Improved machine learning models for predicting selective compounds

Xia Ning, Michael Walters, George Karypis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The identification of small potent compounds that selectively bind to the target under consideration with high affinities is a critical step towards successful drug discovery. However, there still lacks efficient and accurate computational methods to predict compound selectivity properties. In this paper, we propose a set of machine learning methods to do compound selectivity prediction. In particular, we propose a novel cascaded learning method and a multi-task learning method. The cascaded method decomposes the selectivity prediction into two steps, one model for each step, so as to effectively filter out non-selective compounds. The multi-task method incorporates both activity and selectivity models into one multi-task model so as to better differentiate compound selectivity properties. We conducted a comprehensive set of experiments and compared the results with other conventional selectivity prediction methods, and our results demonstrated that the cascaded and multi-task methods significantly improve the selectivity prediction performance.

Original languageEnglish (US)
Title of host publication2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2011
Pages106-115
Number of pages10
DOIs
StatePublished - Dec 1 2011
Event2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, ACM-BCB 2011 - Chicago, IL, United States
Duration: Aug 1 2011Aug 3 2011

Publication series

Name2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2011

Other

Other2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, ACM-BCB 2011
CountryUnited States
CityChicago, IL
Period8/1/118/3/11

Keywords

  • Compound selectivity
  • Multi-task learning

Fingerprint Dive into the research topics of 'Improved machine learning models for predicting selective compounds'. Together they form a unique fingerprint.

Cite this