Genome-Scale Screening of Drug-Target Associations Relevant to Ki Using a Chemogenomics Approach

The identification of interactions between drugs and target proteins plays a key role in genomic drug discovery. In the present study, the quantitative binding affinities of drug-target pairs are differentiated as a measurement to define whether a drug interacts with a protein or not, and then a chemogenomics framework using an unbiased set of general integrated features and random forest (RF) is employed to construct a predictive model which can accurately classify drug-target pairs. The predictability of the model is further investigated and validated by several independent validation sets. The built model is used to predict drug-target associations, some of which were confirmed by comparing experimental data from public biological resources. A drug-target interaction network with high confidence drug-target pairs was also reconstructed. This network provides further insight for the action of drugs and targets. Finally, a web-based server called PreDPI-Ki was developed to predict drug-target interactions for drug discovery. In addition to providing a high-confidence list of drug-target associations for subsequent experimental investigation guidance, these results also contribute to the understanding of drug-target interactions. We can also see that quantitative information of drug-target associations could greatly promote the development of more accurate models. The PreDPI-Ki server is freely available via: http://sdd.whu.edu.cn/dpiki.

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

[2]  Hiroyuki Ogata,et al.  AAindex: Amino Acid Index Database , 1999, Nucleic Acids Res..

[3]  A. Barabasi,et al.  Network biology: understanding the cell's functional organization , 2004, Nature Reviews Genetics.

[4]  Xiaobo Zhou,et al.  Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces , 2010, BMC Systems Biology.

[5]  Gerhard Klebe,et al.  AffinDB: a freely accessible database of affinities for protein–ligand complexes from the PDB , 2005, Nucleic Acids Res..

[6]  Jennifer Venhorst,et al.  Target-drug interactions: first principles and their application to drug discovery. , 2012, Drug discovery today.

[7]  W. Jahnke,et al.  Fragment-Based Approaches , 2007 .

[8]  Jordi Mestres,et al.  Computational chemogenomics approaches to systematic knowledge-based drug discovery. , 2004, Current opinion in drug discovery & development.

[9]  Hong Liu,et al.  Computational Screening for Active Compounds Targeting Protein Sequences: Methodology and Experimental Validation , 2011, J. Chem. Inf. Model..

[10]  Lin He,et al.  DRAR-CPI: a server for identifying drug repositioning potential and adverse drug reactions via the chemical–protein interactome , 2011, Nucleic Acids Res..

[11]  Michael M. Mysinger,et al.  Automated Docking Screens: A Feasibility Study , 2009, Journal of medicinal chemistry.

[12]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[13]  E. Smith,et al.  The opioid receptor binding of dezocine, morphine, fentanyl, butorphanol and nalbuphine. , 1993, Life sciences.

[14]  Evan Bolton,et al.  An overview of the PubChem BioAssay resource , 2009, Nucleic Acids Res..

[15]  Justin Lamb,et al.  The Connectivity Map: a new tool for biomedical research , 2007, Nature Reviews Cancer.

[16]  Jean-Philippe Vert,et al.  Protein-ligand interaction prediction: an improved chemogenomics approach , 2008, Bioinform..

[17]  A. Hopkins.  Network pharmacology , 2007, Nature Biotechnology.

[18]  Michael J. Keiser,et al.  Predicting new molecular targets for known drugs , 2009, Nature.

[19]  D. Rognan.  Chemogenomic approaches to rational drug design , 2007, British journal of pharmacology.

[20]  D S Goodsell,et al.  Automated docking of flexible ligands: Applications of autodock , 1996, Journal of molecular recognition : JMR.

[21]  Mei Liu,et al.  Prediction of protein-protein interactions using random decision forest framework , 2005, Bioinform..

[22]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[23]  Paul A Clemons,et al.  The Connectivity Map: Using Gene-Expression Signatures to Connect Small Molecules, Genes, and Disease , 2006, Science.

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

[25]  J. Hickman,et al.  Drug-target interactions: only the first step in the commitment to a programmed cell death? , 1991, British Journal of Cancer.

[26]  Jordi Mestres.  Mapping the Chemogenomic Space , 2006 .

[27]  Ramón Díaz-Uriarte,et al.  GeneSrF and varSelRF: a web-based tool and R package for gene selection and classification using random forest , 2007, BMC Bioinformatics.

[28]  P. Bork,et al.  Drug Target Identification Using Side-Effect Similarity , 2008, Science.

[29]  John P. Overington,et al.  How many drug targets are there? , 2006, Nature Reviews Drug Discovery.

[30]  James A. Evans,et al.  Novel opportunities for computational biology and sociology in drug discovery. , 2010, Trends in biotechnology.

[31]  Jerome Sacks,et al.  The Construction and Assessment of a Statistical Model for the Prediction of Protein Assay Data , 2002, J. Chem. Inf. Comput. Sci..

[32]  Philippe Sanseau,et al.  Editorial: Computational methods for drug repurposing , 2011, Briefings Bioinform..

[33]  J. Irwin,et al.  Lead discovery using molecular docking. , 2002, Current opinion in chemical biology.

[34]  E. Jacoby,et al.  Chemogenomics: an emerging strategy for rapid target and drug discovery , 2004, Nature Reviews Genetics.

[35]  J. Irwin,et al.  Benchmarking sets for molecular docking. , 2006, Journal of medicinal chemistry.

