Supervised prediction of drug–target interactions using bipartite local models

By Kevin Bleakley, Yoshihiro Yamanishi. Bioinform., 2009

610 citations recorded by the source corpus.

Motivation: In silico prediction of drug–target interactions from heterogeneous biological data is critical in the search for drugs for known diseases. This problem is currently being attacked from many different points of view, a strong indication of its current importance. Precisely, being able to predict new drug–target interactions with both high precision and accuracy is the holy grail, a fundamental requirement for in silico methods to be useful in a biological setting. This, however, remains extremely challenging due to, amongst other things, the rarity of known drug–target interactions. Results: We propose a novel supervised inference method to predict unknown drug–target interactions, represented as a bipartite graph. We use this method, known as bipartite local models to first predict target proteins of a given drug, then to predict drugs targeting a given protein. This gives two independent predictions for each putative drug–target interaction, which we show can be combined to give a definitive prediction for each interaction. We demonstrate the excellent performance of the proposed method in the prediction of four classes of drug–target interaction networks involving enzymes, ion channels, G protein-coupled receptors (GPCRs) and nuclear receptors in human. This enables us to suggest a number of new potential drug–target interactions. Availability: An implementation of the proposed algorithm is available upon request from the authors. Datasets and all prediction results are available at http://cbio.ensmp.fr/~yyamanishi/bipartitelocal/. Contact: kevbleakley@gmail.com Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Computational Theory and Mathematics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/71cfcc22ae3cab2ca12e26ec4234a857c7fc9bfa

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

Citations in the corpus

Predicting drug–protein interaction using quasi-visual question answering system (2019, methodology): “For example, [Bleakley and Yamanishi, 2009] proposed the bipartite local model by training local SVM classifiers from chemical structure similarity and protein sequence similarity.”
Deep mining heterogeneous networks of biomedical linked data to predict novel drug‐target associations (2017, methodology): “, 2010), genomic sequence (Bleakley and Yamanishi, 2009; Jacob and Vert, 2008; Yamanishi et al., 2008) may all be used for the similarity measure.”
SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines (2017, methodology): “One of the simplest ways of using the similarities is a Nearest Neighbor classifier [28], which predicts new interactions from the weighted (by the similarity) sum of the interaction profiles of the most similar drugs/targets.”
Similarity-based machine learning methods for predicting drug-target interactions: a brief review (2014, methodology): “We used exactly the same data as those in [27].”
Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework (2010, methodology): “A straightforward statistical approach is to use binary classification methods where they take compound–protein pairs as an input for machine learning classifiers such as neural network and support vector machine (SVM) (Bleakley and Yamanishi, 2009; Bock and Gough, 2005; Erhan et al., 2006; Faulon e”
Molecular Systems Biology Peer Review Process File Indi: a Computational Framework for Inferring Drug Interactions and Their Associated Recommendations Transaction Report (neutral): “Unlike the recommendation algorithm, known CRDs may have more than one CYP causing them, thus we normalized the frequency by the maximal CYP occurring and retained all seven features (not necessarily summing to one).”
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions (2018, background): “Recently, the machine learning based methods [6, 7, 5], which fully exploit the latent correlations among the related features of drugs and targets have become a highly promising strategy for DTI prediction.”
DeepDTA: deep drug–target binding affinity prediction (2018, methodology): “Until recently, DTI prediction was approached as a binary classification problem (Bleakley and Yamanishi, 2009; Cao et al., 2014, 2012; Cobanoglu et al., 2013; Gönen, 2012; Öztürk et al., 2016; Yamanishi et al., 2008; van Laarhoven et al., 2011), neglecting an important piece of information about pr”
Structure and dynamics of molecular networks: A novel paradigm of drug discovery: A comprehensive review (2012, background): “…the other projection of drug–target networks, nodes are the drug targets, which are connected, if they both bind the same drug (Keiser et al., 2007, 2009; Ma'ayan et al., 2007; Yildirim et al., 2007; Hert et al., 2008; Yamanishi et al., 2008; Bleakley & Yamanishi, 2009; van Laarhoven et al., 2011).”
DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences (2018, result): “In addition to substantially reducing the computational complexity, this model exhibited higher performance than the previous model [4].”