DeepTraCDR/Scenario2/Target/main_target.py

# main_target.py
import argparse
import numpy as np
import pandas as pd
import scipy.sparse as sp
from sklearn.model_selection import KFold
from sklearn.metrics import roc_auc_score, average_precision_score, precision_score, recall_score, f1_score
from model import DeepTraCDR, ModelOptimizer
from utils import evaluate_auc, common_data_index
from data_sampler import TargetSampler
from data_loader import load_data
import torch
from torch.optim.lr_scheduler import OneCycleLR

# Clear CUDA cache to optimize GPU memory usage
torch.cuda.empty_cache()


def main():
    """
    Main function to execute the DeepTraCDR model training and evaluation pipeline.
    Parses command-line arguments, loads data, performs k-fold cross-validation,
    and reports performance metrics.
    """
    # Initialize argument parser for command-line arguments
    parser = argparse.ArgumentParser(description="DeepTraCDR Advanced Model Training")
    parser.add_argument('-device', type=str, default="cuda:0" if torch.cuda.is_available() else "cpu",
                        help="Device to run the model on (cuda:0 or cpu)")
    parser.add_argument('-data', type=str, default='gdsc', help="Dataset to use (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 model")
    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('--lr', type=float, default=0.0005, help="Learning rate for optimizer")
    args = parser.parse_args()

    # Load target drug data based on the specified dataset
    if args.data == "gdsc":
        target_drug_cids = np.array([5330286, 11338033, 24825971])
        # Load cell-drug binary matrix for GDSC dataset
        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
        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":
        target_drug_cids = np.array([5330286])
        # Load cell-drug binary matrix for CCLE dataset
        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
        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 dataset components including adjacency matrix, fingerprints, and expression data
    full_adj, drug_fingerprints, exprs, null_mask, pos_num, args = load_data(args)
    full_adj_np = full_adj.copy()

    # Log original adjacency matrix shape for debugging
    print(f"Original adj_mat shape: {full_adj.shape}")

    # Log shapes of loaded data for verification
    print("\n--- Data Shapes ---")
    print(f"Expression data shape: {exprs.shape}")
    print(f"Null mask shape: {null_mask.shape}")

    # Convert adjacency matrix to PyTorch tensor if it is a NumPy array
    if isinstance(full_adj, np.ndarray):
        full_adj = torch.from_numpy(full_adj).float().to(args.device)

    # Log converted adjacency matrix shape for verification
    print(f"Converted adj_mat shape: {full_adj.shape}")

    # Initialize k-fold cross-validation parameters
    k = 5
    n_kfolds = 5
    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)
        for fold, (train_idx, test_idx) in enumerate(kfold.split(np.arange(target_pos_num))):
            # Initialize data sampler for train/test split
            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_fingerprints=drug_fingerprints,
                layer_size=args.layer_size,
                gamma=args.gamma,
                device=args.device
            )

            # Initialize optimizer for model training
            opt = ModelOptimizer(
                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,
                device=args.device
            )

            # Train model and retrieve evaluation metrics
            true, pred, best_auc, best_auprc = opt.train()

            # Store metrics for this fold
            all_metrics['auc'].append(best_auc)
            all_metrics['auprc'].append(best_auprc)

            # Log performance for the current fold
            print(f"Fold {n_kfold * k + fold + 1}: AUC={best_auc:.4f}, AUPRC={best_auprc:.4f}")

    # Calculate and log mean and standard deviation of metrics
    print(f"\nFinal Average Metrics:")
    for metric, values in all_metrics.items():
        mean = np.mean(values)
        std = np.std(values)
        print(f"{metric.upper()}: {mean:.4f} ± {std:.4f}")


if __name__ == "__main__":
    # Set precision for matrix multiplication to optimize performance
    torch.set_float32_matmul_precision('high')
    main()