@teselagen/sequence-utils 0.3.7 → 0.3.9

package/src/bioData.js

@@ -1,85 +1,15 @@
 //Adapted from biopython. Check the BIOPYTHON_LICENSE for licensing info
 
 export const protein_letters = "ACDEFGHIKLMNPQRSTVWY";
+export const protein_letters_withUandX = "ACDEFGHIKLMNPQRSTVWYUX";
 
 export const extended_protein_letters = "ACDEFGHIKLMNPQRSTVWYBXZJUO.*-";
-
-// #   B = "Asx";  aspartic acid or asparagine (D or N)
-// #   X = "Xxx";  unknown or 'other' amino acid
-// #   Z = "Glx";  glutamic acid or glutamine (E or Q)
-// #   http://www.chem.qmul.ac.uk/iupac/AminoAcid/A2021.html#AA212
-// #
-// #   J = "Xle";  leucine or isoleucine (L or I, used in NMR)
-// #   Mentioned in http://www.chem.qmul.ac.uk/iubmb/newsletter/1999/item3.html
-// #   Also the International Nucleotide Sequence Database Collaboration (INSDC)
-// #   (i.e. GenBank, EMBL, DDBJ) adopted this in 2006
-// #   http://www.ddbj.nig.ac.jp/insdc/icm2006-e.html
-// #
-// #   Xle (J); Leucine or Isoleucine
-// #   The residue abbreviations, Xle (the three-letter abbreviation) and J
-// #   (the one-letter abbreviation) are reserved for the case that cannot
-// #   experimentally distinguish leucine from isoleucine.
-// #
-// #   U = "Sec";  selenocysteine
-// #   http://www.chem.qmul.ac.uk/iubmb/newsletter/1999/item3.html
-// #
-// #   O = "Pyl";  pyrrolysine
-// #   http://www.chem.qmul.ac.uk/iubmb/newsletter/2009.html#item35
-
-export const protein_letters_1to3 = {
-  A: "Ala",
-  C: "Cys",
-  D: "Asp",
-  E: "Glu",
-  F: "Phe",
-  G: "Gly",
-  H: "His",
-  I: "Ile",
-  K: "Lys",
-  L: "Leu",
-  M: "Met",
-  N: "Asn",
-  P: "Pro",
-  Q: "Gln",
-  R: "Arg",
-  S: "Ser",
-  T: "Thr",
-  V: "Val",
-  W: "Trp",
-  Y: "Tyr",
-  O: "Pyl",
-  U: "Sec"
-};
-
-// module.exports.protein_letters_1to3_extended = dict(
-//   list(protein_letters_1to3.items()) +
-//     list(
-//       {
-//         B: "Asx",
-//         X: "Xaa",
-//         Z: "Glx",
-//         J: "Xle",
-//         U: "Sel",
-//         O: "Pyl"
-//       }.items()
-//     )
-// );
-
 export const ambiguous_dna_letters = "GATCRYWSMKHBVDN";
-
 export const unambiguous_dna_letters = "GATC";
 export const ambiguous_rna_letters = "GAUCRYWSMKHBVDN";
 export const unambiguous_rna_letters = "GAUC";
-
-// #   B == 5-bromouridine
-// #   D == 5,6-dihydrouridine
-// #   S == thiouridine
-// #   W == wyosine
 export const extended_dna_letters = "GATCBDSW";
 
-// # are there extended forms?
-// # extended_rna_letters = "GAUCBDSW"
-
 export const ambiguous_dna_values = {
   ".": ".",
   A: "A",
@@ -100,180 +30,6 @@ export const ambiguous_dna_values = {
   N: "GATC"
 };
 
