基于随机森林（RF）的机器学习模型预测hERG阻断剂活性

#导入依赖库import pandas as pdimport numpy as npimport warnings; warnings.simplefilter('ignore')
from rdkit import Chem, DataStructsfrom rdkit.Chem.Draw import IPythonConsolefrom rdkit.Chem import PandasToolsfrom rdkit.Chem import AllChem, Draw
from sklearn.ensemble import RandomForestClassifier#from sklearn.model_selection import StratifiedKFoldfrom imblearn.under_sampling import RandomUnderSamplerfrom sklearn.metrics import recall_score, roc_auc_scorefrom sklearn.model_selection import KFold, StratifiedKFold,StratifiedShuffleSplitfrom sklearn.model_selection import train_test_splitfrom matplotlib import cm
import mathimport pickleimport os

class FP:    """    A fingerprint class that inserts molecular fingerprints into pandas data frame    """    def __init__(self, fp):        self.fp = fp    def __str__(self):        return "%d bit FP" % len(self.fp)    def __len__(self):        return len(self.fp)
def get_morgan_fp(mol):    """    Returns the RDKit Morgan fingerprint for a molecule    """    info = {}    arr = np.zeros((1,))    fp = AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=1024, useFeatures=False, bitInfo=info)    DataStructs.ConvertToNumpyArray(fp, arr)    arr = np.array([len(info[x]) if x in info else 0 for x in range(1024)])
    return FP(arr)

df = pd.read_csv("chembl_training_T3.csv", index_col=0)
PandasTools.AddMoleculeColumnToFrame(df, smilesCol='can_smiles')
df = df[~df.ROMol.isnull()]
df['fp'] = df.apply(lambda x: get_morgan_fp(x['ROMol']), axis=1)

df.head()   #查看数据

X = np.array([x.fp for x in df.fp])X.shape
y = np.array(df.ac)y.shape

# Initialize performance measuressens     = np.array([])spec     = np.array([])auc      = np.array([])
# 10-fold cross-validation splitkfolds = StratifiedKFold(n_splits=10, shuffle=True, random_state=0)kfolds.get_n_splits(X, y)print(kfolds)

for train, test in kfolds.split(X, y):    # Split data to training and test set    X_train, X_test, y_train, y_test = X[train], X[test], y[train], y[test]    
    # Training a random forest classifier    rf_clf = RandomForestClassifier(n_estimators=100, criterion='gini', n_jobs=1)    rf_clf.fit(X_train, y_train)
    # Predicting the test set    y_pred       = rf_clf.predict(X_test)    y_pred_proba = rf_clf.predict_proba(X_test).T[1]
    # Append performance measures    auc  = np.append(auc, roc_auc_score(y_test, y_pred_proba))    sens = np.append(sens, recall_score(y_test, y_pred, pos_label=1))    spec = np.append(spec, recall_score(y_test, y_pred, pos_label=0))

# 10-fold cross-validation performanceprint('AUC:\t\t\t%.2f +/- %.2f' % (auc.mean(), auc.std()))print('Sensitivity:\t\t%.2f +/- %.2f' % (sens.mean(), sens.std()))print('Specificity:\t\t%.2f +/- %.2f' % (spec.mean(), spec.std()))

AUC:			0.95 +/- 0.01
Sensitivity:		0.84 +/- 0.03
Specificity:		0.91 +/- 0.03

mySMILES ='Fc1ccc(cc1)n3c2ccc(Cl)cc2c(c3)C5CCN(CCN4C(=O)NCC4)CC5'from rdkit import RDConfigmySMILESinput = pd.DataFrame(columns=['ID','my_smiles']) mySMILESinput = mySMILESinput.append({'ID':123, 'my_smiles':mySMILES}, ignore_index=True)   PandasTools.AddMoleculeColumnToFrame(mySMILESinput,'my_smiles','ROMol')

mySMILESinput['fp'] = mySMILESinput.apply(lambda x: get_morgan_fp(x['ROMol']), axis=1)mySMILESinput

resQuery = np.array([x.fp for x in mySMILESinput.fp])y_pred = rf_clf.predict(resQuery)y_pred

print(rf_clf.predict(resQuery))print(rf_clf.predict_proba(resQuery))

[1]
[[0.04 0.96]]