@datagrok/proteomics 1.2.1 → 1.3.0

package/src/tests/group-mean-correlation.ts

@@ -1,139 +0,0 @@
-import * as DG from 'datagrok-api/dg';
-import {category, test, expect} from '@datagrok-libraries/test/src/test';
-import {
-  createGroupMeanCorrelation,
-  computeGroupMeans,
-  pearson,
-  spearman,
-} from '../viewers/group-mean-correlation';
-import {setGroups} from '../analysis/experiment-setup';
-import {SEMTYPE} from '../utils/proteomics-types';
-
-/** Builds a 5-row, 4-sample fixture DataFrame with a `direction` column so the
- *  correlation viewer's color binding has something to point at. */
-function makeFixtureDf(): DG.DataFrame {
-  const cols: DG.Column[] = [];
-  const pid = DG.Column.fromStrings('Primary Protein ID',
-    ['P1', 'P2', 'P3', 'P4', 'P5']);
-  pid.semType = SEMTYPE.PROTEIN_ID;
-  cols.push(pid);
-
-  const display = DG.Column.fromStrings('Display Name',
-    ['Gene1', 'Gene2', 'Gene3', 'Gene4', 'Gene5']);
-  display.semType = SEMTYPE.DISPLAY_NAME;
-  cols.push(display);
-
-  // Intensities — known per-row mean of [g1,g2] is monotonic for groupMeanColumnsCreated.
-  // Row 0: g1={1,3}→mean=2, g2={5,7}→mean=6
-  // Row 1: g1={2,4}→mean=3, g2={6,8}→mean=7
-  // Row 2: g1={3,5}→mean=4, g2={7,9}→mean=8
-  // Row 3: g1={4,6}→mean=5, g2={8,10}→mean=9
-  // Row 4: g1={5,7}→mean=6, g2={9,11}→mean=10
-  cols.push(DG.Column.fromList('double' as DG.ColumnType, 'S1', [1, 2, 3, 4, 5]));
-  cols.push(DG.Column.fromList('double' as DG.ColumnType, 'S2', [3, 4, 5, 6, 7]));
-  cols.push(DG.Column.fromList('double' as DG.ColumnType, 'S3', [5, 6, 7, 8, 9]));
-  cols.push(DG.Column.fromList('double' as DG.ColumnType, 'S4', [7, 8, 9, 10, 11]));
-
-  // direction column — the viewer reads this for color binding (set by Plan 14-02 ensureDirectionColumn).
-  cols.push(DG.Column.fromStrings('direction',
-    ['Enriched in Control', 'Enriched in Treatment', 'Not significant',
-      'Enriched in Control', 'Enriched in Treatment']));
-
-  const df = DG.DataFrame.fromColumns(cols);
-  setGroups(df, {
-    group1: {name: 'Control', columns: ['S1', 'S2']},
-    group2: {name: 'Treatment', columns: ['S3', 'S4']},
-  });
-  df.name = `correlation-fixture-${Math.random().toString(36).slice(2, 8)}`;
-  return df;
-}
-
-category('Proteomics: 14-04', () => {
-  test('groupMeanColumnsCreated', async () => {
-    const df = makeFixtureDf();
-    computeGroupMeans(df, {
-      group1: {name: 'Control', columns: ['S1', 'S2']},
-      group2: {name: 'Treatment', columns: ['S3', 'S4']},
-    });
-    const num = df.col('Numerator Mean');
-    const den = df.col('Denominator Mean');
-    expect(num !== null, true);
-    expect(den !== null, true);
-    expect(num!.semType, SEMTYPE.NUMERATOR_MEAN);
-    expect(den!.semType, SEMTYPE.DENOMINATOR_MEAN);
-    expect(num!.length, df.rowCount);
-    expect(den!.length, df.rowCount);
-    // Row 0 means: g1=(1+3)/2=2, g2=(5+7)/2=6.
-    expect(Math.abs((num!.get(0) as number) - 2) < 1e-6, true);
-    expect(Math.abs((den!.get(0) as number) - 6) < 1e-6, true);
-    // Row 4 means: g1=(5+7)/2=6, g2=(9+11)/2=10.
