  ".": "\\.\\.",
+  ".": "\\.",
   "-": "\\-"
 };
 const bioData = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.defineProperty({
@@ -12397,9 +12397,12 @@ function getReplaceChars({
   isRna,
   isMixedRnaAndDna
 } = {}) {
-  return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
-    //just plain old dna
-    {}
+  return isProtein ? {} : (
+    // {".": "*"}
+    isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+      //just plain old dna
+      {}
+    )
   );
 }
 __name(getReplaceChars, "getReplaceChars");

package/index.umd.js

@@ -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";
@@ -6058,7 +6058,7 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     Y: "Y",
     Z: "QE",
     "*": "\\*\\.",
-    ".": "\\.\\.",
+    ".": "\\.",
     "-": "\\-"
   };
   const bioData = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.defineProperty({
@@ -12401,9 +12401,12 @@ var __name = (target, value) => __defProp(target, "name", { value, configurable:
     isRna,
     isMixedRnaAndDna
   } = {}) {
-    return isProtein ? {} : isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
-      //just plain old dna
-      {}
+    return isProtein ? {} : (
+      // {".": "*"}
+      isOligo ? {} : isRna ? { t: "u" } : isMixedRnaAndDna ? {} : (
+        //just plain old dna
+        {}
+      )
     );
   }
   __name(getReplaceChars, "getReplaceChars");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@teselagen/sequence-utils",
-  "version": "0.3.10",
+  "version": "0.3.11",
   "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";
@@ -60,6 +60,6 @@ export const extended_protein_values = {
   Y: "Y",
   Z: "QE",
   "*": "\\*\\.",
-  ".": "\\.\\.",
+  ".": "\\.",
   "-": "\\-"
 };

package/src/filterSequenceString.js

@@ -1,7 +1,7 @@
 import {
   ambiguous_dna_letters,
   ambiguous_rna_letters,
-  extended_protein_letters,
+  extended_protein_letters
 } from "./bioData";
 
 export default function filterSequenceString(
@@ -12,14 +12,14 @@ export default function filterSequenceString(
     name,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
+    isMixedRnaAndDna
   } = {}
 ) {
   const acceptedChars = getAcceptedChars({
     isOligo,
     isProtein,
     isRna,
-    isMixedRnaAndDna,
+    isMixedRnaAndDna
   });
   const replaceChars = getReplaceChars({
     isOligo,
@@ -80,7 +80,7 @@ export function getAcceptedChars({
   isOligo,
   isProtein,
   isRna,
-  isMixedRnaAndDna,
+  isMixedRnaAndDna
 } = {}) {
   return isProtein
     ? `${extended_protein_letters.toLowerCase()}}`
@@ -101,8 +101,8 @@ export function getReplaceChars({
 } = {}) {
   return isProtein
     ? {}
-    // {".": "*"}
-    : isOligo
+    : // {".": "*"}
+    isOligo
     ? {}
     : isRna
     ? { t: "u" }

