Add ShareClaw logistic regression label projection variants

src/methods/shareclaw_lda_lsqr_auto/config.vsh.yaml

@@ -0,0 +1,40 @@
+__merge__: /src/api/comp_method.yaml
+name: "shareclaw_lda_lsqr_auto"
+label: ShareClaw LDA LSQR Auto
+summary: "Standardize PCA coordinates and fit a shrinkage-aware linear discriminant analysis classifier."
+description: |
+  ShareClaw LDA LSQR Auto applies a StandardScaler to the PCA embedding and
+  then fits a LinearDiscriminantAnalysis classifier using the LSQR solver with
+  automatic shrinkage. In our ShareClaw-driven search, this variant delivered
+  the strongest Zebrafish macro-F1 among the lightweight linear baselines we
+  evaluated.
+references:
+  bibtex: |
+    @article{fisher1936use,
+      title = {The use of multiple measurements in taxonomic problems},
+      author = {Fisher, Ronald Aylmer},
+      journal = {Annals of Eugenics},
+      volume = {7},
+      number = {2},
+      pages = {179--188},
+      year = {1936}
+    }
+links:
+  repository: https://github.com/anubhav1004/shareclaw
+  documentation: https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.LinearDiscriminantAnalysis.html
+info:
+  preferred_normalization: log_cp10k
+resources:
+  - type: python_script
+    path: script.py
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+      - type: python
+        packages: scikit-learn
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime, midmem, midcpu]

src/methods/shareclaw_lda_lsqr_auto/script.py

@@ -0,0 +1,54 @@
+import anndata as ad
+import pandas as pd
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+## VIASH START
+par = {
+    "input_train": "resources_test/task_label_projection/cxg_immune_cell_atlas/train.h5ad",
+    "input_test": "resources_test/task_label_projection/cxg_immune_cell_atlas/test.h5ad",
+    "output": "output.h5ad",
+}
+meta = {
+    "name": "foo",
+}
+## VIASH END
+
+
+def require_pca(adata_obj, label):
+    if "X_pca" not in adata_obj.obsm:
+        raise KeyError(f"{label} is missing obsm['X_pca']")
+
+
+print("Load input data", flush=True)
+input_train = ad.read_h5ad(par["input_train"])
+input_test = ad.read_h5ad(par["input_test"])
+
+require_pca(input_train, "input_train")
+require_pca(input_test, "input_test")
+
+print("Fit to train data", flush=True)
+classifier = Pipeline(
+    steps=[
+        ("scale", StandardScaler()),
+        ("model", LinearDiscriminantAnalysis(solver="lsqr", shrinkage="auto")),
+    ]
+)
+classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
+
+print("Predict on test data", flush=True)
+label_pred = classifier.predict(input_test.obsm["X_pca"])
+
+print("Create output data", flush=True)
+output = ad.AnnData(
+    obs=pd.DataFrame({"label_pred": label_pred}, index=input_test.obs.index),
+    uns={
+        "method_id": meta["name"],
+        "dataset_id": input_test.uns["dataset_id"],
+        "normalization_id": input_test.uns["normalization_id"],
+    },
+)
+
+print("Write output data", flush=True)
+output.write_h5ad(par["output"], compression="gzip")

src/methods/shareclaw_lda_svd/config.vsh.yaml

@@ -0,0 +1,39 @@
+__merge__: /src/api/comp_method.yaml
+name: "shareclaw_lda_svd"
+label: ShareClaw LDA SVD
+summary: "Standardize PCA coordinates and fit a linear discriminant analysis classifier with the SVD solver."
+description: |
+  ShareClaw LDA SVD applies a StandardScaler to the PCA embedding and then fits
+  a LinearDiscriminantAnalysis classifier with the SVD solver. In our ShareClaw
+  search loop, this was the strongest macro-F1 performer on the official small
+  task resources while also materially improving the local Zebrafish baseline.
+references:
+  bibtex: |
+    @article{fisher1936use,
+      title = {The use of multiple measurements in taxonomic problems},
+      author = {Fisher, Ronald Aylmer},
+      journal = {Annals of Eugenics},
+      volume = {7},
+      number = {2},
+      pages = {179--188},
+      year = {1936}
+    }
+links:
+  repository: https://github.com/anubhav1004/shareclaw
+  documentation: https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.LinearDiscriminantAnalysis.html
+info:
+  preferred_normalization: log_cp10k
+resources:
+  - type: python_script
+    path: script.py
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+      - type: python
+        packages: scikit-learn
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime, midmem, midcpu]