-    expect(Math.abs((num!.get(4) as number) - 6) < 1e-6, true);
-    expect(Math.abs((den!.get(4) as number) - 10) < 1e-6, true);
-  });
-
-  test('groupMeanColumnsReRunSafe', async () => {
-    const df = makeFixtureDf();
-    const groups = {
-      group1: {name: 'Control', columns: ['S1', 'S2']},
-      group2: {name: 'Treatment', columns: ['S3', 'S4']},
-    };
-    computeGroupMeans(df, groups);
-    computeGroupMeans(df, groups);
-    // No duplicates after a second invocation.
-    const numCount = df.columns.toList().filter((c) => c.name === 'Numerator Mean').length;
-    const denCount = df.columns.toList().filter((c) => c.name === 'Denominator Mean').length;
-    expect(numCount, 1);
-    expect(denCount, 1);
-    // Values still correct.
-    const num = df.col('Numerator Mean')!;
-    expect(Math.abs((num.get(0) as number) - 2) < 1e-6, true);
-  });
-
-  test('pearsonPerfectCorrelation', async () => {
-    const r = pearson([1, 2, 3, 4, 5], [2, 4, 6, 8, 10]);
-    expect(Math.abs(r - 1) < 1e-9, true);
-  });
-
-  test('pearsonNoCorrelation', async () => {
-    const r = pearson([1, 2, 3, 4, 5], [3, 1, 4, 1, 5]);
-    // Not exactly 0 — just within a reasonable tolerance away from 1.
-    expect(Math.abs(r) < 0.6, true);
-  });
-
-  test('spearmanRankTies', async () => {
-    const rho = spearman([1, 2, 2, 3, 4], [1, 2, 2, 3, 4]);
-    expect(Math.abs(rho - 1) < 1e-9, true);
-  });
-
-  test('createGroupMeanCorrelationFactory', async () => {
-    const df = makeFixtureDf();
-    const sp = createGroupMeanCorrelation(df);
-    expect(sp !== null, true);
-    const opts: any = (sp as any).getOptions?.();
-    const title: string = opts?.look?.title ?? '';
-    expect(title.includes('r='), true);
-    expect(title.includes('ρ='), true);
-    expect(sp.props.xColumnName, 'Numerator Mean');
-    expect(sp.props.yColumnName, 'Denominator Mean');
-    expect(sp.props.colorColumnName, 'direction');
-  });
-
-  test('correlationDiagonalLine', async () => {
-    const df = makeFixtureDf();
-    createGroupMeanCorrelation(df);
-    const lines = df.meta.formulaLines.items;
-    const diagonal = lines.find((l: any) => {
-      const f = (l.formula ?? '') as string;
-      return typeof f === 'string' &&
-        f.includes('Numerator Mean') && f.includes('Denominator Mean');
-    });
-    expect(diagonal !== undefined, true);
-    expect((diagonal as any).color, '#888888');
-  });
-
-  test('correlationLabelBindsToDisplayName', async () => {
-    const df = makeFixtureDf();
-    const sp = createGroupMeanCorrelation(df);
-    expect((sp.props.labelColumnNames as string[])?.includes('Display Name'), true);
-  });
-});

package/src/viewers/group-mean-correlation.ts

@@ -1,218 +0,0 @@
-import * as DG from 'datagrok-api/dg';
-import {findColumn} from '../utils/column-detection';
-import {SEMTYPE} from '../utils/proteomics-types';
-import {getGroups, GroupAssignment} from '../analysis/experiment-setup';
-
-/**
- * R4 / D-12 — Group-Mean Correlation viewer.
- *
- * Adds two derived columns to the host DataFrame (Numerator Mean, Denominator
- * Mean — means of the group1/group2 intensity columns per row) and renders
- * them as a scatter colored by the existing `direction` column (magenta/cyan/
- * gray per D-04). The viewer title carries inline Pearson r and Spearman ρ
- * over the current filter; a y=x diagonal reference line is drawn in #888888.
- *
- * The derived columns are re-run-safe via `ensureFreshFloat` — a second
- * invocation replaces the columns instead of duplicating them.
- *
- * Statistics: `@datagrok-libraries/statistics` exports only Kendall's tau,
- * so Pearson and Spearman are implemented inline (Pearson over raw values,
- * Spearman = Pearson over fractional ranks).
