GEFA: Early Fusion Approach in Drug-Target Affinity Prediction

Predicting the interaction between a compound and a target is crucial for rapid drug repurposing. Deep learning has been successfully applied in drug-target affinity (DTA) problem. However, previous deep learning-based methods ignore modeling the direct interactions between drug and protein residues. This would lead to inaccurate learning of target representation which may change due to the drug binding effects. In addition, previous DTA methods learn protein representation solely based on a small number of protein sequences in DTA datasets while neglecting the use of proteins outside of the DTA datasets. We propose GEFA (Graph Early Fusion Affinity), a novel graph-in-graph neural network with attention mechanism to address the changes in target representation because of the binding effects. Specifically, a drug is modeled as a graph of atoms, which then serves as a node in a larger graph of residues-drug complex. The resulting model is an expressive deep nested graph neural network. We also use pre-trained protein representation powered by the recent effort of learning contextualized protein representation. The experiments are conducted under different settings to evaluate scenarios such as novel drugs or targets. The results demonstrate the effectiveness of the pre-trained protein embedding and the advantages our GEFA in modeling the nested graph for drug-target interaction.

[1]  Atul J. Butte,et al.  Repurpose terbutaline sulfate for amyotrophic lateral sclerosis using electronic medical records , 2015, Scientific Reports.

[2]  José M. García,et al.  High-Throughput parallel blind Virtual Screening using BINDSURF , 2012, BMC Bioinformatics.

[3]  P. Sanseau,et al.  Drug repurposing: progress, challenges and recommendations , 2018, Nature Reviews Drug Discovery.

[4]  Sara Ballouz,et al.  Novel therapeutics for coronary artery disease from genome-wide association study data , 2015, BMC Medical Genomics.

[5]  John Canny,et al.  Evaluating Protein Transfer Learning with TAPE , 2019, bioRxiv.

[6]  Langchong He,et al.  Overview of the detection methods for equilibrium dissociation constant KD of drug-receptor interaction , 2018, Journal of pharmaceutical analysis.

[7]  L. Cardon,et al.  Use of genome-wide association studies for drug repositioning , 2012, Nature Biotechnology.

[8]  W. Beyer.  CRC Standard Probability And Statistics Tables and Formulae , 1990 .

[9]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[10]  Oakland J. Peters,et al.  Predicting new indications for approved drugs using a proteochemometric method. , 2012, Journal of medicinal chemistry.

[11]  I. Kuntz,et al.  Automated docking with grid‐based energy evaluation , 1992 .

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

[13]  Jonathan S. Mason,et al.  Structures of G protein-coupled receptors reveal new opportunities for drug discovery. , 2015, Drug discovery today.

[14]  Artem Cherkasov,et al.  PADME: A Deep Learning-based Framework for Drug-Target Interaction Prediction , 2018, ArXiv.

[15]  S. Brunak,et al.  Mining electronic health records: towards better research applications and clinical care , 2012, Nature Reviews Genetics.

[16]  W. L. Jorgensen,et al.  Comparison of simple potential functions for simulating liquid water , 1983 .

[17]  Daniel Zwillinger,et al.  CRC Standard Probability and Statistics Tables and Formulae, Student Edition , 1999 .

[18]  Alexander A. Morgan,et al.  Discovery and Preclinical Validation of Drug Indications Using Compendia of Public Gene Expression Data , 2011, Science Translational Medicine.

[19]  Goutam Paul,et al.  A machine learning approach towards the prediction of protein–ligand binding affinity based on fundamental molecular properties , 2018, RSC advances.

[20]  Julio Saez-Rodriguez,et al.  Network based elucidation of drug response: from modulators to targets , 2013, BMC Systems Biology.

[21]  Yun Xie,et al.  Identification of drug-target interaction from interactome network with 'guilt-by-association' principle and topology features , 2016, Bioinform..

[22]  Marta M. Stepniewska-Dziubinska,et al.  Development and evaluation of a deep learning model for protein-ligand binding affinity prediction , 2017, 1712.07042.

