Machine Learning in Drug Discovery and Development

被引:18
作者
Wale, Nikil [1 ]
机构
[1] Pfizer Inc, Groton Labs 200 3055, Computat Sci Ctr Emphasis, Groton, CT 06340 USA
关键词
machine learning; statistical methods; prediction; virtual screening; chemogenomics; safety prediction; SVM; CHEMICAL-COMPOUND RETRIEVAL; DESCRIPTOR SPACES; PREDICTION; KERNELS; MODELS; MUTAGENICITY; TOXICITY; GENETICS; GENOME;
D O I
10.1002/ddr.20407
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
In-silico tools and computational techniques have become an integral part of pharmaceutical research. These techniques are now used extensively at various phases during the drug development process. Such tools perform a wide range of functions from retrieving and analyzing data to sophisticated computational models for many biological and chemical processes in drug discovery. Among them, machine-learning techniques are becoming especially popular because of their emphasis on obtaining accurate predictions. In this overview, we discuss the increasing role of Machine Learning in Drug Discovery. Since this field has close connections with the field of Statistics, we will first describe similarities and differences between these fields. We will then highlight various domains and problems within drug discovery that are utilizing machine-learning technology to improve and speed up the drug discovery process. Drug Dev Res 72: 112-119, 2011. (C) 2010 Wiley-Liss, Inc.
引用
收藏
页码:112 / 119
页数:8
相关论文
共 61 条
[1]   Ranking Chemical Structures for Drug Discovery: A New Machine Learning Approach [J].
Agarwal, Shivani ;
Dugar, Deepak ;
Sengupta, Shiladitya .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2010, 50 (05) :716-731
[2]  
[Anonymous], 2005, ALGORITHMIC LEARNING, DOI DOI 10.1007/B106715
[3]  
[Anonymous], NAT AC SCI S DYN SOC
[4]   Ensemble of linear models for predicting drug properties [J].
Arodz, T ;
Yuen, DA ;
Dudek, AZ .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2006, 46 (01) :416-423
[5]   Predicting gene regulatory elements in silico on a genomic scale [J].
Brazma, A ;
Jonassen, I ;
Vilo, J ;
Ukkonen, E .
GENOME RESEARCH, 1998, 8 (11) :1202-1215
[6]   Statistical modeling: The two cultures [J].
Breiman, L .
STATISTICAL SCIENCE, 2001, 16 (03) :199-215
[7]   Evaluation of machine-learning methods for ligand-based virtual screening [J].
Chen, Beining ;
Harrison, Robert F. ;
Papadatos, George ;
Willett, Peter ;
Wood, David J. ;
Lewell, Xiao Qing ;
Greenidge, Paulette ;
Stiefl, Nikolaus .
JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN, 2007, 21 (1-3) :53-62
[8]   Frequent substructure-based approaches for classifying chemical compounds [J].
Deshpande, M ;
Kuramochi, M ;
Wale, N ;
Karypis, G .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (08) :1036-1050
[9]  
DEVORE J, 2004, STAT EXPLORATION ANA
[10]   The ToxCast program for prioritizing toxicity testing of environmental chemicals [J].
Dix, David J. ;
Houck, Keith A. ;
Martin, Matthew T. ;
Richard, Ann M. ;
Setzer, R. Woodrow ;
Kavlock, Robert J. .
TOXICOLOGICAL SCIENCES, 2007, 95 (01) :5-12