- */
-
-const NUMERATOR_MEAN_COL = 'Numerator Mean';
-const DENOMINATOR_MEAN_COL = 'Denominator Mean';
-const DIRECTION_COL = 'direction';
-const DIAGONAL_FORMULA = `\${${NUMERATOR_MEAN_COL}} = \${${DENOMINATOR_MEAN_COL}}`;
-const DIAGONAL_COLOR = '#888888';
-
-/** Bulk-init pattern — removes an existing column first to avoid duplicates on
- * re-run. Mirrors src/viewers/qc-computations.ts:28-32. */
-function ensureFreshFloat(df: DG.DataFrame, name: string): DG.Column {
-  if (df.columns.contains(name))
-    df.columns.remove(name);
-  return df.columns.addNewFloat(name);
-}
-
-/** Mean of non-null values across `cols` at `rowIdx`. Returns NaN if every
- * value is null. Mirrors qc-computations.ts:15-25. */
-function groupMean(cols: DG.Column[], rowIdx: number): number {
-  let sum = 0;
-  let n = 0;
-  for (const c of cols) {
-    if (c.isNone(rowIdx)) continue;
-    sum += c.get(rowIdx) as number;
-    n++;
-  }
-  return n > 0 ? sum / n : NaN;
-}
-
-/**
- * Derives Numerator Mean (group1) and Denominator Mean (group2) columns on
- * `df`. The join key is the protein row index — never a derived key like
- * gene name (project memory project_proteomics_deqms_result_misalignment).
- *
- * The columns carry the dedicated SEMTYPE.NUMERATOR_MEAN / SEMTYPE.DENOMINATOR_MEAN
- * tags so downstream tooling can find them via `findColumn`.
- */
-export function computeGroupMeans(df: DG.DataFrame, groups: GroupAssignment): void {
-  const g1Cols = groups.group1.columns
-    .map((n) => df.col(n))
-    .filter((c): c is DG.Column => c != null);
-  const g2Cols = groups.group2.columns
-    .map((n) => df.col(n))
-    .filter((c): c is DG.Column => c != null);
-
-  const nRows = df.rowCount;
-  const numArr = new Float32Array(nRows);
-  const denArr = new Float32Array(nRows);
-  for (let i = 0; i < nRows; i++) {
-    const m1 = groupMean(g1Cols, i);
-    const m2 = groupMean(g2Cols, i);
-    numArr[i] = isNaN(m1) ? DG.FLOAT_NULL : m1;
-    denArr[i] = isNaN(m2) ? DG.FLOAT_NULL : m2;
-  }
-
-  const numCol = ensureFreshFloat(df, NUMERATOR_MEAN_COL);
-  numCol.init((i) => numArr[i]);
-  numCol.semType = SEMTYPE.NUMERATOR_MEAN;
-
-  const denCol = ensureFreshFloat(df, DENOMINATOR_MEAN_COL);
-  denCol.init((i) => denArr[i]);
-  denCol.semType = SEMTYPE.DENOMINATOR_MEAN;
-}
-
-/** Pearson correlation. Skips paired entries containing NaN or FLOAT_NULL. */
-export function pearson(xs: number[], ys: number[]): number {
-  let n = 0;
-  let sumX = 0;
-  let sumY = 0;
-  for (let i = 0; i < xs.length; i++) {
-    const x = xs[i];
-    const y = ys[i];
-    if (!Number.isFinite(x) || !Number.isFinite(y) || x === DG.FLOAT_NULL || y === DG.FLOAT_NULL) continue;
-    sumX += x;
-    sumY += y;
-    n++;
-  }
-  if (n === 0) return NaN;
-  const meanX = sumX / n;
-  const meanY = sumY / n;
-  let num = 0;
-  let denX = 0;
-  let denY = 0;
-  for (let i = 0; i < xs.length; i++) {
-    const x = xs[i];
-    const y = ys[i];
-    if (!Number.isFinite(x) || !Number.isFinite(y) || x === DG.FLOAT_NULL || y === DG.FLOAT_NULL) continue;
-    const dx = x - meanX;
-    const dy = y - meanY;
-    num += dx * dy;
-    denX += dx * dx;
-    denY += dy * dy;
-  }
-  const den = Math.sqrt(denX * denY);
-  return den === 0 ? NaN : num / den;
-}
-
-/** Fractional ranks (1-based). Ties get the average of the positions they span. */
-function rank(arr: number[]): number[] {
-  const indexed = arr.map((v, i) => ({v, i}));
-  indexed.sort((a, b) => a.v - b.v);
