TY - GEN
T1 - Improved machine learning models for predicting selective compounds
AU - Ning, Xia
AU - Walters, Michael
AU - Karypis, George
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
KW - Compound selectivity
KW - Multi-task learning
UR - http://www.scopus.com/inward/record.url?scp=84858968202&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84858968202&partnerID=8YFLogxK
U2 - 10.1145/2147805.2147817
DO - 10.1145/2147805.2147817
M3 - Conference contribution
AN - SCOPUS:84858968202
SN - 9781450307963
T3 - 2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2011
SP - 106
EP - 115
BT - 2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2011
T2 - 2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, ACM-BCB 2011
Y2 - 1 August 2011 through 3 August 2011
ER -