-export const ambiguous_rna_values = {
-  ".": ".",
-  A: "A",
-  C: "C",
-  G: "G",
-  U: "U",
-  M: "AC",
-  R: "AG",
-  W: "AU",
-  S: "CG",
-  Y: "CU",
-  K: "GU",
-  V: "ACG",
-  H: "ACU",
-  D: "AGU",
-  B: "CGU",
-  X: "GAUC",
-  N: "GAUC"
-};
-
-export const ambiguous_dna_complement = {
-  ".": ".",
-  A: "T",
-  C: "G",
-  G: "C",
-  T: "A",
-  M: "K",
-  R: "Y",
-  W: "W",
-  S: "S",
-  Y: "R",
-  K: "M",
-  V: "B",
-  H: "D",
-  D: "H",
-  B: "V",
-  X: "X",
-  N: "N"
-};
-
-export const ambiguous_rna_complement = {
-  ".": ".",
-  A: "U",
-  C: "G",
-  G: "C",
-  U: "A",
-  M: "K",
-  R: "Y",
-  W: "W",
-  S: "S",
-  Y: "R",
-  K: "M",
-  V: "B",
-  H: "D",
-  D: "H",
-  B: "V",
-  X: "X",
-  N: "N"
-};
-
-// # Mass data taken from PubChem
-
-// # Average masses of monophosphate deoxy nucleotides
-export const unambiguous_dna_weights = {
-  A: 331.2218,
-  C: 307.1971,
-  G: 347.2212,
-  T: 322.2085
-};
-
-// # Monoisotopic masses of monophospate deoxy nucleotides
-export const monoisotopic_unambiguous_dna_weights = {
-  A: 331.06817,
-  C: 307.056936,
-  G: 347.063084,
-  T: 322.056602
-};
-
-// module.exports.unambiguous_dna_weight_ranges = _make_ranges(
-//   unambiguous_dna_weights
-// );
-
-export const unambiguous_rna_weights = {
-  A: 347.2212,
-  C: 323.1965,
-  G: 363.2206,
-  U: 324.1813
-};
-
-export const monoisotopic_unambiguous_rna_weights = {
-  A: 347.063084,
-  C: 323.051851,
-  G: 363.057999,
-  U: 324.035867
-};
-
-// module.exports.unambiguous_rna_weight_ranges = _make_ranges(
-//   unambiguous_rna_weights
-// );
-
-// def _make_ambiguous_ranges(mydict, weight_table):
-//     range_d = {}
-//     avg_d = {}
-//     for letter, values in mydict.items():
-//         # Following line is a quick hack to skip undefined weights for U and O
-//         if len(values) == 1 and values[0] not in weight_table:
-//             continue
-
-//         weights = [weight_table.get(x) for x in values]
-//         range_d[letter] = (min(weights), max(weights))
-//         total_w = 0.0
-//         for w in weights:
-//             total_w = total_w + w
-//         avg_d[letter] = total_w / len(weights)
-//     return range_d, avg_d
-
-// ambiguous_dna_weight_ranges, avg_ambiguous_dna_weights = \
-//                _make_ambiguous_ranges(ambiguous_dna_values,
-//                                       unambiguous_dna_weights)
-
-// ambiguous_rna_weight_ranges, avg_ambiguous_rna_weights = \
-//                _make_ambiguous_ranges(ambiguous_rna_values,
-//                                       unambiguous_rna_weights)
-
-export const protein_weights = {
-  A: 89.0932,
-  C: 121.1582,
-  D: 133.1027,
-  E: 147.1293,
-  F: 165.1891,
-  G: 75.0666,
-  H: 155.1546,
-  I: 131.1729,
-  K: 146.1876,
-  L: 131.1729,
-  M: 149.2113,
-  N: 132.1179,
-  O: 255.3134,
-  P: 115.1305,
