@datagrok/peptides 0.7.1 → 0.8.7

package/.eslintrc.json

@@ -23,7 +23,17 @@
       "error",
       120
     ],
+    "require-jsdoc": "off",
     "spaced-comment": "off",
-    "require-jsdoc": "off"
+    "linebreak-style": "off",
+    "curly": [
+      "error",
+      "multi-or-nest"
+    ],
+    "brace-style": [
+      "error",
+      "1tbs",
+      { "allowSingleLine": true }
+    ]
   }
-}
+}

package/files/aligned_2.csv

@@ -10272,4 +10272,4 @@ ID,AlignedSequence,Measured,Value
 1357,HOC18gEPEG2PEG2-k(Me3)-Aib-K(PEG2PEG2PgEC18OH)-Hyp-7(4OCF3Ph)W-K(Me)3-S5H(4)-mTyr-6OH2Nal  6OH2Nal-aMeK-S5H-3Pya-H-4diFPro-PEG2PEG2eKC16OH-ON(Me)2A,SGF (No protein present) % Remaining 24 hr,86.31581627936768
 1359,HOC18gEPEG2PEG2-k(Me3)-Aib-K(PEG2PEG2PgEC18OH)-Hyp-7(4OCF3Ph)W-K(Me)3-S5H(4)-mTyr-6OH2Nal  6OH2Nal-aMeK-S5H-3Pya-homobAla-4diFPro-PEG2PEG2eKC16OH-ON(Me)2A,SGF (No protein present) % Remaining 24 hr,93.44441627936769
 1360,HOC18gEPEG2PEG2-k(Me3)-Aib-K(PEG2PEG2PgEC18OH)-Hyp-7(4OCF3Ph)W-K(Me)3-S5H(4)-mTyr-6OH2Nal  6OH2Nal-aMeK-S5H-3Pya-D(NPyr)-4diFPro-PEG2PEG2eKC16OH-ON(Me)2A,SGF (No protein present) % Remaining 24 hr,88.34951627936769
-1361,HOC18gEPEG2PEG2-k(Me3)-Aib-K(PEG2PEG2PgEC18OH)-Hyp-7(4OCF3Ph)W-K(Me)3-S5H(4)-mTyr-6OH2Nal  6OH2Nal-aMeK-S5H-3Pya-3OHPhe-4diFPro-PEG2PEG2eKC16OH-ON(Me)2A,SGF (No protein present) % Remaining 24 hr,98.38061627936769
+1361,HOC18gEPEG2PEG2-k(Me3)-Aib-K(PEG2PEG2PgEC18OH)-Hyp-7(4OCF3Ph)W-K(Me)3-S5H(4)-mTyr-6OH2Nal  6OH2Nal-aMeK-S5H-3Pya-3OHPhe-4diFPro-PEG2PEG2eKC16OH-ON(Me)2A,SGF (No protein present) % Remaining 24 hr,98.38061627936769