src/methods/shareclaw_lda_svd/script.py

@@ -0,0 +1,54 @@
+import anndata as ad
+import pandas as pd
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+## VIASH START
+par = {
+    "input_train": "resources_test/task_label_projection/cxg_immune_cell_atlas/train.h5ad",
+    "input_test": "resources_test/task_label_projection/cxg_immune_cell_atlas/test.h5ad",
+    "output": "output.h5ad",
+}
+meta = {
+    "name": "foo",
+}
+## VIASH END
+
+
+def require_pca(adata_obj, label):
+    if "X_pca" not in adata_obj.obsm:
+        raise KeyError(f"{label} is missing obsm['X_pca']")
+
+
+print("Load input data", flush=True)
+input_train = ad.read_h5ad(par["input_train"])
+input_test = ad.read_h5ad(par["input_test"])
+
+require_pca(input_train, "input_train")
+require_pca(input_test, "input_test")
+
+print("Fit to train data", flush=True)
+classifier = Pipeline(
+    steps=[
+        ("scale", StandardScaler()),
+        ("model", LinearDiscriminantAnalysis(solver="svd")),
+    ]
+)
+classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
+
+print("Predict on test data", flush=True)
+label_pred = classifier.predict(input_test.obsm["X_pca"])
+
+print("Create output data", flush=True)
+output = ad.AnnData(
+    obs=pd.DataFrame({"label_pred": label_pred}, index=input_test.obs.index),
+    uns={
+        "method_id": meta["name"],
+        "dataset_id": input_test.uns["dataset_id"],
+        "normalization_id": input_test.uns["normalization_id"],
+    },
+)
+
+print("Write output data", flush=True)
+output.write_h5ad(par["output"], compression="gzip")

src/methods/shareclaw_logreg_balanced/config.vsh.yaml

@@ -0,0 +1,37 @@
+__merge__: /src/api/comp_method.yaml
+name: "shareclaw_logreg_balanced"
+label: ShareClaw Logistic Regression Balanced
+summary: "Standardize PCA coordinates and fit a class-balanced logistic regression classifier for macro-F1-oriented label projection."
+description: |
+  ShareClaw Logistic Regression Balanced applies a StandardScaler to the PCA
+  embedding and fits a logistic regression classifier with balanced class
+  weights. The goal is to preserve a simple, reproducible linear baseline while
+  improving performance on rarer classes that matter for macro F1.
+references:
+  bibtex: |
+    @book{hosmer2013applied,
+      title = {Applied logistic regression},
+      author = {Hosmer Jr, D.W. and Lemeshow, S. and Sturdivant, R.X.},
+      year = {2013},
+      publisher = {John Wiley \& Sons},
+      volume = {398}
+    }
+links:
+  repository: https://github.com/anubhav1004/shareclaw
+  documentation: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
+info:
+  preferred_normalization: log_cp10k
+resources:
+  - type: python_script
+    path: script.py
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+      - type: python
+        packages: scikit-learn
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime, midmem, midcpu]