package/src/filterSequenceString.test.js

@@ -50,7 +50,9 @@ describe("filterSequenceString", () => {
       }
     );
     // expect(warnings[0]).toBe(`Replaced "." with "*" 2 times`);
-    expect(warnings[0]).toBe(      'Invalid character(s) detected and removed: 3, 4, 2, ", ", ", ,, ,, ., ., / ');
+    expect(warnings[0]).toBe(
+      'Invalid character(s) detected and removed: 3, 4, 2, ", ", ", ,, ,, ., ., / '
+    );
     expect(str).toBe("bbbxtgalmfwkqespvicyhrnd");
   });
   it("when isProtein: true, should handle upper case letters", () => {
@@ -60,11 +62,27 @@ describe("filterSequenceString", () => {
     expect(warnings.length).toBe(0);
     expect(str).toBe("xtgalmfWKQEspvicyhrnd");
   });
+
+  it("when isProtein: true it should not filter this aa seq", () => {
+    const [str] = filterSequenceString(
+      "mhhhhhhgsgsmledlkrqvleanlalpkhnlasgssghvsavdrergvfviapsgvdfrimtaddmvvvsietgevvegekppaedtpthrllyqafpsiggivhthsrhatiwaqagqsipatgtthadhfygtipctrkmtdaeingeyewetgnvivetfekqgidaaqmpgvlvhshgpfawgknaedavhnaivleevaymgifcrqlapqlpdmqqtllnkhylrkhgakayygq",
+      {
+        isProtein: true
+      }
+    );
+
+    expect(str).toBe(
+      `mhhhhhhgsgsmledlkrqvleanlalpkhnlasgssghvsavdrergvfviapsgvdfrimtaddmvvvsietgevvegekppaedtpthrllyqafpsiggivhthsrhatiwaqagqsipatgtthadhfygtipctrkmtdaeingeyewetgnvivetfekqgidaaqmpgvlvhshgpfawgknaedavhnaivleevaymgifcrqlapqlpdmqqtllnkhylrkhgakayygq`
+    );
+  });
   it("when isProtein: true, it should convert . to *", () => {
-    const [str] = filterSequenceString('BXZJUO*bbb342"""xtgalbmfwkqespvicyhrnd,,../', {
-      isProtein: true,
-    });
+    const [str] = filterSequenceString(
+      'BXZJUO*bbb342"""xtgalbmfwkqespvicyhrnd,,../',
+      {
+        isProtein: true
+      }
+    );
 
-    expect(str).toBe("BXZJUO*bbbxtgalbmfwkqespvicyhrnd");
+    expect(str).toBe("BXZJUObbbxtgalbmfwkqespvicyhrnd");
   });
 });

package/src/insertSequenceDataAtPositionOrRange.test.js

@@ -135,7 +135,7 @@ describe("insertSequenceData", () => {
   });
   it("inserts characters at correct origin spanning range with {maintainOriginSplit: true} option", () => {
     const sequenceToInsert = {
-      sequence: "xrrrrry",
+      sequence: "crrrrry",
       //         fffffff
       features: [{ name: "feat1", start: 0, end: 6 }]
     };
@@ -154,7 +154,7 @@ describe("insertSequenceData", () => {
         maintainOriginSplit: true
       }
     );
-    postInsertSeq.sequence.should.equal("rrrryagagaxr");
+    postInsertSeq.sequence.should.equal("rrrryagagacr");
     //                                   fffff fff ff
     postInsertSeq.features.should.containSubset([
       { name: "feat1", start: 10, end: 4 },

package/src/tidyUpSequenceData.test.js

@@ -6,28 +6,25 @@ chai.use(chaiSubset);
 chai.should();
 describe("tidyUpSequenceData", () => {
   it("should remove invalid chars by default, while handling annotation start,end (and location start,end) truncation correctly", () => {
-    const res = tidyUpSequenceData(
-      {
-        sequence: "http://localhost:3344/Standalone",
-        features: [
-          {
-            start: 3,
-            end: 20,
-            locations: [
-              {
-                start: "3", //this should be converted to an int :)
-                end: 5
-              },
-              {
-                start: 10,
-                end: 20
-              }
-            ]
-          }
-        ]
-      },
-      
-    );
+    const res = tidyUpSequenceData({
+      sequence: "http://localhost:3344/Standalone",
+      features: [
+        {
+          start: 3,
+          end: 20,
+          locations: [
+            {
+              start: "3", //this should be converted to an int :)
+              end: 5
+            },
+            {
+              start: 10,
+              end: 20
+            }
+          ]
+        }
+      ]
+    });
     res.should.containSubset({
       sequence: "httcahstStandan",
       circular: false,
@@ -64,22 +61,22 @@ describe("tidyUpSequenceData", () => {
       },
       { convertAnnotationsFromAAIndices: true }
     );
-    
+
     res.should.containSubset({
       aminoAcidDataForEachBaseOfDNA: [],
       isProtein: true,
-      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*",
+      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",
       circular: false,
       features: [
         { start: 9, end: 32, forward: true },
-        { start: 30, end: 56, forward: true },
+        { start: 30, end: 53, forward: true },
         {
           name: "iDon'tFit",
-          start: 54,
-          end: 56,
+          start: 51,
+          end: 53,
           forward: true
         }
       ]