Updated docs and code examples.

.gitignore

@@ -16,11 +16,15 @@ bioneuralnet.egg-info
 /build/
 /docker_files/
 .mypy_cache
-Quick Start.ipynb
+Quick_Start_testing*.ipynb
 TCGA-BRCA_Datatest.ipynb
 DevNotes.md
 TCGA-BRCA_Datatest_copy.ipynb
 split
+doc_examples_outdated
+dpmon_output
+.enviroment
+TCGA-BRCA_Dataset_testing*.ipynb
 # Other example data and tests not needed in the repo.
 
 Output**

.pre-commit-config.yaml

@@ -28,7 +28,8 @@ repos:
     hooks:
       - id: remove-pyc-and-pycache
         name: Remove .pyc files and __pycache__ directories
-        entry: bash -c "find . \( -path './.venv' -o -path './docs' -o -path './node_modules' \) -prune -o -type f -name '*.pyc' -exec rm -f {} + -o -type d -name '__pycache__' -exec rm -rf {} +"
+        entry: bash -c 'find . \( -path "./.enviroment" -o -path "./.testing" -o -path "./.venv" -o -path "./docs" -o -path "./node_modules" \) -prune -o -type f -name "*.pyc" -exec rm -f {} + -o -type d -name "__pycache__" -exec rm -rf {} +'
+        pass_filenames: false
         language: system
         stages: [pre-commit]
 

README.md

@@ -1,12 +1,13 @@
 # BioNeuralNet: Multi-Omics Integration with Graph Neural Networks
 
-![License](https://img.shields.io/badge/license-MIT-blue.svg)
-![PyPI](https://img.shields.io/pypi/v/bioneuralnet)
-![GitHub Issues](https://img.shields.io/github/issues/UCD-BDLab/BioNeuralNet)
-![GitHub Contributors](https://img.shields.io/github/contributors/UCD-BDLab/BioNeuralNet)
-![Downloads](https://static.pepy.tech/badge/bioneuralnet)
+[![License](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/UCD-BDLab/BioNeuralNet/blob/main/LICENSE)
+[![PyPI](https://img.shields.io/pypi/v/bioneuralnet)](https://pypi.org/project/bioneuralnet/)
+[![GitHub Issues](https://img.shields.io/github/issues/UCD-BDLab/BioNeuralNet)](https://github.com/UCD-BDLab/BioNeuralNet/issues)
+[![GitHub Contributors](https://img.shields.io/github/contributors/UCD-BDLab/BioNeuralNet)](https://github.com/UCD-BDLab/BioNeuralNet/graphs/contributors)
+[![Downloads](https://static.pepy.tech/badge/bioneuralnet)](https://pepy.tech/project/bioneuralnet)
 [![Documentation](https://img.shields.io/badge/docs-read%20the%20docs-blue.svg)](https://bioneuralnet.readthedocs.io/en/latest/)
 
+
 ## Welcome to BioNeuralNet 1.0.7
 
 ![BioNeuralNet Logo](assets/LOGO_WB.png)

bioneuralnet/__init__.py

@@ -37,19 +37,26 @@
 from .clustering import CorrelatedPageRank
 from .clustering import CorrelatedLouvain
 from .clustering import HybridLouvain
+from .datasets import DatasetLoader
+from .external_tools import SmCCNet
 
 from .metrics import omics_correlation
 from .metrics import cluster_correlation
 from .metrics import louvain_to_adjacency
 from .metrics import evaluate_rf
+from .metrics import evaluate_model
+from .metrics import evaluate_f1m
+from .metrics import evaluate_f1w
 from .metrics import plot_performance_three
 from .metrics import plot_variance_distribution
 from .metrics import plot_variance_by_feature
 from .metrics import plot_performance
 from .metrics import plot_embeddings
 from .metrics import plot_network
+from .metrics import plot_multiple_metrics
 from .metrics import compare_clusters
 
+
 from .utils import get_logger
 from .utils import rdata_to_df
 from .utils import variance_summary
@@ -75,8 +82,6 @@
 from .utils import gen_mst_graph
 from .utils import gen_snn_graph
 
-from .datasets import DatasetLoader
-from .external_tools import SmCCNet
 
 __all__: list = [
     "__version__",
@@ -97,6 +102,10 @@
     "plot_embeddings",
     "plot_network",
     "compare_clusters",
+    "plot_multiple_metrics",
+    "evaluate_model",
+    "evaluate_f1m",
+    "evaluate_f1w",
     "get_logger",
     "rdata_to_df",
     "variance_summary",
@@ -122,9 +131,6 @@
     "gen_mst_graph",
     "gen_snn_graph",
     "DatasetLoader",
-    "NetworkLoader",
     "SmCCNet",
-    "WGCNA",
-    "Node2Vec"
     "evaluate_model",
 ]

bioneuralnet/clustering/hybrid_louvain.py

@@ -33,7 +33,7 @@ def __init__(
         Y: pd.DataFrame,
         k3: float = 0.2,
         k4: float = 0.8,
-        max_iter: int = 10,
+        max_iter: int = 3,
         weight: str = "weight",
         gpu: bool = False,
         seed: Optional[int] = None,

bioneuralnet/downstream_task/subject_representation.py

@@ -22,7 +22,7 @@
 from ray.tune import CLIReporter
 from ray.tune.schedulers import ASHAScheduler
 from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
-from sklearn.metrics import accuracy_score, r2_score
+from sklearn.metrics import accuracy_score, r2_score, mean_squared_error
 
 from sklearn.decomposition import PCA
 from sklearn.model_selection import train_test_split
@@ -247,14 +247,16 @@ def _integrate_embeddings(self, reduced: pd.DataFrame, method="multiply", alpha=
 
         With the default parameters (alpha = 2.0, beta = 0.5), each feature is updated as:
 
