Boosting compound-protein interaction prediction by deep learning

In recent years, numerous structure-free deep-learning-based neural networks have emerged aiming to predict compound-protein interactions for drug virtual screening. Although these methods show high prediction accuracy in their own tests, we find that they are not generalizable to predict interactions between unknown proteins and unknown small molecules, thus hindering the utilization of state-of-the-art deep learning techniques in the field of virtual screening. In our work, we develop a compound-protein interaction predictor, YueL, which can predict compound-protein interactions with high generalizability. Upon comprehensive tests on various data sets, we find that YueL has the ability to predict interactions between unknown compounds and unknown proteins. We anticipate our work can motivate broad application of deep learning techniques for drug virtual screening to supersede the traditional docking and cheminformatics methods.

Download Full-text

Deep learning with feature embedding for compound-protein interaction prediction

10.1101/086033 ◽

2016 ◽

Cited By ~ 16

Author(s):

Fangping Wan ◽

Jianyang (Michael) Zeng

Keyword(s):

Deep Learning ◽

Protein Interaction ◽

Protein Interactions ◽

Large Scale ◽

Computational Models ◽

Drug Repositioning ◽

Representation Learning ◽

Small Scale ◽

Interaction Prediction ◽

Protein Interaction Prediction

AbstractAccurately identifying compound-protein interactions in silico can deepen our understanding of the mechanisms of drug action and significantly facilitate the drug discovery and development process. Traditional similarity-based computational models for compound-protein interaction prediction rarely exploit the latent features from current available large-scale unlabelled compound and protein data, and often limit their usage on relatively small-scale datasets. We propose a new scheme that combines feature embedding (a technique of representation learning) with deep learning for predicting compound-protein interactions. Our method automatically learns the low-dimensional implicit but expressive features for compounds and proteins from the massive amount of unlabelled data. Combining effective feature embedding with powerful deep learning techniques, our method provides a general computational pipeline for accurate compound-protein interaction prediction, even when the interaction knowledge of compounds and proteins is entirely unknown. Evaluations on current large-scale databases of the measured compound-protein affinities, such as ChEMBL and BindingDB, as well as known drug-target interactions from DrugBank have demonstrated the superior prediction performance of our method, and suggested that it can offer a useful tool for drug development and drug repositioning.

Download Full-text

Recent methodology progress of deep learning for RNA–protein interaction prediction

Wiley Interdisciplinary Reviews - RNA ◽

10.1002/wrna.1544 ◽

2019 ◽

Vol 10 (6) ◽

Cited By ~ 11

Author(s):

Xiaoyong Pan ◽

Yang Yang ◽

Chun‐Qiu Xia ◽

Aashiq H. Mirza ◽

Hong‐Bin Shen

Keyword(s):

Deep Learning ◽

Protein Interaction ◽

Interaction Prediction ◽

Protein Interaction Prediction

Download Full-text

A deep-learning framework for multi-level peptide–protein interaction prediction

Nature Communications ◽

10.1038/s41467-021-25772-4 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Yipin Lei ◽

Shuya Li ◽

Ziyi Liu ◽

Fangping Wan ◽

Tingzhong Tian ◽

...

Keyword(s):

Deep Learning ◽

Protein Interaction ◽

Protein Interactions ◽

Comprehensive Evaluation ◽

Interaction Prediction ◽

Learning Framework ◽

Binding Residue ◽

Protein Interaction Prediction ◽

Binding Residues ◽

Multi Level

AbstractPeptide-protein interactions are involved in various fundamental cellular functions and their identification is crucial for designing efficacious peptide therapeutics. Recently, a number of computational methods have been developed to predict peptide-protein interactions. However, most of the existing prediction approaches heavily depend on high-resolution structure data. Here, we present a deep learning framework for multi-level peptide-protein interaction prediction, called CAMP, including binary peptide-protein interaction prediction and corresponding peptide binding residue identification. Comprehensive evaluation demonstrated that CAMP can successfully capture the binary interactions between peptides and proteins and identify the binding residues along the peptides involved in the interactions. In addition, CAMP outperformed other state-of-the-art methods on binary peptide-protein interaction prediction. CAMP can serve as a useful tool in peptide-protein interaction prediction and identification of important binding residues in the peptides, which can thus facilitate the peptide drug discovery process.

Download Full-text