@datagrok/sequence-translator 1.0.16 → 1.1.0

package/src/apps/oligo-sd-file-app.ts

@@ -1,58 +0,0 @@
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-import {_package} from '../package';
-import {FileSource} from 'datagrok-api/dg';
-
-export class OligoSdFileApp {
-  df!: DG.DataFrame;
-
-  constructor() {}
-
-  async init(srcDf?: DG.DataFrame): Promise<void> {
-    let dataDf: DG.DataFrame;
-    if (srcDf) {
-      dataDf = srcDf;
-    } else {
-      const dfFn: string = 'System:AppData/SequenceTranslator/test input_Nov28_Duplex_dimer.xlsx';
-      dataDf = await this.loadData(dfFn);
-    }
-
-    this.setData(dataDf);
-  }
-
-  async loadData(dfFn: string): Promise<DG.DataFrame> {
-    //
-    const dataDf: DG.DataFrame = await grok.data.files.openTable(dfFn);
-    return dataDf;
-  }
-
-  async setData(df: DG.DataFrame): Promise<void> {
-    if (this.viewed) {
-      await this.destroyView();
-      this.viewed = false;
-    }
-
-    this.df = df;
-
-    if (!this.viewed) {
-      await this.buildView();
-      this.viewed = true;
-    }
-  }
-
-  private viewed: boolean = false;
-  private tView?: DG.TableView;
-
-  async destroyView(): Promise<void> {
-    this.tView!.close();
-    delete this.tView;
-  }
-
-  async buildView(): Promise<void> {
-    console.debug('SequenceTranslator: OligoSdFileApp.buildView() ');
-
-    this.tView = grok.shell.addTableView(this.df);
-    this.tView.path = this.tView.basePath = 'func/SequenceTranslator.oligoSdFileApp';
-  }
-}

package/src/autostart/ICDs.ts

@@ -1,3 +0,0 @@
-export const ICDS = `DISPLAY
-NO DATA
-`;

package/src/autostart/IDPs.ts

@@ -1,3 +0,0 @@
-export const IDPS = `DISPLAY
-NO DATA
-`;

package/src/autostart/calculations.ts

@@ -1,40 +0,0 @@
-import * as DG from 'datagrok-api/dg';
-
-import {sortByStringLengthInDescendingOrder} from '../helpers';
-import {MODIFICATIONS} from '../structures-works/map';
-
-export function saltMass(
-  saltNames: string[], saltsMolWeightList: number[], equivalentsCol: DG.Column, i: number, saltCol: DG.Column
-): number {
-  const saltRowIndex = saltNames.indexOf(saltCol.get(i));
-  return (
-    saltRowIndex == -1 || saltsMolWeightList[saltRowIndex] == DG.FLOAT_NULL || equivalentsCol.get(i) == DG.INT_NULL
-  ) ?
-    DG.FLOAT_NULL :
-    saltsMolWeightList[saltRowIndex] * equivalentsCol.get(i);
-}
-
-export function saltMolWeigth(
-  saltNamesList: string[], saltCol: DG.Column, saltsMolWeightList: number[], i: number
-): number {
-  const saltRowIndex = saltNamesList.indexOf(saltCol.get(i));
-  return (saltRowIndex == -1) ? DG.FLOAT_NULL : saltsMolWeightList[saltRowIndex];
-}
-
-export function batchMolWeight(compoundMolWeightCol: DG.Column, saltMassCol: DG.Column, i: number): number {
-  return (compoundMolWeightCol.getString(i) == '' || saltMassCol.getString(i) == '') ?
-    DG.FLOAT_NULL :
-    compoundMolWeightCol.get(i) + saltMassCol.get(i);
-}
-
-export function molecularWeight(sequence: string, weightsObj: { [index: string]: number }): number {
-  const codes = sortByStringLengthInDescendingOrder(Object.keys(weightsObj)).concat(Object.keys(MODIFICATIONS));
-  let weight = 0;
-  let i = 0;
-  while (i < sequence.length) {
-    const matchedCode = codes.find((s) => s == sequence.slice(i, i + s.length))!;
-    weight += weightsObj[sequence.slice(i, i + matchedCode.length)];
-    i += matchedCode.length;
-  }
-  return weight - 61.97;
-}

