import argparse import numpy as np import pandas as pd import torch import scipy.sparse as sp from sklearn.model_selection import KFold from sklearn.metrics import roc_auc_score, average_precision_score from model import DeepTraCDR, Optimizer from utils import evaluate_auc, common_data_index from data_sampler import TargetSampler from data_loader import load_data # Clear CUDA cache to optimize memory usage torch.cuda.empty_cache() def main(): # Parse command-line arguments for model configuration parser = argparse.ArgumentParser(description="DeepTraCDR Case Study for Drug Response Prediction") parser.add_argument('-device', type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="Device to run the model (cuda:0 or cpu)") parser.add_argument('-data', type=str, default='gdsc', help="Dataset to use (e.g., gdsc or ccle)") parser.add_argument('--wd', type=float, default=1e-4, help="Weight decay for optimizer") parser.add_argument('--layer_size', nargs='+', type=int, default=[512], help="List of layer sizes for the GCN model") parser.add_argument('--gamma', type=float, default=15, help="Gamma parameter for loss function") parser.add_argument('--epochs', type=int, default=1000, help="Number of training epochs") parser.add_argument('--test_freq', type=int, default=50, help="Frequency of evaluation during training") parser.add_argument('--patience', type=int, default=100, help="Patience for early stopping") parser.add_argument('--lr', type=float, default=0.0005, help="Learning rate for optimizer") parser.add_argument('--k_fold', type=int, default=5, help="Number of folds for cross-validation") args = parser.parse_args() # Load dataset-specific drug response data if args.data == "gdsc": # Define target drug CIDs (e.g., Dasatinib=5330286, GSK690693=11338033) target_drug_cids = np.array([5330286, 11338033, 24825971]) # Load cell-drug binary response matrix cell_drug = pd.read_csv( "/media/external_16TB_1/ali_kianfar/Data/GDSC/cell_drug_binary.csv", index_col=0, header=0 ) cell_drug.columns = cell_drug.columns.astype(np.int32) drug_cids = cell_drug.columns.values # Extract target drug responses and compute positive sample count cell_target_drug = np.array(cell_drug.loc[:, target_drug_cids], dtype=np.float32) target_pos_num = sp.coo_matrix(cell_target_drug).data.shape[0] target_indexes = common_data_index(drug_cids, target_drug_cids) elif args.data == "ccle": # Define target drug CIDs for CCLE dataset target_drug_cids = np.array([5330286]) # Load cell-drug binary response matrix cell_drug = pd.read_csv( "/media/external_16TB_1/ali_kianfar/Data/CCLE/cell_drug_binary.csv", index_col=0, header=0 ) cell_drug.columns = cell_drug.columns.astype(np.int32) drug_cids = cell_drug.columns.values # Extract target drug responses and compute positive sample count cell_target_drug = np.array(cell_drug.loc[:, target_drug_cids], dtype=np.float32) target_pos_num = sp.coo_matrix(cell_target_drug).data.shape[0] target_indexes = common_data_index(drug_cids, target_drug_cids) # Load additional data (adjacency matrix, fingerprints, expression, etc.) full_adj, drug_fingerprints, exprs, null_mask, pos_num, args = load_data(args) full_adj_np = full_adj.copy() # Copy for sampler usage # Print data shapes for verification print(f"Adjacency matrix shape: {full_adj.shape}") print(f"Expression data shape: {exprs.shape}") print(f"Null mask shape: {null_mask.shape}") # Convert adjacency matrix to PyTorch tensor if isinstance(full_adj, np.ndarray): full_adj = torch.from_numpy(full_adj).float().to(args.device) # Initialize k-fold cross-validation k = args.k_fold n_kfolds = 5 # Number of k-fold iterations all_metrics = {'auc': [], 'auprc': []} # Perform k-fold cross-validation for n_kfold in range(n_kfolds): kfold = KFold(n_splits=k, shuffle=True, random_state=n_kfold) idx_all = np.arange(target_pos_num) for fold, (train_idx, test_idx) in enumerate(kfold.split(idx_all)): print(f"\n--- Fold {fold+1}/{k} (Iteration {n_kfold+1}/{n_kfolds}) ---") # Initialize data sampler for training and testing sampler = TargetSampler( response_mat=full_adj_np, null_mask=null_mask, target_indexes=target_indexes, pos_train_index=train_idx, pos_test_index=test_idx ) # Initialize DeepTraCDR model model = DeepTraCDR( adj_mat=full_adj, cell_exprs=exprs, drug_finger=drug_fingerprints, layer_size=args.layer_size, gamma=args.gamma, device=args.device ) # Initialize optimizer for training opt = Optimizer( model=model, train_data=sampler.train_data, test_data=sampler.test_data, test_mask=sampler.test_mask, train_mask=sampler.train_mask, adj_matrix=full_adj, evaluate_fun=evaluate_auc, lr=args.lr, wd=args.wd, epochs=args.epochs, test_freq=args.test_freq, patience=args.patience, device=args.device ) # Train the model and retrieve best metrics true, pred, best_auc, best_auprc = opt.train() all_metrics['auc'].append(best_auc) all_metrics['auprc'].append(best_auprc) print(f"Fold {fold+1}: AUC={best_auc:.4f}, AUPRC={best_auprc:.4f}") # Compute and display average metrics across all folds print(f"\nFinal Average Metrics (Across {n_kfolds*k} Folds):") for metric, values in all_metrics.items(): mean = np.mean(values) std = np.std(values) print(f"{metric.upper()}: {mean:.4f} ± {std:.4f}") # Perform case study: Predict missing responses for target drugs print("\n--- Case Study: Predicting Missing Responses for Target Drugs ---") model.eval() with torch.no_grad(): final_pred, cell_emb, drug_emb = model() # Shape: [num_cells, num_drugs] # Create a DataFrame to sort cell lines by predicted sensitivity num_cells, num_drugs = final_pred.size() cell_names = cell_drug.index.values # Cell line names cid_list = cell_drug.columns.values # Drug CIDs # Identify top 10 sensitive cell lines for each target drug for d in range(num_drugs): cid = cid_list[d] if cid in [5330286, 11338033]: # Focus on Dasatinib or GSK690693 drug_preds = final_pred[:, d].cpu().numpy() sorted_idx = np.argsort(-drug_preds) # Sort in descending order top_10_cells = [(cell_names[i], drug_preds[i]) for i in sorted_idx[:10]] drug_name = "Dasatinib" if cid == 5330286 else "GSK690693" print(f"\nTop 10 Sensitive Cell Lines for {drug_name} (CID={cid}):") for rank, (cell, score) in enumerate(top_10_cells, start=1): print(f"{rank}. Cell: {cell}, Score: {score:.4f}") if __name__ == "__main__": # Set high precision for matrix multiplication torch.set_float32_matmul_precision('high') main()