DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
This work addresses the need for accurate and interpretable methods in drug discovery to quantify compound-protein interactions, representing an incremental advance by combining existing neural network types with novel representations and attention mechanisms.
The authors tackled the problem of predicting compound-protein affinity from sequences alone by developing DeepAffinity, a deep learning model that integrates recurrent and convolutional neural networks with attention mechanisms. The model achieved relative error in IC50 within 5-fold for test cases and 20-fold for protein classes not included in training, with performance improved by transfer learning for new classes with few labeled data.
Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy, and interpretability. Results: We present a seamless integration of domain knowledges and learning-based approaches. Under novel representations of structurally-annotated protein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding molecular representations and predicting affinities. Our representations and models outperform conventional options in achieving relative error in IC$_{50}$ within 5-fold for test cases and 20-fold for protein classes not included for training. Performances for new protein classes with few labeled data are further improved by transfer learning. Furthermore, separate and joint attention mechanisms are developed and embedded to our model to add to its interpretability, as illustrated in case studies for predicting and explaining selective drug-target interactions. Lastly, alternative representations using protein sequences or compound graphs and a unified RNN/GCNN-CNN model using graph CNN (GCNN) are also explored to reveal algorithmic challenges ahead. Availability: Data and source codes are available at https://github.com/Shen-Lab/DeepAffinity Supplementary Information: Supplementary data are available at http://shen-lab.github.io/deep-affinity-bioinf18-supp-rev.pdf