-            - enhanced = beta * raw + (1 - beta) * (alpha * normalized_weight * raw)
+            enhanced = beta * raw + (1 - beta) * (alpha * normalized_weight * raw)
 
         For example, with alpha = 2.0 and beta = 0.5:
 
-            - If a features normalized weight is 1.0:
-                - enhanced = 0.5xraw + 0.5x(2.0x1.0xraw) = 0.5xraw + raw = 1.5xraw
-            - If a features normalized weight is 0.5:
-                - enhanced = 0.5xraw + 0.5x(2.0x0.5xraw) = 0.5xraw + 0.5xraw = raw
+            If a features normalized weight is 1.0:
+
+                enhanced = 0.5xraw + 0.5x(2.0x1.0xraw) = 0.5xraw + raw = 1.5xraw
+            If a features normalized weight is 0.5:
+
+                enhanced = 0.5xraw + 0.5x(2.0x0.5xraw) = 0.5xraw + 0.5xraw = raw
 
         This is so at least 50% of the final output is influenced by the computed weight
         """
@@ -340,37 +342,32 @@ def _run_classification_tuning(self) -> Dict[str, Any]:
         def tune_helper(config):
             try:
                 method = config["method"].upper()
-                ae_params = config.get("ae_params", {
-                    "epochs": 64,
-                    "hidden_dim": 4,
-                    "dropout": 0.2,
-                    "lr": 1e-3,
-                    "activation": "relu",
-                })
-                alpha = config.get("alpha", 2.0)
-                beta = config.get("beta", 0.5)
-                compressed_dim = config.get("compressed_dim", 2)
+                ae_params = config["ae_params"]
+                alpha = config["alpha"]
+                beta = config["beta"]
+                compressed_dim = config["compressed_dim"]
 
                 reduced = self._reduce_embeddings(method=method, compressed_dim=compressed_dim,ae_params=ae_params)
-                enhanced = self._integrate_embeddings(reduced, method="multiply", alpha=alpha, beta=beta)
+                enhanced = self._integrate_embeddings(reduced, method=config["integration_method"], alpha=alpha, beta=beta)
                 common_index = enhanced.index.intersection(self.phenotype_data.index)
 
                 X = enhanced.loc[common_index].values
                 y = self.phenotype_data.loc[common_index, self.phenotype_col]
 
                 is_classification = y.dtype != float and y.nunique() <= 20
-                X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=self.seed)
+                X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
 
                 if is_classification:
-                    model = RandomForestClassifier(random_state=self.seed)
+                    model = RandomForestClassifier()
                     model.fit(X_train, y_train.astype(int))
                     y_pred = model.predict(X_test)
                     score = accuracy_score(y_test, y_pred)
                 else:
-                    model = RandomForestRegressor(random_state=self.seed)
+                    model = RandomForestRegressor()
                     model.fit(X_train, y_train)
                     y_pred = model.predict(X_test)
-                    score = r2_score(y_test, y_pred)
+                    mse = mean_squared_error(y_test, y_pred)
+                    score = -mse
 
                 tune.report({"score": score})
 
@@ -392,7 +389,7 @@ def short_dirname_creator(trial):
             analysis = tune.run(
                 tune_helper,
                 config=search_config,
-                num_samples=10,
+                num_samples=20,
                 scheduler=scheduler,
                 progress_reporter=reporter,
                 storage_path=os.path.expanduser("~/sr"),

bioneuralnet/external_tools/smccnet.py

@@ -32,7 +32,7 @@ class SmCCNet:
         omics_dfs (List[pd.DataFrame]): List of omics DataFrames.
         data_types (List[str]): List of omics data type strings (e.g. ["Genes", "miRNA"]).
         kfold (int): Number of folds for cross-validation. Default=5.
-        eval_method (str): e.g. 'accuracy', 'auc', 'f1', or 'Rsquared' (if you patch SmCCNet).
+        eval_method (str): e.g. 'accuracy', 'auc', 'f1', or 'Rsquared'.
         subSampNum (int): # of subsamplings. Default=50.
         summarization (str): 'NetSHy', 'PCA', or 'SVD'. Default='NetSHy'.
         seed (int): Random seed. Default=123.

bioneuralnet/metrics/__init__.py

@@ -1,9 +1,5 @@
 from .correlation import omics_correlation, cluster_correlation, louvain_to_adjacency
-from .plot import plot_variance_distribution, plot_variance_by_feature, plot_performance_three, plot_performance, plot_embeddings, plot_network, compare_clusters
-from .evaluation import evaluate_model, evaluate_rf, evaluate_f1m, evaluate_f1w, plot_multiple_metrics, evaluate_single_run
+from .evaluation import evaluate_model, evaluate_rf, evaluate_f1m, evaluate_f1w
+from .plot import plot_variance_distribution, plot_variance_by_feature, plot_performance_three, plot_performance,plot_multiple_metrics, plot_embeddings, plot_network, compare_clusters
 
-__all__ = ["omics_correlation", "cluster_correlation", "louvain_to_adjacency",
-            "plot_variance_distribution", "plot_variance_by_feature", "plot_performance_three",
-            "plot_performance", "plot_embeddings", "plot_network", "compare_clusters",
-            "evaluate_model", "evaluate_rf", "evaluate_single_run", "evaluate_f1m", "evaluate_f1w",
-            "plot_multiple_metrics"]
+__all__ = ["omics_correlation", "cluster_correlation", "louvain_to_adjacency","evaluate_model", "evaluate_rf", "evaluate_f1m", "evaluate_f1w", "plot_variance_distribution", "plot_variance_by_feature", "plot_performance_three", "plot_performance", "plot_multiple_metrics", "plot_embeddings", "plot_network", "compare_clusters"]