-  Q: 146.1445,
-  R: 174.201,
-  S: 105.0926,
-  T: 119.1192,
-  U: 168.0532,
-  V: 117.1463,
-  W: 204.2252,
-  Y: 181.1885
-};
-
-export const monoisotopic_protein_weights = {
-  A: 89.047678,
-  C: 121.019749,
-  D: 133.037508,
-  E: 147.053158,
-  F: 165.078979,
-  G: 75.032028,
-  H: 155.069477,
-  I: 131.094629,
-  K: 146.105528,
-  L: 131.094629,
-  M: 149.051049,
-  N: 132.053492,
-  O: 255.158292,
-  P: 115.063329,
-  Q: 146.069142,
-  R: 174.111676,
-  S: 105.042593,
-  T: 119.058243,
-  U: 168.964203,
-  V: 117.078979,
-  W: 204.089878,
-  Y: 181.073893
-};
-
 export const extended_protein_values = {
   A: "A",
   B: "ND",
@@ -308,124 +64,3 @@ export const extended_protein_values = {
   ".": "\\.\\.",
   "-": "\\-"
 };
-
-// protein_weight_ranges = _make_ranges(protein_weights)
-
-// extended_protein_weight_ranges, avg_extended_protein_weights = \
-//                _make_ambiguous_ranges(extended_protein_values,
-//                                       protein_weights)
-
-// # For Center of Mass Calculation.
-// # Taken from http://www.chem.qmul.ac.uk/iupac/AtWt/ & PyMol
-export const atom_weights = {
-  H: 1.00794,
-  D: 2.0141,
-  He: 4.002602,
-  Li: 6.941,
-  Be: 9.012182,
-  B: 10.811,
-  C: 12.0107,
-  N: 14.0067,
-  O: 15.9994,
-  F: 18.9984032,
-  Ne: 20.1797,
-  Na: 22.98977,
-  Mg: 24.305,
-  Al: 26.981538,
-  Si: 28.0855,
-  P: 30.973761,
-  S: 32.065,
-  Cl: 35.453,
-  Ar: 39.948,
-  K: 39.0983,
-  Ca: 40.078,
-  Sc: 44.95591,
-  Ti: 47.867,
-  V: 50.9415,
-  Cr: 51.9961,
-  Mn: 54.938049,
-  Fe: 55.845,
-  Co: 58.9332,
-  Ni: 58.6934,
-  Cu: 63.546,
-  Zn: 65.39,
-  Ga: 69.723,
-  Ge: 72.64,
-  As: 74.9216,
-  Se: 78.96,
-  Br: 79.904,
-  Kr: 83.8,
-  Rb: 85.4678,
-  Sr: 87.62,
-  Y: 88.90585,
-  Zr: 91.224,
-  Nb: 92.90638,
-  Mo: 95.94,
-  Tc: 98.0,
-  Ru: 101.07,
-  Rh: 102.9055,
-  Pd: 106.42,
-  Ag: 107.8682,
-  Cd: 112.411,
-  In: 114.818,
-  Sn: 118.71,
-  Sb: 121.76,
-  Te: 127.6,
-  I: 126.90447,
-  Xe: 131.293,
-  Cs: 132.90545,
-  Ba: 137.327,
-  La: 138.9055,
-  Ce: 140.116,
-  Pr: 140.90765,
-  Nd: 144.24,
-  Pm: 145.0,
-  Sm: 150.36,
-  Eu: 151.964,
-  Gd: 157.25,
-  Tb: 158.92534,
-  Dy: 162.5,
-  Ho: 164.93032,
-  Er: 167.259,
-  Tm: 168.93421,
-  Yb: 173.04,
-  Lu: 174.967,
-  Hf: 178.49,
-  Ta: 180.9479,
-  W: 183.84,
-  Re: 186.207,
-  Os: 190.23,
-  Ir: 192.217,
-  Pt: 195.078,
-  Au: 196.96655,
-  Hg: 200.59,
-  Tl: 204.3833,
-  Pb: 207.2,
-  Bi: 208.98038,
-  Po: 208.98,
-  At: 209.99,
-  Rn: 222.02,
-  Fr: 223.02,
-  Ra: 226.03,
-  Ac: 227.03,
-  Th: 232.0381,
-  Pa: 231.03588,
-  U: 238.02891,
-  Np: 237.05,
-  Pu: 244.06,
-  Am: 243.06,
-  Cm: 247.07,
-  Bk: 247.07,
-  Cf: 251.08,
-  Es: 252.08,
-  Fm: 257.1,
-  Md: 258.1,
-  No: 259.1,
-  Lr: 262.11,
-  Rf: 261.11,
-  Db: 262.11,
-  Sg: 266.12,
-  Bh: 264.12,
-  Hs: 269.13,
-  Mt: 268.14
-};

