FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction
- 21 December 2021
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 23 (1)
Abstract
The prediction of drug-target affinity (DTA) plays an increasingly important role in drug discovery. Nowadays, lots of prediction methods focus on feature encoding of drugs and proteins, but ignore the importance of feature aggregation. However, the increasingly complex encoder networks lead to the loss of implicit information and excessive model size. To this end, we propose a deep-learning-based approach namely FusionDTA. For the loss of implicit information, a novel muti-head linear attention mechanism was utilized to replace the rough pooling method. This allows FusionDTA aggregates global information based on attention weights, instead of selecting the largest one as max-pooling does. To solve the redundancy issue of parameters, we applied knowledge distillation in FusionDTA by transfering learnable information from teacher model to student. Results show that FusionDTA performs better than existing models for the test domain on all evaluation metrics. We obtained concordance index (CI) index of 0.913 and 0.906 in Davis and KIBA dataset respectively, compared with 0.893 and 0.891 of previous state-of-art model. Under the cold-start constrain, our model proved to be more robust and more effective with unseen inputs than baseline methods. In addition, the knowledge distillation did save half of the parameters of the model, with only 0.006 reduction in CI index. Even FusionDTA with half the parameters could easily exceed the baseline on all metrics. In general, our model has superior performance and improves the effect of drug–target interaction (DTI) prediction. The visualization of DTI can effectively help predict the binding region of proteins during structure-based drug design.Keywords
Funding Information
- National Natural Science Foundation of China (62176272)
- Guangzhou science and technology fund (201803010072)
- Science, Technology and Innovation Commission of Shenzhen Municipality (JCYL 20170818165305521)
- China Medical University Hospital (DMR-111-102, DMR-111-143, DMR-111-123)
This publication has 25 references indexed in Scilit:
- The Current Status of Drug Discovery and Development as Originated in United States Academia: The Influence of Industrial and Academic Collaboration on Drug Discovery and DevelopmentClinical and Translational Science, 2018
- Deep-Learning-Based Drug–Target Interaction PredictionJournal of Proteome Research, 2017
- Continuous Distributed Representation of Biological Sequences for Deep Proteomics and GenomicsPLOS ONE, 2015
- Toward more realistic drug-target interaction predictionsBriefings in Bioinformatics, 2014
- Making Sense of Large-Scale Kinase Inhibitor Bioactivity Data Sets: A Comparative and Integrative AnalysisJournal of Chemical Information and Modeling, 2014
- Comprehensive analysis of kinase inhibitor selectivityNature Biotechnology, 2011
- Drug–protein binding: a critical review of analytical toolsAnalytical and Bioanalytical Chemistry, 2010
- Model compression2006
- Concordance probability and discriminatory power in proportional hazards regressionBiometrika, 2005
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988