logPexp # Default modelsmodels = {"rf": RandomForestRegressor(n_estimators=100, random_state=42), "nnet": MLPRegressor(random_state=42), "svr": SVR(gamma='auto')} scores = {} for f in fps: scores[f] = {} # Convert fps to 2D numpy array X = np.array(fps[f].tolist()) X...
RDKit | 通过评估合成难度(SA Score)筛选化合物 https://blog.csdn.net/u012325865/article/details/102488056 RDKit | 天然产物的相似度评分(NP-likeness) https://blog.csdn.net/u012325865/article/details/102593918 RDKit | RDKit 中的RECAP进行分子裂解 https://blog.csdn.net/u012325865/article/details...
X = np.array(fps[f].tolist()) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42) for m in models: models[m].fit(X_train, y_train) #scores[f][m + "_r2_train"] = models[m].score(X_train, y_train) y_pred = models[m].pr...
accuracy_score(test_y, pred_y) 0.7665369649805448 print(classification_report(test_y, pred_y)) 3 基于3D分子描述符预测溶解度 导入包 from rdkit.Chem import AllChem from rdkit.Chem.Descriptors import rdMolDescriptors from sklearn.preprocessing import normalize from sklearn.ensemble import RandomForest...
# In[11]:随机森林模型rf = RandomForestRegressor(n_estimators=100, oob_score=True, max_features='auto')rf.fit(X_train, y_train)# In[12]:y_pred = rf.predict(X_test)rms = (np.mean((y_test - y_pred)**2))**0.5print ("RF RMS", rms)# out[12]:RF RMS 0.6057144333891424# In[...
metrics import silhouette_samples, silhouette_score from sklearn.cluster import KMeans 2. 载入分子数据 该库包含超过10 000 000个SMILES。 可以将.smiles文件作为文本文件读取,将10000个分子保存在pandas中。 文章来源: drugai.blog.csdn.net,作者:DrugAI,版权归原作者所有,如需转载,请联系作者。 原文链接:...
#导入依赖库importnumpyasnp from rdkitimportChem from rdkit.Chem.CrippenimportMolLogP from rdkitimportChem,DataStructs from rdkit.ChemimportAllChem from sklearn.svmimportSVRfrom sklearn.metricsimportmean_squared_error,r2_score from scipyimportstatsimportmatplotlib.pyplotasplt ...
importcopyimportcollectionsimportpandasaspdimportnumpyasnp from rdkitimportChem from rdkit.ChemimportDescriptors from rdkit.ML.DescriptorsimportMoleculeDescriptors from sklearnimportmodel_selection from sklearn.metricsimportconfusion_matrix from sklearn.metricsimportaccuracy_score ...
Reid, Ricardo Rodriguez, Nikitas Rontsis, Fio Ruggiu, Vincent F. Scalfani, Ulrich Schatzschneider, Wonseok Shin, Anton Siomchen, Paolo Tosco, Kollin Trujillo, Ivan Tubert-Brohman, Franz Waibl, Rachel Walker, Riccardo Vianello, Marco Visani, QJ-Chen, UENO, M., heng-yin, EvaSnow, JP, J...
Tanimoto score exceeds 1 for deuterium-containing molecules in rdShapeAlign.AlignMol() (github issue #8096 from fulopjoz) Rascal returns empty results even when told not to (github issue #8098 from DavidACosgrove) Use endian-aware read/write for length of string. (github pull #8105 from Da...