Hyper-parameter optimization of multiple machine learning algorithms for molecular property prediction using hyperopt library

作     者：Jun Zhang Qin Wang Weifeng Shen Jun Zhang;Qin Wang;Weifeng Shen

作者机构：School of Chemistry and Chemical EngineeringChongqing UniversityChongqing 401331China School of Chemistry and Chemical EngineeringChongqing University of Science&TechnologyChongqing 401331China Chongqing Key Laboratory of Theoretical and Computational ChemistryChongqing 400044China 

出 版 物：《Chinese Journal of Chemical Engineering》 (中国化学工程学报（英文版）)

年 卷 期：2022年第52卷第12期

页      面：115-125页

核心收录：

学科分类：0710[理学-生物学] 0711[理学-系统科学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：financial support provided by the National Key Research and Development Project(2019YFC0214403) Chongqing Joint Chinese Medicine Scientific Research Project(2021ZY023984) 

主　　题：Machine learning Prediction Optimal design Hyper-parameter optimization Hyperopt library 

摘      要：Due to outstanding performance in cheminformatics,machine learning algorithms have been increasingly used to mine molecular properties and biomedical big *** performance of machine learning models is known to critically depend on the selection of the hyper-parameter ***,many studies either explored the optimal hyper-parameters per the grid searching method or employed arbitrarily selected hyper-parameters,which can easily lead to achieving a suboptimal hyper-parameter *** this study,Hyperopt library embedding with the Bayesian optimization is employed to find optimal hyper-parameters for different machine learning *** drug discovery datasets,including solubility,probe-likeness,h ERG,Chagas disease,tuberculosis,and malaria,are used to compare different machine learning algorithms with ECFP6 *** contribution aims to evaluate whether the Bernoulli Na?ve Bayes,logistic linear regression,Ada Boost decision tree,random forest,support vector machine,and deep neural networks algorithms with optimized hyper-parameters can offer any improvement in testing as compared with the referenced models assessed by an array of metrics including AUC,F1-score,Cohen’s kappa,Matthews correlation coefficient,recall,precision,and *** on the rank normalized score approach,the Hyperopt models achieve better or comparable performance on 33 out 36 models for different drug discovery datasets,showing significant improvement achieved by employing the Hyperopt *** open-source code of all the 6 machine learning frameworks employed in the Hyperopt python package is provided to make this approach accessible to more scientists,who are not familiar with writing code.