Improving the drug discovery process by using multiple classifier systems
作者：
Highlights：
• Review of existing ML-based in-silico screening models for drug discovery domain.
• Creation of new feature clustering techniques to tackle high-dimensionality datasets.
• Use of problem-oriented measures to improve classification accuracy.
• Comparison of D2-MCS against most popular ML classifiers in the drug discovery domain.
• Construction of ML models according to the intrinsic characteristic of each cluster.
摘要
•Review of existing ML-based in-silico screening models for drug discovery domain.•Creation of new feature clustering techniques to tackle high-dimensionality datasets.•Use of problem-oriented measures to improve classification accuracy.•Comparison of D2-MCS against most popular ML classifiers in the drug discovery domain.•Construction of ML models according to the intrinsic characteristic of each cluster.
论文关键词：Drug discovery,Machine learning algorithms,Feature clustering,Multiple classifier systems
论文评审过程：Received 25 May 2018, Revised 18 December 2018, Accepted 19 December 2018, Available online 20 December 2018, Version of Record 24 December 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.12.032