package/package.json

@@ -1,31 +1,33 @@
 {
 	"name": "@datagrok/peptides",
-	"version": "0.7.1",
+	"version": "0.8.7",
 	"description": "",
 	"dependencies": {
+		"@biowasm/aioli": ">=2.4.0",
+		"@datagrok-libraries/bio": ">=0.0.4",
+		"@datagrok-libraries/ml": ">=0.0.14",
+		"@datagrok-libraries/statistics": ">=0.1.5",
+		"@datagrok-libraries/utils": ">=0.0.22",
+		"@types/d3": "^7.0.0",
+		"@types/jquery": "^3.5.6",
 		"cash-dom": "latest",
 		"d3": "latest",
-		"datagrok-api": ">=0.104.0",
+		"datagrok-api": ">=0.115.0",
 		"dayjs": "latest",
+		"file-loader": "^6.2.0",
 		"jstat": "^1.9.5",
 		"logojs-react": "^2.1.1",
-		"rxjs": "^6.5.5",
-		"@datagrok-libraries/utils": ">=0.0.13",
-		"@datagrok-libraries/statistics": ">=0.1.5",
-		"@datagrok-libraries/ml": ">=0.0.1",
-		"@datagrok-libraries/bio": ">=0.0.4",
-		"@types/d3": "^7.0.0",
-		"@types/jquery": "^3.5.6"
+		"rxjs": "^6.5.5"
 	},
 	"devDependencies": {
-		"typescript": "^4.4.4",
-		"ts-loader": "^9.2.5",
-		"css-loader": "^5.2.4",
-		"style-loader": "^2.0.0",
 		"@typescript-eslint/eslint-plugin": "^4.29.1",
 		"@typescript-eslint/parser": "^4.29.1",
+		"css-loader": "^5.2.4",
 		"eslint": "^7.32.0",
 		"eslint-config-google": "^0.14.0",
+		"style-loader": "^2.0.0",
+		"ts-loader": "^9.2.5",
+		"typescript": "^4.4.4",
 		"webpack": "latest",
 		"webpack-cli": "latest"
 	},
@@ -55,6 +57,10 @@
 		"lint": "eslint \"./src/**/*.ts\"",
 		"lint-fix": "eslint \"./src/**/*.ts\" --fix"
 	},
-	"canEdit": [ "Developers" ],
-	"canView": [ "All users" ]
+	"canEdit": [
+		"Developers"
+	],
+	"canView": [
+		"All users"
+	]
 }

package/setup.sh

@@ -0,0 +1,15 @@
+npm unlink datagrok-api
+npm unlink @datagrok-libraries/utils
+npm unlink @datagrok-libraries/ml
+cd ../../js-api
+npm install
+npm link
+cd ../libraries/utils
+npm install
+npm link
+cd ../../libraries/ml
+npm install
+npm link datagrok-api @datagrok-libraries/utils
+cd ../../packages/Peptides
+npm install
+npm link datagrok-api @datagrok-libraries/utils @datagrok-libraries/ml 

package/src/describe.ts

@@ -3,6 +3,7 @@ import * as DG from 'datagrok-api/dg';
 import {splitAlignedPeptides} from './utils/split-aligned';
 import {tTest} from '@datagrok-libraries/statistics/src/tests';
 import {fdrcorrection} from '@datagrok-libraries/statistics/src/multiple-tests';
+import {StringDictionary} from '@datagrok-libraries/utils/src/type-declarations';
 import {ChemPalette} from './utils/chem-palette';
 import {setAARRenderer} from './utils/cell-renderer';
 
@@ -60,41 +61,38 @@ function joinDataFrames(
   splitSeqDf: DG.DataFrame,
   activityColumn: string,
 ) {
-  if (df.col(activityColumnScaled)) {
-    df.columns.remove(activityColumnScaled);
-  }
+  if (df.col(activityColumnScaled))
+  (df.columns as DG.ColumnList).remove(activityColumnScaled);
+
 
   //FIXME: this column usually duplicates, so remove it then
-  if (df.col(`${activityColumnScaled} (2)`)) {
-    df.columns.remove(`${activityColumnScaled} (2)`);
-  }
+  if (df.col(`${activityColumnScaled} (2)`))
+    (df.columns as DG.ColumnList).remove(`${activityColumnScaled} (2)`);
+
 
   // append splitSeqDf columns to source table and make sure columns are not added more than once
   const dfColsSet = new Set(df.columns.names());
-  if (!positionColumns.every((col: string) => dfColsSet.has(col))) {
+  if (!positionColumns.every((col: string) => dfColsSet.has(col)))
     df.join(splitSeqDf, [activityColumn], [activityColumn], df.columns.names(), positionColumns, 'inner', true);
-  }
 }
 