package/src/autostart/constants.ts

@@ -1,37 +0,0 @@
-export const SEQUENCE_TYPES = {
-  SENSE_STRAND: 'SS',
-  ANTISENSE_STRAND: 'AS',
-  DUPLEX: 'Duplex',
-  TRIPLEX: 'Triplex',
-  DIMER: 'Dimer',
-};
-
-export const COL_NAMES = {
-  CHEMISTRY: 'Chemistry',
-  NUMBER: 'Number',
-  TYPE: 'Type',
-  CHEMISTRY_NAME: 'Chemistry Name',
-  INTERNAL_COMPOUND_ID: 'Internal compound ID',
-  IDP: 'IDP',
-  SEQUENCE: 'Sequence',
-  COMPOUND_NAME: 'Compound Name',
-  COMPOUND_COMMENTS: 'Compound Comments',
-  SALT: 'Salt',
-  EQUIVALENTS: 'Equivalents',
-  PURITY: 'Purity',
-  COMPOUND_MOL_WEIGHT: 'Cpd MW',
-  SALT_MOL_WEIGHT: 'Salt MW',
-  SALT_MASS: 'Salt mass',
-  BATCH_MOL_WEIGHT: 'Batch MW',
-  SOURCE: 'Source',
-  ICD: 'ICD',
-  OWNER: 'Owner',
-};
-
-export const GENERATED_COL_NAMES = [
-  COL_NAMES.COMPOUND_NAME,
-  COL_NAMES.COMPOUND_COMMENTS,
-  COL_NAMES.COMPOUND_MOL_WEIGHT,
-  COL_NAMES.SALT_MASS,
-  COL_NAMES.BATCH_MOL_WEIGHT,
-];