package/src/calculateNebTa.js

@@ -31,4 +31,4 @@ export default function calculateNebTa(
   } catch (err) {
     return `Error calculating annealing temperature: ${err}`;
   }
-};
+}

package/src/calculateNebTm.js

@@ -124,4 +124,4 @@ export default function calculateNebTm(
   } catch (err) {
     return `Error calculating Tm for sequence ${sequence}: ${err}`;
   }
-};
+}

package/src/calculatePercentGC.js

@@ -1,3 +1,3 @@
 export default function calculatePercentGC(bps) {
-  return (bps.match(/[cg]/gi) || []).length / bps.length * 100 || 0;
-};
+  return ((bps.match(/[cg]/gi) || []).length / bps.length) * 100 || 0;
+}

package/src/calculateTm.js

@@ -23,12 +23,13 @@ const calcTmMethods = {
    * @param  {Double} Na THe monovalent salt concentration. Defaults to 50e-3M.
    * @return {Double} Temperature for the given sequence, in Celsius.
    */
-  calculateTemperature: function(sequence, type, A, R, C, Na) {
+  calculateTemperature: function (sequence, type, A, R, C, Na) {
     if (typeof type === "undefined") {
       type = this.TABLE_BRESLAUER;
     } else if (
       type != this.TABLE_BRESLAUER &&
-      (type != this.TABLE_UNIFIED && type != this.TABLE_SUGIMOTO)
+      type != this.TABLE_UNIFIED &&
+      type != this.TABLE_SUGIMOTO
     ) {
       throw new Error("Invalid table type!");
     }
@@ -104,63 +105,21 @@ const calcTmMethods = {
    * @param {String} type Algorithm to get table for.
    * @return {Number[]} deltaH table for given algorithm.
    */
-  getDeltaHTable: function(type) {
+  getDeltaHTable: function (type) {
     if (type == this.TABLE_BRESLAUER) {
       return [
-        9.1,
-        8.6,
-        6.5,
-        7.8,
-        9.1,
-        6.0,
-        5.6,
-        5.8,
-        11.0,
-        5.8,
-        7.8,
-        11.9,
-        11.0,
-        5.6,
-        6.5,
-        11.1
+        9.1, 8.6, 6.5, 7.8, 9.1, 6.0, 5.6, 5.8, 11.0, 5.8, 7.8, 11.9, 11.0, 5.6,
+        6.5, 11.1
       ];
     } else if (type == this.TABLE_SUGIMOTO) {
       return [
-        8.0,
-        5.6,
-        6.5,
-        7.8,
-        8.0,
-        5.6,
-        5.6,
-        5.8,
-        10.9,
-        8.2,
-        6.6,
-        11.8,
-        10.9,
-        6.6,
-        9.4,
-        11.9
+        8.0, 5.6, 6.5, 7.8, 8.0, 5.6, 5.6, 5.8, 10.9, 8.2, 6.6, 11.8, 10.9, 6.6,
+        9.4, 11.9
       ];
     } else if (type == this.TABLE_UNIFIED) {
       return [
-        7.9,
-        7.2,
-        8.4,
-        7.8,
-        7.9,
-        7.2,
-        8.2,
-        8.5,
-        8.0,
-        8.5,
-        7.8,
-        10.6,
-        8.0,
-        8.2,
-        8.4,
-        9.8
+        7.9, 7.2, 8.4, 7.8, 7.9, 7.2, 8.2, 8.5, 8.0, 8.5, 7.8, 10.6, 8.0, 8.2,
+        8.4, 9.8
       ];
     } else {
       return null;
@@ -173,63 +132,21 @@ const calcTmMethods = {
    * @param {String} type Algorithm to get table for.
    * @return {Number[]} deltaS table for given algorithm.
    */
-  getDeltaSTable: function(type) {
+  getDeltaSTable: function (type) {
     if (type == this.TABLE_BRESLAUER) {
       return [
-        24.0,
-        23.9,
-        17.3,
-        20.8,
-        24.0,
-        16.9,
-        13.5,
-        12.9,
-        26.6,
-        12.9,
-        20.8,
-        27.8,
-        26.6,
-        13.5,
-        17.3,
-        26.7
+        24.0, 23.9, 17.3, 20.8, 24.0, 16.9, 13.5, 12.9, 26.6, 12.9, 20.8, 27.8,
+        26.6, 13.5, 17.3, 26.7
       ];
     } else if (type == this.TABLE_SUGIMOTO) {
       return [
-        21.9,
-        15.2,
-        17.3,
-        20.8,
-        21.9,
-        15.2,
-        13.5,
-        12.9,
-        28.4,
-        25.5,
-        23.5,
-        29.0,
-        28.4,
-        16.4,
-        25.5,
-        29.0
+        21.9, 15.2, 17.3, 20.8, 21.9, 15.2, 13.5, 12.9, 28.4, 25.5, 23.5, 29.0,
+        28.4, 16.4, 25.5, 29.0
       ];
     } else if (type == this.TABLE_UNIFIED) {
       return [
-        22.2,
-        20.4,
-        22.4,
-        21.0,
-        22.2,
-        21.3,
-        22.2,
-        22.7,
-        19.9,
-        22.7,
-        21.0,
-        27.2,
-        19.9,
-        22.2,
-        22.4,
-        24.4
+        22.2, 20.4, 22.4, 21.0, 22.2, 21.3, 22.2, 22.7, 19.9, 22.7, 21.0, 27.2,
+        19.9, 22.2, 22.4, 24.4
       ];
     } else {
       return null;
@@ -245,7 +162,7 @@ const calcTmMethods = {
    * @param  {String} target   The string to search for.
    * @return {Int} Number of occurrences of target in sequence, with repeats.
    */
-  calculateReps: function(sequence, target) {
+  calculateReps: function (sequence, target) {
     const sequenceLength = sequence.length;
 
     if (sequenceLength == 0) {
@@ -281,7 +198,7 @@ const calcTmMethods = {
    * @param  {String} target   The string to search for.
    * @return {Int} Number of occurrences of target in sequence.
    */
-  calculateNumberOfOccurrences: function(sequence, target) {
+  calculateNumberOfOccurrences: function (sequence, target) {
     const sequenceLength = sequence.length;
 