 function sortSourceGrid(sourceGrid: DG.Grid) {
   if (sourceGrid) {
-    const colNames:string[] = [];
-    for (let i = 0; i < sourceGrid.columns.length; i++) {
-      colNames.push(sourceGrid.columns.byIndex(i)!.name);
-    }
+    const colNames: DG.GridColumn[] = [];
+    for (let i = 1; i < sourceGrid.columns.length; i++)
+      colNames.push(sourceGrid.columns.byIndex(i)!);
+
     colNames.sort((a, b)=>{
-      if (sourceGrid.columns.byName(a)?.column?.semType == 'aminoAcids') {
-        if (sourceGrid.columns.byName(b)?.column?.semType == 'aminoAcids') {
+      if (a.column!.semType == 'aminoAcids') {
+        if (b.column!.semType == 'aminoAcids')
           return 0;
-        }
         return -1;
       }
-      if (sourceGrid.columns.byName(b)?.column?.semType == 'aminoAcids') {
+      if (b.column!.semType == 'aminoAcids')
         return 1;
-      }
       return 0;
     });
-    sourceGrid?.columns.setOrder(colNames);
+    sourceGrid.columns.setOrder(colNames.map((v) => v.name));
   }
 }
 
@@ -135,7 +133,7 @@ async function calculateStatistics(
   activityColumnScaled: string,
   peptidesCount: number,
   splitSeqDf: DG.DataFrame,
-  groupMapping: {[key: string]: string},
+  groupMapping: StringDictionary,
 ) {
   matrixDf = matrixDf.groupBy([positionColName, aminoAcidResidue])
     .add('count', activityColumnScaled, 'Count')
@@ -180,13 +178,13 @@ async function calculateStatistics(
     pvalues[i] = pvalue;
   }
 
-  if (true) {
+  if (true)
     pvalues = fdrcorrection(pvalues)[1];
-  }
 
-  for (let i = 0; i < pvalues.length; ++i) {
+
+  for (let i = 0; i < pvalues.length; ++i)
     pValCol.set(i, pvalues[i]);
-  }
+
 
   return matrixDf.clone();
 }
@@ -195,9 +193,9 @@ async function setCategoryOrder(
   twoColorMode: boolean, statsDf: DG.DataFrame, aminoAcidResidue: string, matrixDf: DG.DataFrame,
 ) {
   const sortArgument = twoColorMode ? 'Absolute Mean difference' : 'Mean difference';
-  if (twoColorMode) {
+  if (twoColorMode)
     await statsDf.columns.addNewCalculated('Absolute Mean difference', 'Abs(${Mean difference})');
-  }
+
   const aarWeightsDf = statsDf.groupBy([aminoAcidResidue]).sum(sortArgument, 'weight').aggregate();
   const aarList = aarWeightsDf.getCol(aminoAcidResidue).toList();
   const getWeight = (aar: string) => aarWeightsDf
@@ -257,13 +255,12 @@ function createGrids(
 
   if (!grouping) {
     let tempCol = matrixDf.columns.byName(aminoAcidResidue);
-    if (tempCol) {
+    if (tempCol)
       setAARRenderer(tempCol, sarGrid);
-    }
+
     tempCol = sequenceDf.columns.byName(aminoAcidResidue);
-    if (tempCol) {
+    if (tempCol)
       setAARRenderer(tempCol, sarGrid);
-    }
   }
 
   return [sarGrid, sarVGrid];
@@ -308,15 +305,15 @@ function setCellRendererFunc(
 
         let coef;
         const variant = args.cell.cell.value < 0;
-        if (pVal < 0.01) {
+        if (pVal < 0.01)
           coef = variant && twoColorMode ? '#FF7900' : '#299617';
-        } else if (pVal < 0.05) {
+        else if (pVal < 0.05)
           coef = variant && twoColorMode ? '#FFA500' : '#32CD32';
-        } else if (pVal < 0.1) {
+        else if (pVal < 0.1)
           coef = variant && twoColorMode ? '#FBCEB1' : '#98FF98';
-        } else {
+        else
           coef = DG.Color.toHtml(DG.Color.lightLightGray);
-        }
+
 
         const chooseMin = () => twoColorMode ? 0 : mdCol.min;
         const chooseMax = () => twoColorMode ? Math.max(Math.abs(mdCol.min), mdCol.max) : mdCol.max;
@@ -380,11 +377,11 @@ function setTooltipFunc(
           const textNum = statsDf.groupBy([col]).where(query).aggregate().get(col, 0);
           let text = `${col === 'Count' ? textNum : textNum.toFixed(5)}`;
 