package/src/autostart/registration.ts

@@ -1,241 +0,0 @@
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-import {
-  siRnaBioSpringToGcrs, siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
-  siRnaNucleotidesToGcrs
-} from '../structures-works/converters';
-import {weightsObj, SYNTHESIZERS} from '../structures-works/map';
-import {SEQUENCE_TYPES, COL_NAMES, GENERATED_COL_NAMES} from './constants';
-import {saltMass, saltMolWeigth, molecularWeight, batchMolWeight} from './calculations';
-import {isValidSequence} from '../structures-works/sequence-codes-tools';
-import {sequenceToMolV3000} from '../structures-works/from-monomers';
-import {linkStrandsV3000} from '../structures-works/mol-transformations';
-import {stringify, download, removeEmptyRows, differenceOfTwoArrays} from '../helpers';
-
-import {SALTS_CSV} from './salts';
-import {USERS_CSV} from './users';
-import {ICDS} from './ICDs';
-import {SOURCES} from './sources';
-import {IDPS} from './IDPs';
-
-import {sdfAddColumns} from '../utils/sdf-add-columns';
-import {sdfSaveTable} from '../utils/sdf-save-table';
-
-const enum SEQ_TYPE {
-  AS = 'AS',
-  SS = 'SS',
-  DUPLEX = 'Duplex',
-  DIMER = 'Dimer',
-}
-
-/** Computable classes of sequence types */
-const enum SEQ_TYPE_CLASS {
-  AS_OR_SS,
-  DUPLEX,
-  DIMER,
-}
-
-/** Style used for a cell with invalid value  */
-const errorStyle = {
-  'background-color': '#ff8080',
-  'width': '100%',
-  'height': '100%',
-};
-
-export function sdfHandleErrorUI(msgPrefix: string, df: DG.DataFrame, rowI: number, err: any) {
-  const errStr: string = err.toString();
-  const errMsg: string = msgPrefix + `row #${rowI + 1}, name: '${df.get('Chemistry Name', rowI)}', ` +
-    `type: ${df.get('Type', rowI)} error: ${errStr}.`;
-  grok.shell.warning(errMsg);
-}
-
-// todo: use a dictionary instead?
-function getActualTypeClass(actualType: string): SEQ_TYPE_CLASS {
-  if (actualType === SEQ_TYPE.AS || actualType === SEQ_TYPE.SS)
-    return SEQ_TYPE_CLASS.AS_OR_SS;
-  else if (actualType === SEQ_TYPE.DIMER)
-    return SEQ_TYPE_CLASS.DIMER;
-  else if (actualType === SEQ_TYPE.DUPLEX)
-    return SEQ_TYPE_CLASS.DUPLEX;
-  else
-    throw new Error('Some types in \'Types\' column are invalid ');
-}
-
-function inferTypeClassFromSequence(seq: string): SEQ_TYPE_CLASS {
-  const lines = seq.split('\n');
-  if (lines.length === 1)
-    return SEQ_TYPE_CLASS.AS_OR_SS;
-  else if (lines.length === 2)
-    return SEQ_TYPE_CLASS.DUPLEX;
-  else if (lines.length === 3)
-    return SEQ_TYPE_CLASS.DIMER;
-  else
-    throw new Error('Wrong formatting of sequences in \'Sequence\' column');
-  //todo: throw in the case of wrong formatting
-}
-
-/** Compare type specified in 'Type' column to that computed from 'Sequence' column  */
-function validateType(actualType: string, seq: string): boolean {
-  return getActualTypeClass(actualType) === inferTypeClassFromSequence(seq);
-}
-
-function oligoSdFileGrid(view: DG.TableView): void {
-  const typeColName = 'Type';
-  const seqColName = 'Sequence';
-  const grid = view.grid;
-  const df = view.dataFrame;
-  const typeCol = df.getCol(typeColName);
-  grid.columns.byName(typeColName)!.cellType = 'html';
-  const seqCol = df.getCol(seqColName);
-  grid.onCellPrepare((gridCell: DG.GridCell) => {
-    if (gridCell.isTableCell && gridCell.gridColumn.column!.name === typeColName) {
-      const isValidType = validateType(gridCell.cell.value, seqCol.get(gridCell.tableRow!.idx));
-      gridCell.style.element = ui.div(gridCell.cell.value, isValidType ? {} : {style: errorStyle});