     if (sequenceLength == 0) {

package/src/computeDigestFragments.js

@@ -1,6 +1,9 @@
 import shortid from "shortid";
-import {flatMap, cloneDeep} from "lodash";
-import {normalizePositionByRangeLength, getRangeLength} from "@teselagen/range-utils";
+import { flatMap, cloneDeep } from "lodash";
+import {
+  normalizePositionByRangeLength,
+  getRangeLength
+} from "@teselagen/range-utils";
 import getCutsitesFromSequence from "./getCutsitesFromSequence";
 
 function computeDigestFragments({
@@ -175,5 +178,5 @@ function getDigestFragsForSeqAndEnzymes({
   });
 }
 
-export {computeDigestFragments};
-export {getDigestFragsForSeqAndEnzymes};
+export { computeDigestFragments };
+export { getDigestFragsForSeqAndEnzymes };

package/src/computeDigestFragments.test.js

@@ -1,4 +1,4 @@
-import {getDigestFragsForSeqAndEnzymes} from "./computeDigestFragments.js";
+import { getDigestFragsForSeqAndEnzymes } from "./computeDigestFragments.js";
 import aliasedEnzymesByName from "./aliasedEnzymesByName.js";
 
 describe("computeDigestFragments", () => {

package/src/condensePairwiseAlignmentDifferences.js

@@ -82,4 +82,4 @@ export default function condensePairwiseAlignmentDifferences(
     }
   }
   return overviewMinimapTrack.join("");
-};
+}

package/src/convertAACaretPositionOrRangeToDna.js

@@ -9,7 +9,7 @@ export default function convertAACaretPositionOrRangeToDna(rangeOrCaret) {
   } else {
     return convertAACaretPositionToDnaCaretPosition(rangeOrCaret);
   }
-};
+}
 
 function convertAACaretPositionToDnaCaretPosition(caret) {
   return caret * 3;

package/src/convertDnaCaretPositionOrRangeToAA.js

@@ -9,7 +9,7 @@ export default function convertDnaCaretPositionOrRangeToAA(rangeOrCaret) {
   } else {
     return convertDnaCaretPositionToAACaretPosition(rangeOrCaret);
   }
-};
+}
 
 function convertDnaCaretPositionToAACaretPosition(caret) {
   return Math.floor(caret / 3);

package/src/cutSequenceByRestrictionEnzyme.js

@@ -1,11 +1,11 @@
-import {assign} from "lodash";
+import { assign } from "lodash";
 import shortid from "shortid";
 import getReverseComplementSequenceString from "./getReverseComplementSequenceString";
 
 import {
   getSequenceWithinRange,
   normalizePositionByRangeLength,
-  reversePositionInRange,
+  reversePositionInRange
 } from "@teselagen/range-utils";
 
 export default function cutSequenceByRestrictionEnzyme(
@@ -98,7 +98,7 @@ export default function cutSequenceByRestrictionEnzyme(
       forward: false
     });
   }
-};
+}
 
 function cutSequence(
   forwardRegExpPattern,

package/src/cutSequenceByRestrictionEnzyme.test.js

@@ -1,6 +1,5 @@
 /* eslint-disable no-unused-expressions */
 
-
 import chai from "chai";
 import cutSequenceByRestrictionEnzyme from "./cutSequenceByRestrictionEnzyme.js";
 import enzymeList from "./aliasedEnzymesByName";

package/src/degenerateDnaToAminoAcidMap.js

@@ -1,4 +1,4 @@
-import {invert} from "lodash";
+import { invert } from "lodash";
 import aminoAcidToDegenerateDnaMap from "./aminoAcidToDegenerateDnaMap";
 
 const degenerateDnaToAminoAcidMap = invert(aminoAcidToDegenerateDnaMap);

package/src/degenerateRnaToAminoAcidMap.js

@@ -1,4 +1,4 @@
-import {invert} from "lodash";
+import { invert } from "lodash";
 import aminoAcidToDegenerateRnaMap from "./aminoAcidToDegenerateRnaMap";
 
 const degenerateRnaToAminoAcidMap = invert(aminoAcidToDegenerateRnaMap);

package/src/deleteSequenceDataAtRange.js

@@ -2,4 +2,4 @@ import insertSequenceDataAtPositionOrRange from "./insertSequenceDataAtPositionO
 
 export default function deleteSequenceDataAtRange(sequenceData, range) {
   return insertSequenceDataAtPositionOrRange({}, sequenceData, range);
-};
+}