gpbench 1.0.0__py3-none-any.whl

gpbench/method_reg/GBLUP/GBLUP_R.py

@@ -0,0 +1,182 @@
+import os
+import time
+import psutil
+import swanlab
+import argparse
+import random
+import torch
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import KFold
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error
+
+# rpy2 导入
+import rpy2.robjects as ro
+from rpy2.robjects import numpy2ri
+numpy2ri.activate()
+
+# 为 BLUP 求逆
+ro.r('library(MASS)')
+
+def gblup_r_vanraden_reml(X_train, y_train, X_test):
+
+    # Pass data to R
+    ro.globalenv['X_train'] = X_train
+    ro.globalenv['y_train'] = y_train
+    ro.globalenv['X_test'] = X_test
+
+    r_code = """
+    library(rrBLUP)
+
+    n_train <- nrow(X_train)
+    m <- ncol(X_train)
+
+    # Step1: allele frequencies
+    p <- colMeans(X_train) / 2
+    p <- pmax(pmin(p, 0.99), 0.01)
+
+    # Step2: VanRaden standardized genotype
+    Z_train <- sweep(X_train, 2, 2*p, "-") / sqrt(2*p*(1-p))
+    Z_train[is.na(Z_train)] <- 0
+
+    Z_test <- sweep(X_test, 2, 2*p, "-") / sqrt(2*p*(1-p))
+    Z_test[is.na(Z_test)] <- 0
+
+    # Step3: Genomic relationship matrix (VanRaden method 2)
+    denom <- sum(2*p*(1-p))
+    G <- Z_train %*% t(Z_train) / denom
+    G <- G + diag(1e-6, n_train)  # stability
+
+    # Step4: REML GBLUP
+    fit <- mixed.solve(y = y_train, K = G, SE = FALSE)
+
+    # Extract variance components and fixed effect
+    Vu <- fit$Vu
+    Ve <- fit$Ve
+    mu <- as.numeric(fit$beta)  # <-- 转成标量，避免非兼容数组
+    h2 <- Vu / (Vu + Ve)
+
+    # Step5: GBLUP prediction for test set
+    y_centered <- y_train - mu
+    A <- G + (Ve / Vu) * diag(n_train)  # G + λ I
+
+    G_test_train <- Z_test %*% t(Z_train) / denom
+    u_test <- G_test_train %*% solve(A, y_centered)  # strictly correct formula
+
+    y_pred <- mu + u_test
+    y_pred
+    """
+
+    y_pred = np.array(ro.r(r_code)).flatten()
+    return y_pred
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Argument parser")
+    parser.add_argument('--methods', type=str, default='GBLUP_R/', help='Method name') 
+    parser.add_argument('--species', type=str, default='')
+    parser.add_argument('--phe', type=str, default='', help='Dataset name')
+    parser.add_argument('--data_dir', type=str, default='../../data/', help='Path to data directory')
+    parser.add_argument('--result_dir', type=str, default='result/', help='Path to result directory')
+    args = parser.parse_args()
+    return args
+
+
+def load_data(args):
+    xData = np.load(os.path.join(args.data_dir, args.species, 'genotype.npz'))["arr_0"]
+    yData = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_0"]
+    names = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_1"]
+
+    nsample = xData.shape[0]
+    nsnp = xData.shape[1]
+    print("Number of samples: ", nsample)
+    print("Number of SNPs: ", nsnp)
+    return xData, yData, nsample, nsnp, names
+
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(torch.tensor(seed))
+    torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+
+def run_nested_cv(args, data, label, process):
+    result_dir = os.path.join(args.result_dir, args.methods + args.species + args.phe)
+    os.makedirs(result_dir, exist_ok=True)
+    print("Starting 10-fold cross-validation with GBLUP (R VanRaden)...")
+
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+    time_star = time.time()
+    
+    for fold, (train_idx, test_idx) in enumerate(kf.split(label)):
+        print(f"===== Fold {fold} =====")
+        fold_start_time = time.time()
+        X_train, X_test = data[train_idx], data[test_idx]
+        y_train, y_test = label[train_idx], label[test_idx]
+
+        # === run strict GBLUP via R ===
+        y_pred = gblup_r_vanraden_reml(X_train, y_train, X_test)
+
+        # 评价指标
+        pcc = pearsonr(y_test, y_pred)[0]
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem = torch.cuda.max_memory_allocated() / 1024**2 if torch.cuda.is_available() else 0
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}: Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+              f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+
+        results_df = pd.DataFrame({'Y_test': y_test, 'Y_pred': y_pred})
+        results_df.to_csv(os.path.join(result_dir, f"fold{fold}.csv"), index=False)
+
+    print("\n===== Cross-validation summary =====")
+    print(f"Average PCC: {np.mean(all_pcc):.4f} ± {np.std(all_pcc):.4f}")
+    print(f"Average MAE: {np.mean(all_mae):.4f} ± {np.std(all_mae):.4f}")
+    print(f"Average MSE: {np.mean(all_mse):.4f} ± {np.std(all_mse):.4f}")
+    print(f"Average R2 : {np.mean(all_r2):.4f} ± {np.std(all_r2):.4f}")
+    print(f"Time: {time.time() - time_star:.2f}s")
+
+
+
+def GBLUP_reg():
+    set_seed(42)
+    torch.cuda.empty_cache()
+    device = torch.device("cuda:0")
+    args = parse_args()
+    process = psutil.Process(os.getpid())
+    all_species =['Cotton/']
+
+    for sp in all_species:
+        args.species = sp
+        X, Y, nsamples, nsnp, names = load_data(args)
+        for i, phe in enumerate(names):
+            args.phe = phe
+            print("starting run " + args.methods + args.species + args.phe)
+            label = Y[:, i]
+            label = np.nan_to_num(label, nan=np.nanmean(label))
+            start_time = time.time()
+            torch.cuda.reset_peak_memory_stats()
+
+
+            run_nested_cv(args, data=X, label=label, process=process)
+        
+            elapsed_time = time.time() - start_time
+            print(f"运行时间: {elapsed_time:.2f} 秒")
+            print("successfully")
+
+
+if __name__ == "__main__":
+    GBLUP_reg()