-    }
-  });
-}
-
-export function autostartOligoSdFileSubscription() {
-  grok.events.onViewAdded.subscribe((v: any) => {
-    if (v.type === DG.VIEW_TYPE.TABLE_VIEW) {
-      if (v.dataFrame.columns.contains(COL_NAMES.TYPE)) {
-        oligoSdFileGrid(v);
-        oligoSdFile(v.dataFrame);
-      }
-
-      // Should be removed after fixing bug https://github.com/datagrok-ai/public/issues/808
-      grok.events.onContextMenu.subscribe((args) => {
-        if (!(args.args.context instanceof DG.Grid)) return;
-        const grid: DG.Grid = args.args.context as DG.Grid;
-        const menu: DG.Menu = args.args.menu;
-
-        const seqCol = grid.table.currentCol; // /^[fsACGUacgu]{6,}$/
-        if (DG.Detector.sampleCategories(seqCol,
-          (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C){6,}$/.test(s))) {
-          menu.item('Convert raw nucleotides to GCRS', () => {
-            grid.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
-              return siRnaNucleotidesToGcrs(seqCol.get(i));
-            });
-          });
-        } else if (DG.Detector.sampleCategories(seqCol,
-          (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|f|s|A|C|G|U|a|c|g|u){6,}$/.test(s))) {
-          menu.item('Convert Axolabs to GCRS', () => {
-            grid.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
-              return siRnaAxolabsToGcrs(seqCol.get(i));
-            });
-          }); // /^[fmpsACGU]{6,}$/
-        } else if (DG.Detector.sampleCategories(seqCol,
-            (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|f|m|ps|A|C|G|U){6,}$/.test(s)) ||
-          DG.Detector.sampleCategories(seqCol, (s) => /^(?=.*moe)(?=.*5mC)(?=.*ps){6,}/.test(s))) {
-          menu.item('Convert GCRS to raw', () => {
-            grid.table.columns.addNewString(seqCol.name + ' to raw').init((i: number) => {
-              return gcrsToNucleotides(seqCol.get(i));
-            });
-          });
-          menu.item('Convert GCRS to MM12', () => {
-            grid.table.columns.addNewString(seqCol.name + ' to MM12').init((i: number) => {
-              return gcrsToMermade12(seqCol.get(i));
-            });
-          }); // /^[*56789ATGC]{6,}$/
-        } else if (DG.Detector.sampleCategories(seqCol,
-          (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|\*|5|6|7|8|9|A|T|G|C){6,}$/.test(s))) {
-          menu.item('Convert Biospring to GCRS', () => {
-            const seqCol = grid.table.currentCol;
-            grid.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
-              return asoGapmersBioSpringToGcrs(seqCol.get(i));
-            });
-          }); // /^[*1-8]{6,}$/
-        } else if (DG.Detector.sampleCategories(seqCol,
-          (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|\*|1|2|3|4|5|6|7|8){6,}$/.test(s))) {
-          menu.item('Convert Biospring to GCRS', () => {
-            grid.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
-              return siRnaBioSpringToGcrs(seqCol.get(i));
-            });
-          });
-        }
-      });
-    }
-  });
-}
-
-export function oligoSdFile(table: DG.DataFrame) {
-  const saltsDf = DG.DataFrame.fromCsv(SALTS_CSV);
-  const usersDf = DG.DataFrame.fromCsv(USERS_CSV);
-  const sourcesDf = DG.DataFrame.fromCsv(SOURCES);
-  const icdsDf = DG.DataFrame.fromCsv(ICDS);
-  const idpsDf = DG.DataFrame.fromCsv(IDPS);
-
-  const saltCol = table.getCol(COL_NAMES.SALT);
-  const equivalentsCol = table.getCol(COL_NAMES.EQUIVALENTS);
-