-  const ranks = new Array<number>(arr.length);
-  let i = 0;
-  while (i < indexed.length) {
-    let j = i;
-    while (j + 1 < indexed.length && indexed[j + 1].v === indexed[i].v) j++;
-    const avg = (i + j) / 2 + 1; // 1-based average of positions [i..j]
-    for (let k = i; k <= j; k++) ranks[indexed[k].i] = avg;
-    i = j + 1;
-  }
-  return ranks;
-}
-
-/** Spearman = Pearson over fractional ranks. */
-export function spearman(xs: number[], ys: number[]): number {
-  return pearson(rank(xs), rank(ys));
-}
-
-/** Computes Pearson + Spearman over the filtered subset of two columns. */
-function computePearsonSpearman(
-  df: DG.DataFrame, xName: string, yName: string,
-): {r: number; rho: number} {
-  const xCol = df.col(xName);
-  const yCol = df.col(yName);
-  if (!xCol || !yCol) return {r: NaN, rho: NaN};
-  const xRaw = xCol.getRawData() as Float32Array | Float64Array;
-  const yRaw = yCol.getRawData() as Float32Array | Float64Array;
-
-  const xs: number[] = [];
-  const ys: number[] = [];
-  for (let i = 0; i < df.rowCount; i++) {
-    if (!df.filter.get(i)) continue;
-    const x = xRaw[i];
-    const y = yRaw[i];
-    if (x === DG.FLOAT_NULL || y === DG.FLOAT_NULL) continue;
-    if (!Number.isFinite(x) || !Number.isFinite(y)) continue;
-    xs.push(x);
-    ys.push(y);
-  }
-  return {r: pearson(xs, ys), rho: spearman(xs, ys)};
-}
-
-/**
- * Main factory — derives Numerator/Denominator Mean, plots them as a scatter
- * colored by direction, draws the y=x diagonal, and writes an inline
- * Pearson/Spearman annotation into the title.
- */
-export function createGroupMeanCorrelation(
-  df: DG.DataFrame,
-  options?: {title?: string},
-): DG.ScatterPlotViewer {
-  const groups = getGroups(df);
-  if (!groups)
-    throw new Error('Annotate experimental groups first (Proteomics | Annotate Experiment)');
-
-  computeGroupMeans(df, groups);
-
-  const sp = df.plot.scatter({
-    x: NUMERATOR_MEAN_COL,
-    y: DENOMINATOR_MEAN_COL,
-    color: DIRECTION_COL,
-  });
-
-  // Display Name primary, Gene name fallback (Plan 02 pattern).
-  const labelCol = findColumn(df, SEMTYPE.DISPLAY_NAME, ['display name']) ??
-    findColumn(df, SEMTYPE.GENE_SYMBOL, ['gene name', 'gene symbol']);
-  if (labelCol) {
-    sp.props.labelColumnNames = [labelCol.name];
-    sp.props.showLabelsFor = 'MouseOverRow';
-  }
-
-  // y = x diagonal reference — replace any prior diagonal so re-run doesn't stack.
-  df.meta.formulaLines.items = df.meta.formulaLines.items.filter((line) => {
-    const f = (line.formula ?? '') as string;
-    return !(typeof f === 'string' &&
-      f.includes(NUMERATOR_MEAN_COL) && f.includes(DENOMINATOR_MEAN_COL));
-  });
-  df.meta.formulaLines.addLine({
-    formula: DIAGONAL_FORMULA,
-    color: DIAGONAL_COLOR,
-    width: 1,
-    visible: true,
-  });
-  sp.props.showViewerFormulaLines = true;
-
-  // Inline correlation annotation over the current filter.
-  const {r, rho} = computePearsonSpearman(df, NUMERATOR_MEAN_COL, DENOMINATOR_MEAN_COL);
-  const baseTitle = options?.title ?? 'Group-Mean Correlation';
-  const rStr = Number.isFinite(r) ? r.toFixed(2) : 'NA';
-  const rhoStr = Number.isFinite(rho) ? rho.toFixed(2) : 'NA';
-  sp.setOptions({
-    title: `${baseTitle} — r=${rStr} (Pearson), ρ=${rhoStr} (Spearman)`,
-    xColumnLabel: `${groups.group1.name} mean (log2 intensity)`,
-    yColumnLabel: `${groups.group2.name} mean (log2 intensity)`,
-  } as any);
-
-  return sp;
-}