-          if (col === 'Count') {
+          if (col === 'Count')
             text += ` / ${peptidesCount}`;
-          } else if (col === 'pValue') {
+          else if (col === 'pValue')
             text = parseFloat(text) !== 0 ? text : '<0.01';
-          }
+
 
           tooltipMap[col === 'pValue' ? 'p-value' : col] = text;
         }
@@ -403,9 +400,8 @@ function setTooltipFunc(
         const currentGroup = groupDescription[cell.cell.value];
         const divText = ui.divText('Amino Acids in this group: ' + currentGroup['aminoAcids'].join(', '));
         ui.tooltip.show(ui.divV([ui.h3(currentGroup['description']), divText]), x, y);
-      } else {
+      } else
         cp.showTooltip(cell, x, y);
-      }
     }
     return true;
   };
@@ -424,14 +420,13 @@ function postProcessGrids(
 ) {
   sourceGrid.onCellPrepare((cell: DG.GridCell) => {
     const currentRowIndex = cell.tableRowIndex;
-    if (currentRowIndex && invalidIndexes.includes(currentRowIndex) && !cell.isRowHeader) {
+    if (currentRowIndex && invalidIndexes.includes(currentRowIndex) && !cell.isRowHeader)
       cell.style.backColor = DG.Color.lightLightGray;
-    }
   });
 
-  for (const col of matrixDf.columns.names()) {
+  for (const col of matrixDf.columns.names())
     sarGrid.col(col)!.width = sarGrid.props.rowHeight;
-  }
+
 
   if (grouping) {
     sarGrid.col(aminoAcidResidue)!.name = 'Groups';
@@ -440,6 +435,8 @@ function postProcessGrids(
 
   sarGrid.props.allowEdit = false;
   sarVGrid.props.allowEdit = false;
+
+  sarVGrid.col('Mean difference')!.name = 'Diff';
 }
 
 export async function describe(
@@ -450,7 +447,7 @@ export async function describe(
   twoColorMode: boolean,
   initialBitset: DG.BitSet | null,
   grouping: boolean,
-): Promise<[DG.Grid, DG.Grid, DG.DataFrame, {[key: string]: string}]> {
+): Promise<[DG.Grid, DG.Grid, DG.DataFrame, StringDictionary]> {
   //Split the aligned sequence into separate AARs
   let splitSeqDf: DG.DataFrame | undefined;
   let invalidIndexes: number[];
@@ -469,9 +466,8 @@ export async function describe(
   joinDataFrames(activityColumnScaled, df, positionColumns, splitSeqDf, activityColumn);
 
   for (const col of df.columns) {
-    if (splitSeqDf.col(col.name) && col.name != activityColumn) {
+    if (splitSeqDf.col(col.name) && col.name != activityColumn)
       setAARRenderer(col, sourceGrid);
-    }
   }
 
   sortSourceGrid(sourceGrid);
@@ -489,15 +485,15 @@ export async function describe(
   let matrixDf = splitSeqDf.unpivot([activityColumnScaled], positionColumns, positionColName, aminoAcidResidue);
 
   //TODO: move to chem palette
-  let groupMapping: {[key: string]: string} = {};
+  let groupMapping: StringDictionary = {};
   if (grouping) {
     groupMapping = aarGroups;
     const aarCol = matrixDf.getCol(aminoAcidResidue);
     aarCol.init((index) => groupMapping[aarCol.get(index)[0]] ?? '-');
     aarCol.compact();
-  } else {
+  } else
     Object.keys(aarGroups).forEach((value) => groupMapping[value] = value);
-  }
+
 
