Deep learning with feature embedding for compound-protein interaction prediction

By Fangping Wan, Jianyang Zeng. 2016

77 citations recorded by the source corpus.

Accurately 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.

Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology

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 Molecular Biology

In Pharmacology

Citations in the corpus

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition (2018, positive): “10 In parallel, natural language processing (NLP) techniques were adopted to learn from classical features, like molecular FPs, 11 SMILES strings, 12 and graph representations of compounds.”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “Performance comparison of CPI is shown in Fig.”
Graph convolutional networks for computational drug development and discovery (2019, methodology): “Several commonly used deep architectures have been employed in drug-related works [4–7] and achieved substantial improvements compared to traditional machine learning methods.”
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks (2018, methodology): “Wan et al. exploited feature embedding algorithm such as latent semantic algorithm (Deerwester et al. , 1990) and word2vec (Mikolov et al. , 2013) to automatically learn low-dimensional feature vectors of compounds and proteins from the corresponding large-scale unlabeled data (Wan and Zeng, 2016).”
Compound‐protein interaction prediction with end‐to‐end learning of neural networks for graphs and sequences (2018, methodology): “Most datasets used to evaluate machine learning-based CPI prediction methods (Hamanaka et al., 2017; Tian et al., 2016; Wan and Zeng, 2016) include positive samples (i.”
DeepDTA: deep drug–target binding affinity prediction (2018, background): “Recently, DTI studies that rely on databases with binding affinity information have been providing more realistic binary datasets created with a chosen binding affinity threshold value (Wan and Zeng, 2016).”
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions (2018, background): “, compound-protein interaction prediction, drug discovery with one-shot learning) [11, 12, 13, 14, 15, 16].”
Artificial intelligence in drug discovery and development (2020, unknown): “…drug discovery by predicting the 3D protein structure because the design is in accordance with the chemical environment of the target protein site, thus helping to predict the effect of a compound on the target along with safety considerations before their synthesis or production [55].”