[23]  D. di Bernardo,et al.  Identification of small molecules enhancing autophagic function from drug network analysis. , 2010, Autophagy.

[24]  Andrei N. Lupas,et al.  CLANS: a Java application for visualizing protein families based on pairwise similarity , 2004, Bioinform..

[25]  S. Venkatesh,et al.  GraphDTA: prediction of drug–target binding affinity using graph convolutional networks , 2019 .

[26]  P. Sanseau,et al.  Computational Drug Repositioning: From Data to Therapeutics , 2013, Clinical pharmacology and therapeutics.

[27]  Graham Richards,et al.  Intermolecular forces , 1978, Nature.

[28]  Truyen Tran,et al.  Dynamic Language Binding in Relational Visual Reasoning , 2020, IJCAI.

[29]  Jinbo Xu,et al.  Analysis of deep learning methods for blind protein contact prediction in CASP12 , 2018, Proteins.

[30]  Elif Ozkirimli,et al.  WideDTA: prediction of drug-target binding affinity , 2019, ArXiv.

[31]  Abien Fred Agarap.  Deep Learning using Rectified Linear Units (ReLU) , 2018, ArXiv.

[32]  Juho Rousu,et al.  Learning with multiple pairwise kernels for drug bioactivity prediction , 2018, Bioinform..

[33]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[34]  Demis Hassabis,et al.  Improved protein structure prediction using potentials from deep learning , 2020, Nature.

[35]  A. Mantel‐Teeuwisse,et al.  Drug repositioning and repurposing: terminology and definitions in literature. , 2015, Drug discovery today.

[36]  Michael K. Gilson,et al.  BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology , 2015, Nucleic Acids Res..

[37]  Jacob Benesty,et al.  Noise Reduction in Speech Processing , 2009 .

[38]  Yingli Tian,et al.  Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  The UniProt Consortium,et al.  UniProt: a worldwide hub of protein knowledge , 2018, Nucleic Acids Res..

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

[41]  Russ B. Altman,et al.  Graph Convolutional Neural Networks for Predicting Drug-Target Interactions , 2018, bioRxiv.

[42]  Evan Bolton,et al.  PubChem 2019 update: improved access to chemical data , 2018, Nucleic Acids Res..

[43]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Bing Wang,et al.  The role of quantum mechanics in structure-based drug design. , 2007, Drug discovery today.

[45]  S. Teague.  Implications of protein flexibility for drug discovery , 2003, Nature Reviews Drug Discovery.

[46]  Michal Magid-Slav,et al.  Identification of Common Biological Pathways and Drug Targets Across Multiple Respiratory Viruses Based on Human Host Gene Expression Analysis , 2012, PloS one.

[47]  Vladimir B. Bajic,et al.  Comparison Study of Computational Prediction Tools for Drug-Target Binding Affinities , 2019, Front. Chem..

[48]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[49]  J. Bajorath,et al.  Docking and scoring in virtual screening for drug discovery: methods and applications , 2004, Nature Reviews Drug Discovery.

[50]  Yongjian Li,et al.  Predicting drug–protein interaction using quasi-visual question answering system , 2019, Nature Machine Intelligence.

[51]  F. Iorio,et al.  Transcriptional data: a new gateway to drug repositioning? , 2013, Drug discovery today.

[52]  Catherine Etchebest,et al.  Determining membrane protein structures: still a challenge! , 2007, Trends in biochemical sciences.

[53]  Zhen Li,et al.  Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model , 2016, bioRxiv.

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

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

[56]  Jie Li,et al.  Review of Drug Repositioning Approaches and Resources , 2018, International journal of biological sciences.

[57]  Juho Rousu,et al.  Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors , 2017, PLoS Comput. Biol..

[58]  Xiaofeng Wang,et al.  Drug–target affinity prediction using graph neural network and contact maps , 2020, RSC advances.

[59]  Vijay S. Pande,et al.  Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity , 2017, ArXiv.

[60]  M. Gonen,et al.  Concordance probability and discriminatory power in proportional hazards regression , 2005 .