Machine learning in computational docking

作者：

Highlights：

• The state-of-the-art machine-learning techniques in computational docking.

• Various molecular features extracted from molecular databases and software.

• Potential future research directions e.g. combining more than one ML-model.

• The inclusion of quantum effects providing rigorous molecular description.

• Generalizing of bio-molecular applications, e.g., protein–protein docking.

摘要

Highlights•The state-of-the-art machine-learning techniques in computational docking.•Various molecular features extracted from molecular databases and software.•Potential future research directions e.g. combining more than one ML-model.•The inclusion of quantum effects providing rigorous molecular description.•Generalizing of bio-molecular applications, e.g., protein–protein docking.

论文关键词：Machine learning,Random forest,Support vector machine,Drug discovery,Computational docking,Scoring function,Virtual screening,Complex binding affinity,Ligands ranking accuracy,Force field interaction,Pharmacophore fingerprint

论文评审过程：Received 27 July 2014, Revised 8 January 2015, Accepted 9 February 2015, Available online 16 February 2015.

论文官网地址：https://doi.org/10.1016/j.artmed.2015.02.002