[36]  C. Harris,et al.  Chemogenomics: structuring the drug discovery process to gene families. , 2006, Drug discovery today.

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

[38]  T. Klabunde.  Chemogenomic approaches to drug discovery: similar receptors bind similar ligands , 2007, British journal of pharmacology.

[39]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[40]  David S. Wishart,et al.  DrugBank 3.0: a comprehensive resource for ‘Omics’ research on drugs , 2010, Nucleic Acids Res..

[41]  Steven G Potkin,et al.  Atypical antipsychotic drug actions: unitary or multiple mechanisms for ‘atypicality’? , 2003, Clinical Neuroscience Research.

[42]  Heping Zhang,et al.  Cell and tumor classification using gene expression data: Construction of forests , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[43]  R. Solé,et al.  The topology of drug-target interaction networks: implicit dependence on drug properties and target families. , 2009, Molecular bioSystems.

[44]  Steve Horvath,et al.  Tumor classification by tissue microarray profiling: random forest clustering applied to renal cell carcinoma , 2005, Modern Pathology.

[45]  Paul Ernsberger,et al.  H1-Histamine Receptor Affinity Predicts Short-Term Weight Gain for Typical and Atypical Antipsychotic Drugs , 2003, Neuropsychopharmacology.

[46]  A. Hopkins.  Network pharmacology: the next paradigm in drug discovery. , 2008, Nature chemical biology.

[47]  B. Roth,et al.  Magic shotguns versus magic bullets: selectively non-selective drugs for mood disorders and schizophrenia , 2004, Nature Reviews Drug Discovery.

[48]  Xia Li,et al.  Gene mining: a novel and powerful ensemble decision approach to hunting for disease genes using microarray expression profiling. , 2004, Nucleic acids research.

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

[50]  Jean-Philippe Vert,et al.  Virtual screening of GPCRs: An in silico chemogenomics approach , 2008, BMC Bioinformatics.

[51]  P. Bork,et al.  Large‐scale prediction of drug–target relationships , 2008, FEBS letters.

[52]  Robert P. Sheridan,et al.  Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling , 2003, J. Chem. Inf. Comput. Sci..

[53]  I. Muchnik,et al.  Prediction of protein folding class using global description of amino acid sequence. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[54]  A. Barabasi,et al.  Drug—target network , 2007, Nature Biotechnology.

[55]  Xin Wen,et al.  BindingDB: a web-accessible database of experimentally determined protein–ligand binding affinities , 2006, Nucleic Acids Res..

[56]  Michael J. Keiser,et al.  Relating protein pharmacology by ligand chemistry , 2007, Nature Biotechnology.

[57]  Xiao Sun,et al.  Prediction of DNA-binding residues in proteins from amino acid sequences using a random forest model with a hybrid feature , 2008, Bioinform..

[58]  A. Hopkins,et al.  Ligand efficiency: a useful metric for lead selection. , 2004, Drug discovery today.

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

[60]  Y. Martin,et al.  Do structurally similar molecules have similar biological activity? , 2002, Journal of medicinal chemistry.

[61]  Stefan Günther,et al.  SuperPred: drug classification and target prediction , 2008, Nucleic Acids Res..

[62]  M. Rask-Andersen,et al.  Trends in the exploitation of novel drug targets , 2011, Nature Reviews Drug Discovery.

[63]  John P. Overington,et al.  ChEMBL: a large-scale bioactivity database for drug discovery , 2011, Nucleic Acids Res..

[64]  Joel Dudley,et al.  Exploiting drug-disease relationships for computational drug repositioning , 2011, Briefings Bioinform..

[65]  T. Ashburn,et al.  Drug repositioning: identifying and developing new uses for existing drugs , 2004, Nature Reviews Drug Discovery.

[66]  Carolin Strobl,et al.  Random forest Gini importance favours SNPs with large minor allele frequency: impact, sources and recommendations , 2012, Briefings Bioinform..

[67]  William Stafford Noble,et al.  Kernel methods for predicting protein-protein interactions , 2005, ISMB.

[68]  Thomas Lengauer,et al.  ROCR: visualizing classifier performance in R , 2005, Bioinform..

[69]  Heather A. Carlson,et al.  A Call to Arms: What You Can Do for Computational Drug Discovery , 2011, J. Chem. Inf. Model..

[70]  L. Christrup,et al.  The mu1, mu2, delta, kappa opioid receptor binding profiles of methadone stereoisomers and morphine. , 1995, Life sciences.

[71]  Wolfgang Jahnke,et al.  Fragment-based Approaches in Drug Discovery: JAHNKE: FRAGMENT-BASED APPROACHES IN DRUG DISCOVERY O-BK , 2006 .

[72]  L. Christrup,et al.  Pharmacology letterThe mu1, mu2, delta, kappa opioid receptor binding profiles of methadone stereoisomers and morphine , 1994 .

[73]  Wolfgang Jahnke and Daniel A. Erlanson.  Fragment-based approaches in drug discovery , 2013 .

[74]  G. V. Paolini,et al.  Global mapping of pharmacological space , 2006, Nature Biotechnology.

[75]  H. V. van Vlijmen,et al.  Which Compound to Select in Lead Optimization? Prospectively Validated Proteochemometric Models Guide Preclinical Development , 2011, PloS one.

[76]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.