   //statistics for specific AAR at a specific position
   const statsDf = await calculateStatistics(

package/src/model.ts

@@ -2,6 +2,7 @@ import * as DG from 'datagrok-api/dg';
 
 import {describe} from './describe';
 import {Subject} from 'rxjs';
+import {StringDictionary} from '@datagrok-libraries/utils/src/type-declarations';
 
 /**
  * Model class for SAR viewers that retrieves and stores data.
@@ -12,7 +13,7 @@ class SARViewerModel {
   private viewerGrid: Subject<DG.Grid> = new Subject<DG.Grid>();
   private viewerVGrid: Subject<DG.Grid> = new Subject<DG.Grid>();
   private statsDf: Subject<DG.DataFrame> = new Subject<DG.DataFrame>();
-  private groupMapping: Subject<{[key: string]: string}> = new Subject<{[key: string]: string}>();
+  private groupMapping: Subject<StringDictionary> = new Subject<StringDictionary>();
   public viewerGrid$;
   public viewerVGrid$;
   public statsDf$;

package/src/monomer-library.ts

@@ -0,0 +1,187 @@
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+import * as grok from 'datagrok-api/grok';
+
+/** HELM associated sdf libraries with monomer processing*/
+export class MonomerLibrary {
+  private monomerFields: string[] = ['molecule', 'MonomerType', 'MonomerNaturalAnalogCode', 'MonomerName', 'MonomerCode', 'MonomerCaps', 'BranchMonomer'];
+  private library: {
+    [name: string]: {
+      mol: string,
+      type: string,
+      analogueCode: string,
+      linkages: { [link: string]: { atomNumber: number, type: string } }
+    }
+  } = {};
+  private monomers: string[] = [];
+
+  constructor(sdf: string) {
+    //sdf = sdf.replaceAll('\n\[', '\[');
+    const sdfReader = new SDFReader();
+    const data = sdfReader.get_colls(sdf);
+    this.monomerFields.forEach((f) => {
+      if (!(f in data))
+        throw `Monomer library was not compiled: ${f} field is absent in provided file`;
+
+      if (data[f].length != data.molecule.length)
+        throw `Monomer library was not compiled: ${f} field is not presented for each monomer`;
+    });
+
+    for (let i = 0; i < data.molecule.length; i++) {
+      const linkData = this.getLinkData(data.molecule[i], data.MonomerCaps[i], data.MonomerName[i]);
+      const entry = {
+        mol: data.molecule[i],
+        type: 'Peptide',
+        code: data.MonomerCode[i],
+        analogueCode: data.MonomerNaturalAnalogCode[i],
+        linkages: linkData,
+      };
+
+      const name = data.MonomerCode[i] !== '.' ? data.MonomerCode[i] : data.MonomerName[i];
+      this.library[name] = entry;
+      this.monomers.push(data.MonomerName[i]);
+    }
+  }
+
+  /** getting full monomer information from monomer library*/
+  public getMonomerEntry(name: string) {
+    if (!this.monomers.includes(name))
+      throw `Monomer library do not contain ${name} monomer`;
+
+
+    return this.library[name];
+  }
+
+  /** getting mol as string for monomer*/
+  public getMonomerMol(name: string) {
+    if (!this.monomers.includes(name))
+      throw `Monomer library do not contain ${name} monomer`;
+
+
+    const entry = this.library[name];
+    let monomerMol = entry.mol.replace(/M  RGP  .+\n/, '');
+
+    //order matters
+    const links = Object.keys(entry.linkages);
+    for (let i = 0; i < links.length; i++)
+      monomerMol = monomerMol.replace('R#', entry.linkages[links[i]].type + ' ');
+
+
+    return monomerMol;
+  }
+
+  /** getting the list of the minomers available in library*/
+  get monomerNames() {
+    return this.monomers;
+  }
+
+  private getLinkData(mol: string, caps: string, name: string) {
+    const rawData = mol.match(/M  RGP  .+/);
