pyedger 0.2.1__tar.gz → 0.2.2__tar.gz

{pyedger-0.2.1 → pyedger-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyedger
-Version: 0.2.1
+Version: 0.2.2
 Summary: Pure-Python port of Bioconductor edgeR — negative-binomial models for differential expression of count data (estimateDisp, glmFit, glmLRT, glmQLFTest, exactTest).
 Author-email: Zehua Zeng <starlitnightly@163.com>
 License: LGPL-3.0-or-later

{pyedger-0.2.1 → pyedger-0.2.2}/pyedger/__init__.py

@@ -16,12 +16,14 @@ from .core import (
     estimate_common_disp,
     estimate_disp,
     estimate_glm_common_disp,
+    estimate_glm_robust_disp,
     estimate_glm_tagwise_disp,
     estimate_glm_trended_disp,
     estimate_tagwise_disp,
     exact_test,
     filter_by_expr,
     glm_fit,
+    glm_residuals,
     glm_lrt,
     glm_ql_fit,
     glm_qlf_test,
@@ -38,6 +40,8 @@ estimateCommonDisp = estimate_common_disp
 estimateTagwiseDisp = estimate_tagwise_disp
 estimateDisp = estimate_disp
 estimateGLMCommonDisp = estimate_glm_common_disp
+estimateGLMRobustDisp = estimate_glm_robust_disp
+glmResiduals = glm_residuals
 estimateGLMTagwiseDisp = estimate_glm_tagwise_disp
 estimateGLMTrendedDisp = estimate_glm_trended_disp
 exactTest = exact_test
@@ -55,6 +59,10 @@ topTags = top_tags
 aveLogCPM = ave_log_cpm
 
 __all__ = [
+    "estimate_glm_robust_disp",
+    "estimateGLMRobustDisp",
+    "glm_residuals",
+    "glmResiduals",
     "DGEExact",
     "DGEGLM",
     "DGELRT",

{pyedger-0.2.1 → pyedger-0.2.2}/pyedger/core.py

@@ -996,6 +996,78 @@ def _fit_glm_batch(counts, X, offset_mat, phi_mat, W, start=None):
     return beta, mu, dev
 
 
+def glm_residuals(glmfit: DGEGLM, type: str = "pearson") -> np.ndarray:
+    """Observation residuals of a fitted NB GLM (``pearson`` / ``deviance`` / ``anscombe``)."""
+    y = glmfit.counts.to_numpy(dtype=float)
+    mu = np.asarray(glmfit.fitted_values, dtype=float)
+    disp = np.asarray(glmfit.dispersion, dtype=float)
+    phi = np.broadcast_to(disp.reshape(-1, 1) if disp.ndim else disp, y.shape)
+    type = type.lower()
+    if type == "pearson":
+        return (y - mu) / np.sqrt(np.maximum(mu + phi * mu * mu, 1e-300))
+    if type == "deviance":
+        unit = _nbinom_unit_deviance(y, mu, phi)
+        return np.sign(y - mu) * np.sqrt(unit)
+    if type == "anscombe":
+        # Anscombe residual for the NB family (Hilbe 2011), integral evaluated numerically.
+        def a(t, ph):
+            grid = np.linspace(0.0, 1.0, 65)[None, :]
+            s_ = np.maximum(t[:, None] * grid, 1e-12)
+            f = (s_ + ph[:, None] * s_ * s_) ** (-1.0 / 3.0)
+            trap = getattr(np, "trapezoid", None) or np.trapz
+            return trap(f, grid[0], axis=1) * t
+        yf, mf, pf = y.ravel(), mu.ravel(), phi.ravel()
+        res = (a(yf, pf) - a(mf, pf)) / ((mf + pf * mf * mf) ** (1.0 / 6.0) + 1e-300)
+        return res.reshape(y.shape)
+    raise ValueError("type must be 'pearson', 'deviance' or 'anscombe'.")
+
+
+def estimate_glm_robust_disp(
+    y: DGEList,
+    design=None,
+    prior_df: float = 10.0,
+    update_trend: bool = True,
+    trend_method: str = "bin.loess",
+    maxit: int = 6,
+    k: float = 1.345,
+    residual_type: str = "pearson",
+    record: bool = False,
+) -> DGEList:
+    """Observation-weighted robust dispersion, mirroring ``edgeR::estimateGLMRobustDisp``.
+
+    Alternates GLM fits with Huber observation weights ``min(1, k / |r|)`` on
+    the fitted residuals ``r`` and re-estimates the trended and tagwise
+    dispersions with those weights (Zhou, Lindsay & Robinson 2014, NAR). The
+    final weights are kept in ``y.weights`` so a following :func:`glm_fit` /
+    :func:`glm_lrt` down-weights isolated aberrant observations.
+    """
+    if not isinstance(y, DGEList):
+        y = DGEList(y)
+    if design is None:
+        design = _default_design_from_group(y)
+    y.weights = pd.DataFrame(np.ones(y.counts.shape), index=y.counts.index, columns=y.counts.columns)
+    if y.trended_dispersion is None:
+        estimate_glm_trended_disp(y, design=design, method=trend_method)
+    if y.tagwise_dispersion is None:
+        estimate_glm_tagwise_disp(y, design=design, prior_df=prior_df)
+    history = []
+    for _ in range(int(maxit)):
+        fit = glm_fit(y, design=design, dispersion=y.tagwise_dispersion, prior_count=0)
+        res = glm_residuals(fit, type=residual_type)
+        res = np.where(np.isfinite(res), res, 0.0)
+        ares = np.abs(res)
+        wts = np.where(ares <= k, 1.0, k / np.maximum(ares, 1e-300))
+        y.weights = pd.DataFrame(wts, index=y.counts.index, columns=y.counts.columns)
+        if update_trend:
+            estimate_glm_trended_disp(y, design=design, method=trend_method)
+        estimate_glm_tagwise_disp(y, design=design, prior_df=prior_df)
+        if record:
+            history.append({"weights": wts.copy(), "tagwise_dispersion": np.asarray(y.tagwise_dispersion).copy()})
+    if record:
+        y.record = history
+    return y
+
+
 def pred_fc(y, design, prior_count: float = 0.125, offset=None, dispersion=None, weights=None) -> pd.DataFrame:
     """edgeR-style prior-count shrunken GLM coefficients on log2 scale."""
 