-  const saltsMolWeightList: number[] = saltsDf.getCol('MOLWEIGHT').toList();
-  const saltNamesList: string[] = saltsDf.getCol('DISPLAY').toList();
-
-  let newDf: DG.DataFrame | undefined = undefined;
-
-  const d = ui.div([
-    ui.icons.edit(() => {
-      d.innerHTML = '';
-      if (table.getCol(COL_NAMES.IDP).type != DG.COLUMN_TYPE.STRING)
-        table.changeColumnType(COL_NAMES.IDP, DG.COLUMN_TYPE.STRING);
-      d.append(
-        ui.divH([
-          ui.button('Add columns',
-            () => {
-              newDf = sdfAddColumns(table, saltNamesList, saltsMolWeightList,
-                (rowI, err) => { sdfHandleErrorUI('Error on ', table, rowI, err); });
-              grok.shell.getTableView(newDf.name).grid.columns.setOrder(Object.values(COL_NAMES));
-            },
-            `Add columns: '${GENERATED_COL_NAMES.join(`', '`)}'`),
-          ui.bigButton('Save SDF', () => {
-            const df: DG.DataFrame = newDf ?? table;
-            sdfSaveTable(df,
-              (rowI, err) => { sdfHandleErrorUI('Skip ', df, rowI, err); });
-          }, 'Save SD file'),
-        ])
-      );
-
-      const view = grok.shell.getTableView(table.name);
-      view.grid.setOptions({rowHeight: 45});
-      view.dataFrame.getCol(COL_NAMES.TYPE).setTag(DG.TAGS.CHOICES, stringify(Object.values(SEQUENCE_TYPES)));
-      view.dataFrame.getCol(COL_NAMES.OWNER).setTag(DG.TAGS.CHOICES, stringify(usersDf.columns.byIndex(0).toList()));
-      view.dataFrame.getCol(COL_NAMES.SALT).setTag(DG.TAGS.CHOICES, stringify(saltsDf.columns.byIndex(0).toList()));
-      view.dataFrame.getCol(COL_NAMES.SOURCE).setTag(DG.TAGS.CHOICES, stringify(sourcesDf.columns.byIndex(0).toList()));
-      view.dataFrame.getCol(COL_NAMES.ICD).setTag(DG.TAGS.CHOICES, stringify(icdsDf.columns.byIndex(0).toList()));
-      view.dataFrame.getCol(COL_NAMES.IDP).setTag(DG.TAGS.CHOICES, stringify(idpsDf.columns.byIndex(0).toList()));
-
-      grok.events.onContextMenu.subscribe((args) => {
-        if (!(args.args.context instanceof DG.Grid)) return;
-        const grid: DG.Grid = args.args.context as DG.Grid;
-        const menu: DG.Menu = args.args.menu;
-
-        if ([COL_NAMES.TYPE, COL_NAMES.OWNER, COL_NAMES.SALT, COL_NAMES.SOURCE, COL_NAMES.ICD, COL_NAMES.IDP]
-          .includes(grid.table.currentCol.name)) {
-          menu.item('Fill Column With Value', () => {
-            const v = grid.table.currentCell.value;
-            grid.table.currentCell.column.init(v);
-            for (let i = 0; i < view.dataFrame.rowCount; i++)
-              updateCalculatedColumns(view.dataFrame, i);
-          });
-        }
-      });
-
-      view.dataFrame.onDataChanged.subscribe(() => {
-        const colName = view.dataFrame.currentCol.name;
-        if ([COL_NAMES.SALT, COL_NAMES.EQUIVALENTS, COL_NAMES.SALT_MOL_WEIGHT].includes(colName))
-          updateCalculatedColumns(view.dataFrame, view.dataFrame.currentRowIdx);
-      });
-
-      function updateCalculatedColumns(t: DG.DataFrame, i: number): void {
-        const smValue = saltMass(saltNamesList, saltsMolWeightList, equivalentsCol, i, saltCol);
-        t.getCol(COL_NAMES.SALT_MASS).set(i, smValue, false);
-        const smwValue = saltMolWeigth(saltNamesList, saltCol, saltsMolWeightList, i);
-        t.getCol(COL_NAMES.SALT_MOL_WEIGHT).set(i, smwValue, false);
-        const bmw = batchMolWeight(t.getCol(COL_NAMES.COMPOUND_MOL_WEIGHT), t.getCol(COL_NAMES.SALT_MASS), i);
-        t.getCol(COL_NAMES.BATCH_MOL_WEIGHT).set(i, bmw, false);
-      }
-    }),
-  ]);
-  grok.shell.v.setRibbonPanels([[d]]);
-}

