GANsDTA: Predicting Drug-Target Binding Affinity Using GANs

The computational prediction of interactions between drugs and targets is a standing challenge in drug discovery. State-of-the-art methods for drug-target interaction prediction are primarily based on supervised machine learning with known label information. However, in biomedicine, obtaining labeled training data is an expensive and a laborious process. This paper proposes a semi-supervised generative adversarial networks (GANs)-based method to predict binding affinity. Our method comprises two parts, two GANs for feature extraction and a regression network for prediction. The semi-supervised mechanism allows our model to learn proteins drugs features of both labeled and unlabeled data. We evaluate the performance of our method using multiple public datasets. Experimental results demonstrate that our method achieves competitive performance while utilizing freely available unlabeled data. Our results suggest that utilizing such unlabeled data can considerably help improve performance in various biomedical relation extraction processes, for example, Drug-Target interaction and protein-protein interaction, particularly when only limited labeled data are available in such tasks. To our best knowledge, this is the first semi-supervised GANs-based method to predict binding affinity.

[1]  David S. Wishart,et al.  DrugBank: a comprehensive resource for in silico drug discovery and exploration , 2005, Nucleic Acids Res..

[2]  Arzucan Özgür,et al.  DeepDTA: deep drug–target binding affinity prediction , 2018, Bioinform..

[3]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Yoshihiro Yamanishi,et al.  Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework , 2010, Bioinform..

[5]  Yanli Wang,et al.  PubChem: Integrated Platform of Small Molecules and Biological Activities , 2008 .

[6]  Theonie Anastassiadis,et al.  Comprehensive assay of kinase catalytic activity reveals features of kinase inhibitor selectivity , 2011, Nature biotechnology.

[7]  Liang Cheng,et al.  Exposing the Causal Effect of C-Reactive Protein on the Risk of Type 2 Diabetes Mellitus: A Mendelian Randomization Study , 2018, Front. Genet..

[8]  Wojciech Czarnecki,et al.  Learning to SMILE(S) , 2016, ArXiv.

[9]  Mindy I. Davis,et al.  Comprehensive analysis of kinase inhibitor selectivity , 2011, Nature Biotechnology.

[10]  Yoshua Bengio,et al.  Boundary-Seeking Generative Adversarial Networks , 2017, ICLR 2017.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Shuigeng Zhou,et al.  Boosting compound-protein interaction prediction by deep learning , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[13]  Jie Sun,et al.  DincRNA: a comprehensive web-based bioinformatics toolkit for exploring disease associations and ncRNA function , 2018, Bioinform..

[14]  Jiajie Peng,et al.  InfAcrOnt: calculating cross-ontology term similarities using information flow by a random walk , 2018, BMC Genomics.

[15]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[16]  Keith C. C. Chan,et al.  Large-scale prediction of drug-target interactions from deep representations , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[17]  Artem Cherkasov,et al.  SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines , 2017, Journal of Cheminformatics.

[18]  Hojung Nam,et al.  SELF-BLM: Prediction of drug-target interactions via self-training SVM , 2017, PloS one.

[19]  Chunyan Miao,et al.  Neighborhood Regularized Logistic Matrix Factorization for Drug-Target Interaction Prediction , 2016, PLoS Comput. Biol..

[20]  Tapio Pahikkala,et al.  Toward more realistic drug^target interaction predictions , 2014 .

[21]  Kunal Roy,et al.  Some case studies on application of “rm2” metrics for judging quality of quantitative structure–activity relationship predictions: Emphasis on scaling of response data , 2013, J. Comput. Chem..

[22]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[23]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[24]  Meng Zhou,et al.  MetSigDis: a manually curated resource for the metabolic signatures of diseases , 2019, Briefings Bioinform..

[25]  Ivan G. Costa,et al.  A multiple kernel learning algorithm for drug-target interaction prediction , 2016, BMC Bioinformatics.

[26]  Liang Cheng,et al.  gutMDisorder: a comprehensive database for dysbiosis of the gut microbiota in disorders and interventions , 2019, Nucleic acids research.

[27]  Jun Ye,et al.  CGBVS‐DNN: Prediction of Compound‐protein Interactions Based on Deep Learning , 2017, Molecular informatics.

[28]  Tao Xu,et al.  Making Sense of Large-Scale Kinase Inhibitor Bioactivity Data Sets: A Comparative and Integrative Analysis , 2014, J. Chem. Inf. Model..

[29]  K. Roy,et al.  On Two Novel Parameters for Validation of Predictive QSAR Models , 2009, Molecules.

[30]  Wanying Xu,et al.  OAHG: an integrated resource for annotating human genes with multi-level ontologies , 2016, Scientific Reports.

[31]  Qinghua Guo,et al.  LncRNA2Target v2.0: a comprehensive database for target genes of lncRNAs in human and mouse , 2018, Nucleic Acids Res..