{pyedger-0.2.1 → pyedger-0.2.2}/pyedger.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyedger
-Version: 0.2.1
+Version: 0.2.2
 Summary: Pure-Python port of Bioconductor edgeR — negative-binomial models for differential expression of count data (estimateDisp, glmFit, glmLRT, glmQLFTest, exactTest).
 Author-email: Zehua Zeng <starlitnightly@163.com>
 License: LGPL-3.0-or-later

{pyedger-0.2.1 → pyedger-0.2.2}/pyedger.egg-info/SOURCES.txt

@@ -15,4 +15,5 @@ pyedger.egg-info/requires.txt
 pyedger.egg-info/top_level.txt
 tests/test_numba_ql.py
 tests/test_r_parity.py
+tests/test_robust_disp.py
 tests/test_smoke.py

{pyedger-0.2.1 → pyedger-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pyedger"
-version = "0.2.1"
+version = "0.2.2"
 description = "Pure-Python port of Bioconductor edgeR — negative-binomial models for differential expression of count data (estimateDisp, glmFit, glmLRT, glmQLFTest, exactTest)."
 readme = "README.md"
 requires-python = ">=3.9"

pyedger-0.2.2/tests/test_robust_disp.py

@@ -0,0 +1,47 @@
+"""estimate_glm_robust_disp / glm_residuals (edgeR estimateGLMRobustDisp)."""
+import numpy as np
+import pandas as pd
+
+import pyedger as pe
+
+
+def _data(seed=1, G=400, n=8, n_out=20):
+    rs = np.random.RandomState(seed)
+    mu = rs.lognormal(4, 1.2, G)[:, None] * np.ones((1, n))
+    disp = 0.1
+    Y = rs.negative_binomial(1 / disp, 1 / (1 + disp * mu)).astype(float)
+    out = rs.choice(G, n_out, replace=False)
+    col = rs.randint(0, n, n_out)
+    Y[out, col] *= 20
+    counts = pd.DataFrame(Y, index=[f"g{i}" for i in range(G)], columns=[f"s{j}" for j in range(n)])
+    design = pd.DataFrame({"Intercept": 1.0, "cond": [0] * (n // 2) + [1] * (n - n // 2)},
+                          index=counts.columns)
+    return counts, design, out, col
+
+
+def test_glm_residuals_pearson_and_deviance():
+    counts, design, _, _ = _data()
+    y = pe.DGEList(counts, group=["a"] * 4 + ["b"] * 4)
+    pe.estimate_disp(y, design=design)
+    fit = pe.glm_fit(y, design=design)
+    r = pe.glm_residuals(fit, type="pearson")
+    mu = fit.fitted_values
+    phi = np.asarray(fit.dispersion).reshape(-1, 1)
+    np.testing.assert_allclose(r, (counts.to_numpy() - mu) / np.sqrt(mu + phi * mu * mu), rtol=1e-12)
+    d = pe.glm_residuals(fit, type="deviance")
+    assert d.shape == r.shape and np.all(np.sign(d) == np.sign(counts.to_numpy() - mu))
+
+
+def test_robust_disp_downweights_outliers():
+    counts, design, out, col = _data()
+    y = pe.DGEList(counts, group=["a"] * 4 + ["b"] * 4)
+    y = pe.estimateGLMRobustDisp(y, design=design)
+    w = y.weights.to_numpy()
+    assert np.all(w[out, col] < 0.5)
+    mask = np.ones_like(w, dtype=bool)
+    mask[out, col] = False
+    assert np.median(w[mask]) == 1.0
+    assert 0.05 < np.median(y.tagwise_dispersion) < 0.15
+    # the weights flow into the GLM fit
+    fit = pe.glm_fit(y, design=design)
+    assert np.all(np.isfinite(fit.coefficients))