gpbench/method_reg/GBLUP/__init__.py

@@ -0,0 +1,5 @@
+from .GBLUP_R import GBLUP_reg
+
+GBLUP = GBLUP_reg
+
+__all__ = ["GBLUP","GBLUP_reg"]

gpbench/method_reg/GEFormer/GEFormer.py

@@ -0,0 +1,164 @@
+import os
+import torch
+import argparse
+import psutil
+import time
+import random
+import numpy as np
+import pandas as pd
+import pynvml
+from . import GEFormer_Hyperparameters
+from .gMLP import GEFormer
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from sklearn.model_selection import KFold, train_test_split
+from scipy.stats import pearsonr
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Argument parser")
+    parser.add_argument('--methods', type=str, default='GEFormer/', help='Random seed')
+    parser.add_argument('--species', type=str, default='Pig/')
+    parser.add_argument('--phe', type=str, default='', help='Dataset name')
+    parser.add_argument('--data_dir', type=str, default='../../data/')
+    parser.add_argument('--result_dir', type=str, default='result/')
+    
+    parser.add_argument('--epoch', type=int, default=1000, help='Number of training rounds')
+    parser.add_argument('--batch_size', type=int, default=64, help='Batch size')
+    parser.add_argument('--lr', type=float, default=0.01, help='Learning rate')
+    parser.add_argument('--patience', type=int, default=10, help='Patience for early stopping')
+    parser.add_argument('--dropout1', type=float, default=0.5, help='Dropout rate for layer 1')
+    parser.add_argument('--dropout2', type=float, default=0.5, help='Dropout rate for layer 2')
+    args = parser.parse_args()
+    return args
+
+def load_data(args):
+    xData = np.load(os.path.join(args.data_dir, args.species, 'genotype.npz'))["arr_0"]
+    yData = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_0"]
+    names = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_1"]
+
+    nsample = xData.shape[0]
+    nsnp = xData.shape[1]
+    print("Number of samples: ", nsample)
+    print("Number of SNPs: ", nsnp)
+    return xData, yData, nsample, nsnp, names
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def get_gpu_mem_by_pid(pid):
+    procs = pynvml.nvmlDeviceGetComputeRunningProcesses(handle)
+    for p in procs:
+        if p.pid == pid:
+            return p.usedGpuMemory / 1024**2
+    return 0.0
+
+def run_nested_cv(args, data, label, nsnp, device):
+    result_dir = os.path.join(args.result_dir, args.methods + args.species + args.phe)
+    os.makedirs(result_dir, exist_ok=True)
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+    time_star = time.time()
+    for fold, (train_idx, test_idx) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        x_train, x_test = data[train_idx], data[test_idx]
+        y_train, y_test = label[train_idx], label[test_idx]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(x_train, y_train, test_size=0.1, random_state=42)
+
+        x_train_tensor = torch.from_numpy(X_train_sub).float().to(device)
+        y_train_tensor = torch.from_numpy(y_train_sub).float().to(device)
+        x_valid_tensor = torch.from_numpy(X_valid).float().to(device)
+        y_valid_tensor = torch.from_numpy(y_valid).float().to(device)
+        x_test_tensor = torch.from_numpy(x_test).float().to(device)
+        y_test_tensor = torch.from_numpy(y_test).float().to(device)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, args.batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, args.batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, args.batch_size, shuffle=False)
+
+        model = GEFormer(nsnp=nsnp).to(device)
+        model.train_model(train_loader, valid_loader,args.epoch, args.lr, args.patience, device)
+        y_pred = model.predict(test_loader)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem =  get_gpu_mem_by_pid(os.getpid()) 
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+              f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+        
+        torch.cuda.empty_cache()
+        torch.cuda.reset_peak_memory_stats()
+        results_df = pd.DataFrame({'Y_test': y_test, 'Y_pred': y_pred})
+        results_df.to_csv(os.path.join(result_dir, f"fold{fold}.csv"), index=False)
+
+    print("\n===== Cross-validation summary =====")
+    print(f"Average PCC: {np.mean(all_pcc):.4f} ± {np.std(all_pcc):.4f}")
+    print(f"Average MAE: {np.mean(all_mae):.4f} ± {np.std(all_mae):.4f}")
+    print(f"Average MSE: {np.mean(all_mse):.4f} ± {np.std(all_mse):.4f}")
+    print(f"Average R2 : {np.mean(all_r2):.4f} ± {np.std(all_r2):.4f}")
+    print(f"Time: {time.time() - time_star:.2f}s")
+
+
+def GEFormer_reg():
+    set_seed(42)
+    torch.cuda.empty_cache()  
+    pynvml.nvmlInit()
+    handle = pynvml.nvmlDeviceGetHandleByIndex(0)
+    args = parse_args()
+    all_species =['Cotton/']
+    
+    for i in range(len(all_species)):
+        args.species = all_species[i]
+        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+        args.device = device  
+        X, Y, nsamples, nsnp, names = load_data(args)
+        for j in range(len(names)):
+            args.phe = names[j]
+            print("starting run " + args.methods + args.species + args.phe)
+            label = Y[:, j]
+            label = np.nan_to_num(label, nan=np.nanmean(label))
+            best_params = GEFormer_Hyperparameters.Hyperparameter(X, label, nsnp)
+            args.learning_rate = best_params['learning_rate']
+            args.batch_size = best_params['batch_size']
+            args.patience = best_params['patience']
+            start_time = time.time() 
+            torch.cuda.reset_peak_memory_stats()
+            process = psutil.Process(os.getpid())
+            run_nested_cv(args, data=X, label=label, nsnp = nsnp, device = args.device)
+
+            elapsed_time = time.time() - start_time
+            print(f"running time: {elapsed_time:.2f} s")
+            print("successfully")
+
+
+if __name__ == '__main__':
+    GEFormer_reg()

