Machine-learning approaches in drug discovery: methods and applications

• Published in: Drug discovery today 2015-03, Vol.20 (3), p.318-331
• Main Author: Lavecchia, Antonio
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Bayes Theorem; Decision Trees; Drug Discovery; Neural Networks (Computer)
• ISSN: 1359-6446; 1878-5832
• DOI: 10.1016/j.drudis.2014.10.012

•We review machine learning methods/tools relevant to ligand-based virtual screening.•Machine learning methods classify compounds and predict new active molecules.•We discuss challenges, limitations and advantages of the methods and tools.•The wide applicability of the approaches is demonstrated in several case studies.•Some new algorithms and concepts in the machine learning field are provided. During the past decade, virtual screening (VS) has evolved from traditional similarity searching, which utilizes single reference compounds, into an advanced application domain for data mining and machine-learning approaches, which require large and representative training-set compounds to learn robust decision rules. The explosive growth in the amount of public domain-available chemical and biological data has generated huge effort to design, analyze, and apply novel learning methodologies. Here, I focus on machine-learning techniques within the context of ligand-based VS (LBVS). In addition, I analyze several relevant VS studies from recent publications, providing a detailed view of the current state-of-the-art in this field and highlighting not only the problematic issues, but also the successes and opportunities for further advances. This paper focuses on machine-learning approaches in the context of ligand-based virtual screening for addressing complex compound classification problems and predicting new active molecules.