DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks

By Mostafa Karimi, Di Wu, Zhangyang Wang, Yang Shen. 2018

441 citations recorded by the source corpus.

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-annotatedprotein 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 IC50 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 Contact yshen@tamu.edu Supplementary information Supplementary data are available at http://shen-lab.github.io/deep-affinity-bioinf18-supp-rev.pdf.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, methodology): “However, some methods (Karimi et al., 2019; Gao et al., 2018) have found that using the protein sequence and the drug SMILES string already provide competitive predictions for binding afﬁnity without the need for 3D structural data.”
Ensemble deep learning in bioinformatics (2020, methodology): “For example, Karimi et al. proposed an ensemble model that comprised various network modules for compound–protein affinity prediction 84 .”
Artificial intelligence in drug discovery and development (2020, unknown): “47 Karimi, M. et al. (2019) DeepAffinity: interpretable deep learning of compound–”
ATOM3D: Tasks On Molecules in Three Dimensions (2020, methodology): “When possible, for tasks in Table 7, we choose 3D methods that fulfill the following criteria: (1) they represent the current state-of-the-art for that task, or as close as possible, and (2) they either have 10https://github.com/hkmztrk/DeepDTA 11https://github.com/Shen-Lab/DeepAffinity a publicly a”