drugclust a machine learning approach for drugs side effects prediction：（drugclust机器学习的方法对药物副作用的预测）.pdfVIP

Computational Biology and Chemistry 68 (2017) 204–210 Contents lists available at ScienceDirect Computational Biology and Chemistry j o u rn al h omepage: w w w. elsev /locate/compbiolchem Research Article DrugClust: A machine learning approach for drugs side effects prediction Giovanna Maria Dimitri ∗ , Pietro Lió Computer Laboratory, University of Cambridge, 15 JJ Thomson Avenue, Cambridge, UK a r t i c l e i n f o a b s t r a c t Article history: Background: Identification of underlying mechanisms behind drugs side effects is of extreme interest and Received 8 May 2016 importance in drugs discovery today. Therefore machine learning methodology, linking such different Received in revised form 11 February 2017 multi features aspects and able to make predictions, are crucial for understanding side effects. Accepted 27 March 2017 Methods: In this paper we present DrugClust, a machine learning algorithm for drugs side effects pre- Available online 30 March 2017 diction. DrugClust pipeline works as follows: first drugs are clustered with respect to their features and then side effects predictions are made, according to Bayesian scores. Biological validation of resulting Keywords: clusters can be done via enrichment analysis, another functionality implemented in the methodology. Drugs side effects Machine learning This last tool is of extreme interest for drug discovery,