src/methods/shareclaw_logreg_balanced/script.py

@@ -0,0 +1,62 @@
+import anndata as ad
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+## VIASH START
+par = {
+    "input_train": "resources_test/task_label_projection/cxg_immune_cell_atlas/train.h5ad",
+    "input_test": "resources_test/task_label_projection/cxg_immune_cell_atlas/test.h5ad",
+    "output": "output.h5ad",
+}
+meta = {
+    "name": "foo",
+}
+## VIASH END
+
+
+def require_pca(adata_obj, label):
+    if "X_pca" not in adata_obj.obsm:
+        raise KeyError(f"{label} is missing obsm['X_pca']")
+
+
+print("Load input data", flush=True)
+input_train = ad.read_h5ad(par["input_train"])
+input_test = ad.read_h5ad(par["input_test"])
+
+require_pca(input_train, "input_train")
+require_pca(input_test, "input_test")
+
+print("Fit to train data", flush=True)
+classifier = Pipeline(
+    steps=[
+        ("scale", StandardScaler()),
+        (
+            "model",
+            LogisticRegression(
+                max_iter=500,
+                solver="lbfgs",
+                random_state=7,
+                class_weight="balanced",
+            ),
+        ),
+    ]
+)
+classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
+
+print("Predict on test data", flush=True)
+label_pred = classifier.predict(input_test.obsm["X_pca"])
+
+print("Create output data", flush=True)
+output = ad.AnnData(
+    obs=pd.DataFrame({"label_pred": label_pred}, index=input_test.obs.index),
+    uns={
+        "method_id": meta["name"],
+        "dataset_id": input_test.uns["dataset_id"],
+        "normalization_id": input_test.uns["normalization_id"],
+    },
+)
+
+print("Write output data", flush=True)
+output.write_h5ad(par["output"], compression="gzip")

src/methods/shareclaw_logreg_scaled/config.vsh.yaml

@@ -0,0 +1,37 @@
+__merge__: /src/api/comp_method.yaml
+name: "shareclaw_logreg_scaled"
+label: ShareClaw Logistic Regression Scaled
+summary: "Standardize PCA coordinates before fitting a higher-iteration logistic regression classifier for label projection."
+description: |
+  ShareClaw Logistic Regression Scaled applies a StandardScaler to the PCA
+  embedding provided in the task inputs before fitting a multinomial logistic
+  regression classifier. The goal is to preserve the simplicity of a linear
+  baseline while using a more stable optimization setup for the task.
+references:
+  bibtex: |
+    @book{hosmer2013applied,
+      title = {Applied logistic regression},
+      author = {Hosmer Jr, D.W. and Lemeshow, S. and Sturdivant, R.X.},
+      year = {2013},
+      publisher = {John Wiley \& Sons},
+      volume = {398}
+    }
+links:
+  repository: https://github.com/anubhav1004/shareclaw
+  documentation: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
+info:
+  preferred_normalization: log_cp10k
+resources:
+  - type: python_script
+    path: script.py
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+      - type: python
+        packages: scikit-learn
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime, midmem, midcpu]

src/methods/shareclaw_logreg_scaled/script.py

@@ -0,0 +1,54 @@
+import anndata as ad
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+## VIASH START
+par = {
+    "input_train": "resources_test/task_label_projection/cxg_immune_cell_atlas/train.h5ad",
+    "input_test": "resources_test/task_label_projection/cxg_immune_cell_atlas/test.h5ad",
+    "output": "output.h5ad",
+}
+meta = {
+    "name": "foo",
+}
+## VIASH END
+
+
+def require_pca(adata_obj, label):
+    if "X_pca" not in adata_obj.obsm:
+        raise KeyError(f"{label} is missing obsm['X_pca']")
+
+
+print("Load input data", flush=True)
+input_train = ad.read_h5ad(par["input_train"])
+input_test = ad.read_h5ad(par["input_test"])
+
+require_pca(input_train, "input_train")
+require_pca(input_test, "input_test")
+
+print("Fit to train data", flush=True)
+classifier = Pipeline(
+    steps=[
+        ("scale", StandardScaler()),
+        ("model", LogisticRegression(max_iter=500, solver="lbfgs", random_state=7)),
+    ]
+)
+classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
+
+print("Predict on test data", flush=True)
+label_pred = classifier.predict(input_test.obsm["X_pca"])
+
+print("Create output data", flush=True)
+output = ad.AnnData(
+    obs=pd.DataFrame({"label_pred": label_pred}, index=input_test.obs.index),
+    uns={
+        "method_id": meta["name"],
+        "dataset_id": input_test.uns["dataset_id"],
+        "normalization_id": input_test.uns["normalization_id"],
+    },
+)
+
+print("Write output data", flush=True)
+output.write_h5ad(par["output"], compression="gzip")