Use of machine learning approaches for novel drug discovery

被引:161
作者
Lima, Angelica Nakagawa [1 ]
Philot, Eric Allison [1 ]
Goulart Trossini, Gustavo Henrique [2 ]
Barbour Scott, Luis Paulo [3 ]
Maltarollo, Vinicius Goncalves [2 ]
Honorio, Kathia Maria [1 ,4 ]
机构
[1] Univ Fed ABC, Ctr Ciencias Nat & Humanas, Sao Paulo, Brazil
[2] Univ Sao Paulo, Dept Farm, Fac Ciencias Farmaceut, Sao Paulo, Brazil
[3] Univ Fed ABC, Ctr Matemat Comp & Cognicao, Sao Paulo, Brazil
[4] Univ Sao Paulo, Escola Artes Ciencias & Humanidades, Sao Paulo, Brazil
基金
巴西圣保罗研究基金会;
关键词
LBDD; Drug Design; Machine Learning; SBDD; PROTEIN SECONDARY STRUCTURE; SUPPORT VECTOR MACHINE; VARIABLE SELECTION METHODS; HIDDEN MARKOV MODEL; OF-THE-ART; STRUCTURE PREDICTION; MULTITARGET DRUGS; LIGAND DOCKING; HOMOLOGY DETECTION; MOLECULAR DOCKING;
D O I
10.1517/17460441.2016.1146250
中图分类号
R9 [药学];
学科分类号
1007 ;
摘要
Introduction: The use of computational tools in the early stages of drug development has increased in recent decades. Machine learning (ML) approaches have been of special interest, since they can be applied in several steps of the drug discovery methodology, such as prediction of target structure, prediction of biological activity of new ligands through model construction, discovery or optimization of hits, and construction of models that predict the pharmacokinetic and toxicological (ADMET) profile of compounds. Areas covered: This article presents an overview on some applications of ML techniques in drug design. These techniques can be employed in ligand-based drug design (LBDD) and structure-based drug design (SBDD) studies, such as similarity searches, construction of classification and/or prediction models of biological activity, prediction of secondary structures and binding sites docking and virtual screening. Expert opinion: Successful cases have been reported in the literature, demonstrating the efficiency of ML techniques combined with traditional approaches to study medicinal chemistry problems. Some ML techniques used in drug design are: support vector machine, random forest, decision trees and artificial neural networks. Currently, an important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.
引用
收藏
页码:225 / 239
页数:15
相关论文
共 161 条
[111]  
Patrick G.L., 1995, An Introduction to Medicinal Chemistry
[112]  
Petersen TN, 2000, PROTEINS, V41, P17, DOI 10.1002/1097-0134(20001001)41:1<17::AID-PROT40>3.3.CO
[113]  
2-6
[114]   Comparative analysis of local and consensus quantitative structure-activity relationship approaches for the prediction of bioconcentration factor [J].
Piir, G. ;
Sild, S. ;
Maran, U. .
SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2013, 24 (03) :175-199
[115]  
Platt JC, 1999, ADVANCES IN KERNEL METHODS, P185
[116]   Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles [J].
Pollastri, G ;
Przybylski, D ;
Rost, B ;
Baldi, P .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2002, 47 (02) :228-235
[117]   Proteochemometrics analysis of substrate interactions with dengue virus NS3 proteases [J].
Prusis, Peteris ;
Lapins, Maris ;
Yahorava, Sviatlana ;
Petrovska, Ramona ;
Niyomrattanakit, Pornwaratt ;
Katzenmeier, Gerd ;
Wikberg, Jarl E. S. .
BIOORGANIC & MEDICINAL CHEMISTRY, 2008, 16 (20) :9369-9377
[118]   Alignments grow, secondary structure prediction improves [J].
Przybylski, D ;
Rost, B .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2002, 46 (02) :197-205
[119]   PREDICTING THE SECONDARY STRUCTURE OF GLOBULAR-PROTEINS USING NEURAL NETWORK MODELS [J].
Qian, N ;
SEJNOWSKI, TJ .
JOURNAL OF MOLECULAR BIOLOGY, 1988, 202 (04) :865-884
[120]   Active-learning strategies in computer-assisted drug discovery [J].
Reker, Daniel ;
Schneider, Gisbert .
DRUG DISCOVERY TODAY, 2015, 20 (04) :458-465