package/src/autostart/salts.ts

@@ -1,2 +0,0 @@
-export const SALTS_CSV = `DISPLAY,MOLWEIGHT
-no Data Added,100`;

package/src/autostart/sources.ts

@@ -1,3 +0,0 @@
-export const SOURCES = `DISPLAY
-NO DATA
-`;

package/src/autostart/users.ts

@@ -1,3 +0,0 @@
-export const USERS_CSV = `DISPLAY
-NO DATA
-`;

package/src/axolabs/constants.ts

@@ -1,101 +0,0 @@
-const RNA_COLOR = 'rgb(255,230,153)';
-const INVABASIC_COLOR = 'rgb(203,119,211)';
-export const AXOLABS_MAP:
-  {[index: string]: {fullName: string, symbols: [string, string, string, string], color: string}} =
-{
-  'RNA': {
-    fullName: 'RNA nucleotides',
-    symbols: ['A', 'C', 'G', 'U'],
-    color: RNA_COLOR,
-  },
-  'DNA': {
-    fullName: 'DNA nucleotides',
-    symbols: ['dA', 'dC', 'dG', 'dT'],
-    color: 'rgb(197,224,180)',
-  },
-  "2\"-Fluoro": {
-    fullName: '2\'-Fluoro nucleotides',
-    symbols: ['Af', 'Cf', 'Gf', 'Uf'],
-    color: 'rgb(68,114,196)',
-  },
-  "2\"-O-Methyl": {
-    fullName: '2\'-O-Methyl nucleotides',
-    symbols: ['a', 'c', 'g', 'u'],
-    color: 'rgb(166,166,166)',
-  },
-  "2\"-O-MOE": {
-    fullName: '2\'-O-MOE nucleotides (including 5-Methyl C)',
-    symbols: ['Am', 'Cm', 'Gm', 'Tm'],
-    color: 'rgb(112,48,160)',
-  },
-  'GNA': {
-    fullName: 'Glycol nucleic acid',
-    symbols: ['(GNA-A)', '(GNA-C)', '(GNA-G)', '(GNA-T)'],
-    color: 'rgb(255,192,0)',
-  },
-  'LNA': {
-    fullName: 'Locked nucleic acid (including 5-Methyl C)',
-    symbols: ['Ab', 'Cb', 'Gb', 'Tb'],
-    color: 'rgb(54,229,238)',
-  },
-  'UNA': {
-    fullName: 'Unlocked nucleotides',
-    symbols: ['Ao', 'Co', 'Go', 'Uo'],
-    color: 'rgb(255,192,0)',
-  },
-  'A': {
-    fullName: 'Adenosine',
-    symbols: ['a', 'a', 'a', 'a'],
-    color: RNA_COLOR,
-  },
-  'C': {
-    fullName: 'Cytidine',
-    symbols: ['c', 'c', 'c', 'c'],
-    color: RNA_COLOR,
-  },
-  'G': {
-    fullName: 'Guanosine',
-    symbols: ['g', 'g', 'g', 'g'],
-    color: RNA_COLOR,
-  },
-  'U': {
-    fullName: 'Uridine',
-    symbols: ['u', 'u', 'u', 'u'],
-    color: RNA_COLOR,
-  },
-  'X-New': {
-    fullName: '',
-    symbols: ['X', 'X', 'X', 'X'],
-    color: 'rgb(108,0,0)',
-  },
-  'Y-New': {
-    fullName: '',
-    symbols: ['Y', 'Y', 'Y', 'Y'],
-    color: 'rgb(210,146,146)',
-  },
-  'Z-New': {
-    fullName: '',
-    symbols: ['Z', 'Z', 'Z', 'Z'],
-    color: 'rgb(155,108,132)',
-  },
-  'InvAbasic': {
-    fullName: 'Inverted abasic capped',
-    symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: INVABASIC_COLOR,
-  },
-  "5\"-vinylps": {
-    fullName: '5\'-vinylphosphonate-2\'-OMe-uridine',
-    symbols: ['(vinu)', '(vinu)', '(vinu)', '(vinu)'],
-    color: 'rgb(0,0,139)',
-  },
-  'InvAbasic(o)': {
-    fullName: 'Inverted abasic capped (overhang)',
-    symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: INVABASIC_COLOR,
-  },
-  "2\"-OMe-U(o)": {
-    fullName: 'Nucleotide Uridine with 2\'O-Methyl protection (overhang)',
-    symbols: ['mU', 'mU', 'mU', 'mU'],
-    color: 'rgb(65,233,80)',
-  },
-};