SuperTarget and Matador: resources for exploring drug-target relationships

Günther, Stefan; Kuhn, Michael; Dunkel, Mathias; Campillos, Mónica; Senger, Christian; Petsalaki, Evangelia; Ahmed, Jessica; Urdiales, Eduardo Garcia; Gewiess, Andreas; Jensen, Lars Juhl; Schneider, Reinhard; Skoblo, Roman; Russell, Robert B.; Bourne, Philip E.; Bork, Peer; Preißner, Robert

doi:10.1093/nar/gkm862

Cited by 540 publications

(416 citation statements)

References 17 publications

Supporting

Mentioning

415

Contrasting

Unclassified

Order By: Relevance

“…We focused on the best scoring gene for each drug, obtaining putative novel targets for 307 of the 315 drugs used in this study. To validate these predictions, we compared the predicted associations to those reported in two other sources of drug-target interactions that were not used in the learning process: the Therapeutic Target Database (TTD) (Zhu et al, 2010) and the Matador database (Gunther et al, 2008). TTD included only six interactions that were not part of our original data.…”

Section: Novel Predictionsmentioning

confidence: 99%

“…True drug-target interactions were retrieved from KEGG DRUG (Kanehisa et al, 2010), DrugBank (Wishart et al, 2008), and DCDB (Liu et al, 2010). An independent set of drug-target interactions was downloaded from Matador (Gunther et al, 2008) for validation purposes only. The classification features that we use are constructed from scores calculated on pairs combined of one of M drug-drug measures (five in our case) and one of N gene-gene similarity measures (three in our case), resulting in an MxN set of drug-gene measure features for each drug-target association (15 in our case).…”

Section: Combining Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Combining Drug and Gene Similarity Measures for Drug-Target Elucidation

Perlman¹,

Gottlieb

Atias

et al. 2011

Journal of Computational Biology

182

131

View full text Add to dashboard Cite

Understanding drugs and their modes of action is a fundamental challenge in systems medicine. Key to addressing this challenge is the elucidation of drug targets, an important step in the search for new drugs or novel targets for existing drugs. Incorporating multiple biological information sources is of essence for improving the accuracy of drug target prediction. In this article, we introduce a novel framework-Similarity-based Inference of drug-TARgets (SITAR)-for incorporating multiple drug-drug and gene-gene similarity measures for drug target prediction. The framework consists of a new scoring scheme for drug-gene associations based on a given pair of drug-drug and gene-gene similarity measures, combined with a logistic regression component that integrates the scores of multiple measures to yield the final association score. We apply our framework to predict targets for hundreds of drugs using both commonly used and novel drug-drug and gene-gene similarity measures and compare our results to existing state of the art methods, markedly outperforming them. We then employ our framework to make novel target predictions for hundreds of drugs; we validate these predictions via curated databases that were not used in the learning stage. Our framework provides an extensible platform for incorporating additional emerging similarity measures among drugs and genes. Supplementary Material is available at www.liebertonline .com/cmb.

show abstract

Section: Novel Predictionsmentioning

confidence: 99%

Section: Combining Measuresmentioning

confidence: 99%

Combining Drug and Gene Similarity Measures for Drug-Target Elucidation

Perlman¹,

Gottlieb

Atias

et al. 2011

Journal of Computational Biology

182

131

View full text Add to dashboard Cite

show abstract

“…Matador [40] databases and parsing the verified DTIs. This dataset is available in supplementary materials.…”

Section: Methodsmentioning

confidence: 99%

Drug-target interaction prediction: A Bayesian ranking approach

Peška

Búza

Koller

2017

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Background and Objective: In silico prediction of drug-target interactions (DTI) could provide valuable information and speed-up the process of drug repositioning -finding novel usage for existing drugs. In our work, we focus on machine learning algorithms supporting drug-centric repositioning approach, which aims to find novel usage for existing or abandoned drugs. We aim at proposing a per-drug ranking-based method, which reflects the needs of drug-centric repositioning research better than conventional drug-target prediction approaches. Methods: We propose Bayesian Ranking Prediction of Drug-Target Interactions(BRDTI). The method is based on Bayesian Personalized Ranking matrix factorization (BPR) which has been shown to be an excellent approach for various preference learning tasks, however, it has not been used for DTI prediction previously. In order to successfully deal with DTI challenges, we extended BPR by proposing: (i) the incorporation of target bias, (ii) a technique to handle new drugs and (iii) content alignment to take structural similarities of drugs and targets into account. Conclusions:Based on the evaluation, we can conclude that BRDTI is an appropriate choice for researchers looking for an in silico DTI prediction technique to be used in drugcentric repositioning scenarios. BRDTI Software and supplementary materials are available online at www.ksi.mff.cuni.cz/~peska/BRDTI.

show abstract

“…At no cost to academics engaged in mental health research, the same group provides experimental compound screening services with a variety of assays, including bioavailability predictions (e.g., CaCo2) and cardiotoxicity (e.g., HERG). SuperTarget (http://insilico.charite.de/supertarget/) provides various views of over 330,000 interactions involving about 6,000 targets and 200,000 compounds, along with annotated pathway diagrams and the ability to browse for targets categorically, such as by function and cellular location 80,81 .…”

Section: Other Small Molecule Databases Ofmentioning

confidence: 99%