Drug-pathway interaction prediction via multiple feature fusion.

Predicting new drug-pathway interactions from heterogeneous biological data is important not only for the understanding of various drug response and molecular interaction processes, but also for the development of novel drugs and the therapy of human diseases. In this paper, three different learning methods including the Bipartite Local Models method (BLM), Gaussian Interaction Profiles kernels (GIP) method and Graph-based Semi-supervised Learning method (GBSSL) were used to predict drug-pathway interactions. To realize the purpose, drugs were firstly represented by functional groups and chemical structure similarity, and pathways were represented by their related gene expressions and semantic similarity based features. Then, the parameter optimization procedures were further adopted to deal with heterogeneous data sources. As a result, the proposed methods achieved a high ROC curve score (AUC score) over 0.95, which validated the effectiveness of multiple information integration. Moreover, several new potential drug-pathway interactions were identified for further biological function research.

[1]  Yoshihiro Yamanishi,et al.  Supervised prediction of drug–target interactions using bipartite local models , 2009, Bioinform..

[2]  Xing-Ming Zhao,et al.  Prediction of Drug Combinations by Integrating Molecular and Pharmacological Data , 2011, PLoS Comput. Biol..

[3]  K. Kohn,et al.  CellMiner: a web-based suite of genomic and pharmacologic tools to explore transcript and drug patterns in the NCI-60 cell line set. , 2012, Cancer research.

[4]  Rachael P. Huntley,et al.  QuickGO: a web-based tool for Gene Ontology searching , 2009, Bioinform..

[5]  Michael A Babyak,et al.  What You See May Not Be What You Get: A Brief, Nontechnical Introduction to Overfitting in Regression-Type Models , 2004, Psychosomatic medicine.

[6]  Corinna Blasse,et al.  CancerResource: a comprehensive database of cancer-relevant proteins and compound interactions supported by experimental knowledge , 2010, Nucleic Acids Res..

[7]  Yong Wang,et al.  Computationally Probing Drug-Protein Interactions Via Support Vector Machine , 2010 .

[8]  Fan Zhang,et al.  Topologically inferring risk-active pathways toward precise cancer classification by directed random walk , 2013, Bioinform..

[9]  Mário J. Silva,et al.  Measuring semantic similarity between Gene Ontology terms , 2007, Data Knowl. Eng..

[10]  R. Sharan,et al.  PREDICT: a method for inferring novel drug indications with application to personalized medicine , 2011, Molecular systems biology.

[11]  Yong Wang,et al.  Computational Study of Drugs by Integrating Omics Data with Kernel Methods , 2013, Molecular informatics.

[12]  Yoshihiro Yamanishi,et al.  Prediction of drug–target interaction networks from the integration of chemical and genomic spaces , 2008, ISMB.

[13]  R. Shoemaker.  The NCI60 human tumour cell line anticancer drug screen , 2006, Nature Reviews Cancer.

[14]  R. Todeschini,et al.  Molecular Descriptors for Chemoinformatics: Volume I: Alphabetical Listing / Volume II: Appendices, References , 2009 .

[15]  Qing Liu,et al.  Predicting drug-target interaction networks of human diseases based on multiple feature information. , 2013, Pharmacogenomics.

[16]  Pooja Mittal,et al.  A novel signaling pathway impact analysis , 2009, Bioinform..

[17]  K. Chou,et al.  Predicting Drug-Target Interaction Networks Based on Functional Groups and Biological Features , 2010, PloS one.

[18]  Bozena Kaminska,et al.  Identification of Pathway Deregulation – Gene Expression Based Analysis of Consistent Signal Transduction , 2012, PloS one.

[19]  Roberto Todeschini,et al.  Molecular descriptors for chemoinformatics , 2009 .

[20]  Weiming Yu,et al.  Predicting drug‐target interactions based on an improved semi‐supervised learning approach , 2011 .

[21]  Sampsa Hautaniemi,et al.  Fast Gene Ontology based clustering for microarray experiments , 2008, BioData Mining.

[22]  Michel Dumontier,et al.  Identifying aberrant pathways through integrated analysis of knowledge in pharmacogenomics , 2012, Bioinform..

[23]  P. Aloy,et al.  Unveiling the role of network and systems biology in drug discovery. , 2010, Trends in pharmacological sciences.

[24]  Igor V. Tetko,et al.  Virtual Computational Chemistry Laboratory – Design and Description , 2005, J. Comput. Aided Mol. Des..

[25]  M. Ashburner,et al.  Gene Ontology: tool for the unification of biology , 2000, Nature Genetics.

[26]  Elena Marchiori,et al.  Gaussian interaction profile kernels for predicting drug-target interaction , 2011, Bioinform..

[27]  Hongyu Zhao,et al.  Drug target inference through pathway analysis of genomics data. , 2013, Advanced drug delivery reviews.

[28]  Michael R. Kosorok,et al.  Identification of differential gene pathways with principal component analysis , 2009, Bioinform..

[29]  Roded Sharan,et al.  Large-Scale Elucidation of Drug Response Pathways in Humans , 2012, J. Comput. Biol..

[30]  M. Kanehisa,et al.  Development of a chemical structure comparison method for integrated analysis of chemical and genomic information in the metabolic pathways. , 2003, Journal of the American Chemical Society.

[31]  Hongyu Zhao,et al.  iFad: an integrative factor analysis model for drug-pathway association inference , 2012, Bioinform..