gpbench/method_reg/GEFormer/GEFormer_Hyperparameters.py

@@ -0,0 +1,106 @@
+import os
+import time
+import psutil
+import random
+import torch
+import numpy as np
+import optuna
+from sklearn.model_selection import KFold, train_test_split
+from .gMLP import GEFormer
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from optuna.exceptions import TrialPruned 
+
+def run_nested_cv_with_early_stopping(data, label, nsnp, learning_rate, patience, batch_size, epoch=1000):
+    device = torch.device("cuda:0")
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+    
+    for fold, (train_index, test_index) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        X_train, X_test = data[train_index], data[test_index]
+        y_train, y_test = label[train_index], label[test_index]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
+
+        x_train_tensor = torch.from_numpy(X_train_sub).float().to(device)
+        y_train_tensor = torch.from_numpy(y_train_sub).float().to(device)
+        x_valid_tensor = torch.from_numpy(X_valid).float().to(device)
+        y_valid_tensor = torch.from_numpy(y_valid).float().to(device)
+        x_test_tensor = torch.from_numpy(X_test).float().to(device)
+        y_test_tensor = torch.from_numpy(y_test).float().to(device)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, batch_size, shuffle=False)
+
+        model = GEFormer(nsnp=nsnp)
+        model.train_model(train_loader, valid_loader, epoch, learning_rate, patience, device)
+        y_pred = model.predict(test_loader)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        if np.isnan(pcc):
+            print(f"Fold {fold} resulted in NaN PCC, pruning the trial...")
+            raise TrialPruned()
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+                f'CPU={fold_cpu_mem:.2f}MB')
+        
+    return np.mean(all_pcc) if all_pcc else 0.0
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def Hyperparameter(data, label, nsnp):
+    set_seed(42)
+    
+    def objective(trial):
+        learning_rate = trial.suggest_loguniform("learning_rate", 1e-4,0.1)
+        batch_size = trial.suggest_categorical("batch_size", [32, 64, 128])
+        patience = trial.suggest_int("patience", 1, 10)
+        try:
+            corr_score = run_nested_cv_with_early_stopping(
+                data=data,
+                label=label,
+                nsnp=nsnp,
+                learning_rate=learning_rate,
+                patience=patience,
+                batch_size=batch_size
+            )
+        
+        except TrialPruned:
+            return float("-inf")
+        return corr_score
+    
+    study = optuna.create_study(direction="maximize")
+    study.optimize(objective, n_trials=20)
+
+    print("best params:", study.best_params)
+    print("successfully")
+    return study.best_params

gpbench/method_reg/GEFormer/__init__.py

@@ -0,0 +1,5 @@
+from .GEFormer import GEFormer_reg
+
+GEFormer = GEFormer_reg
+
+__all__ = ["GEFormer","GEFormer_reg"]