+    if (rawData === null)
+      throw `Monomer library was not compiled: ${name} entry has no RGP`;
+
+
+    const types: { [code: string]: string } = {};
+    caps.split('\n')?.forEach((e) => {
+      types[e.match(/\d+/)![0]] = e.match(/(?<=\])\w+/)![0];
+    });
+
+    const data = rawData![0].replace('M  RGP  ', '').split(/\s+/);
+    const res: { [link: string]: { atomNumber: number, type: string } } = {};
+    for (let i = 0; i < parseInt(data[0]); i++) {
+      const code = parseInt(data[2 * i + 2]);
+      let type = '';
+      switch (code) {
+      case 1:
+        type = 'N-terminal';
+        break;
+      case 2:
+        type = 'C-terminal';
+        break;
+      case 3:
+        type = 'branch';
+        break;
+      default:
+        break;
+      }
+      res[type] = {atomNumber: parseInt(data[2 * i + 1]), type: types[code]};
+    }
+
+    return res;
+  }
+}
+
+//TODO: merge with Chem version
+class SDFReader {
+  dataColls: { [_: string]: any };
+
+  constructor() {
+    this.dataColls = {'molecule': []};
+  }
+
+  get_colls(content: string) {
+    this.read(content);
+    return this.dataColls;
+  }
+
+  read(content: string) {
+    content = content.replaceAll('\r', ''); //equalize old and new sdf standards
+    let startIndex = content.indexOf('$$$$', 0);
+    this.parse(content, 0, startIndex, (name: string, val: any) => { // TODO: type
+      this.dataColls[name] = [];
+      this.dataColls[name].push(val);
+    });
+    startIndex += 5;
+    while (startIndex > -1 && startIndex < content.length)
+      startIndex = this.readNext(content, startIndex);
+  }
+
+  readNext(content: string, startIndex: number) {
+    const nextStartIndex = content.indexOf('$$$$', startIndex);
+    if (nextStartIndex === -1)
+      return -1;
+    else {
+      this.parse(content, startIndex, nextStartIndex,
+        (name: string, val: number) => this.dataColls[name].push(val));
+    }
+
+    if (nextStartIndex > -1)
+      return nextStartIndex + 5;
+
+
+    return nextStartIndex;
+  }
+
+  parse(content: string, start: number, end: number, handler: any) {
+    const molEnd = +content.indexOf('M  END\n', start) + 7;
+    let localEnd = start;
+    this.dataColls['molecule'].push(content.substr(start, molEnd - start));
+
+    start = molEnd;
+    while (localEnd < end) {
+      start = content.indexOf('> <', localEnd);
+      if (start === -1)
+        return;
+
+
+      start += 3;
+      localEnd = content.indexOf('>\n', start);
+      if (localEnd === -1)
+        return;
+
+
+      const propertyName = content.substring(start, localEnd);
+      start = localEnd + 2;
+
+      localEnd = content.indexOf('\n', start);
+      if (localEnd === -1)
+        localEnd = end;
+      else if (content[localEnd + 1] != '\n')
+        localEnd = content.indexOf('\n', ++localEnd);
+      ;
+
+      handler(propertyName, content.substring(start, localEnd));
+      localEnd += 2;
+    }
+  }
+}

package/src/package-test.ts

@@ -0,0 +1,19 @@
+import * as DG from 'datagrok-api/dg';
+
+import {runTests} from '@datagrok-libraries/utils/src/test';
+
+import './tests/peptide-space-test';
+import './tests/peptides-tests';
+import './tests/msa-tests';
+
+export const _package = new DG.Package();
+
+//name: test
+//input: string category {optional: true}
+//input: string test {optional: true}
+//output: dataframe result
+//top-menu: Tools | Dev | JS API Tests
+export async function test(category: string, test: string): Promise<DG.DataFrame> {
+  const data = await runTests({category, test});
+  return DG.DataFrame.fromObjects(data)!;
+}