Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces

Xia, Zheng; Wu, Ling; Zhou, Xiaobo; Wong, Stephen T.C.

doi:10.1186/1752-0509-4-s2-s6

Cited by 322 publications

(246 citation statements)

References 15 publications

Supporting

Mentioning

246

Contrasting

Order By: Relevance

“…The proposed BRDTI method was compared with four state of the art approaches: BLM-NII [25], WNN-GIP [28], NetLapRLS [26] and CMF [30]. Grid-search was used to tune methods' hyperparameters, details can be found in supplementary materials.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

“…[25], [32]), prediction of each DTI is based on the neighborhood of involved drug and target. Xia et al [26] proposed a semi-supervised approach based on Laplacian regularized least square method (RLS) with kernels derived from known DTIs (NetLapRLS). Van Laarhoven et al [27] proposed to use regularized least squares with Gaussian interaction profile kernel (GIP).…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning methods in general leverage features based on the structure of drugs and targets (e.g., [9,[19][20][21]), drugs' side-effects [22], and the knowledge of already confirmed DTIs [23][24][25][26][27][28][29][30][31][32]. In particular, in case of Bipartite Local Models (BLM) [23] and its extensions (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Evaluation and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…In order to demonstrate the performance of our method, we adopt the 10-fold cross validation and external validation. The 10-fold validation was widely used in prediction of DTIs [29,48,49] and other interaction prediction in bioinformatics. The main experiment process is that the whole dataset is randomly divided into 10 groups; each group alternates as a testing set, and the rest of the 9 groups alternate as the training set, and this process is repeated 10 times.…”

Section: Benchmark Evaluation and Evaluation Indicesmentioning

confidence: 99%

SDTRLS: Predicting Drug-Target Interactions for Complex Diseases Based on Chemical Substructures

Cheng

Lan

et al. 2017

Complexity

View full text Add to dashboard Cite

It is well known that drug discovery for complex diseases via biological experiments is a time-consuming and expensive process. Alternatively, the computational methods provide a low-cost and high-efficiency way for predicting drug-target interactions (DTIs) from biomolecular networks. However, the current computational methods mainly deal with DTI predictions of known drugs; there are few methods for large-scale prediction of failed drugs and new chemical entities that are currently stored in some biological databases may be effective for other diseases compared with their originally targeted diseases. In this study, we propose a method (called SDTRLS) which predicts DTIs through RLS-Kron model with chemical substructure similarity fusion and Gaussian Interaction Profile (GIP) kernels. SDTRLS can be an effective predictor for targets of old drugs, failed drugs, and new chemical entities from large-scale biomolecular network databases. Our computational experiments show that SDTRLS outperforms the state-of-the-art SDTNBI method; specifically, in the G protein-coupled receptors (GPCRs) external validation, the maximum and the average AUC values of SDTRLS are 0.842 and 0.826, respectively, which are superior to those of SDTNBI, which are 0.797 and 0.766, respectively. This study provides an important basis for new drug development and drug repositioning based on biomolecular networks.

show abstract

“…Positive-definite (PD) matrices are widely used in many applications, including recommender systems [12,20] and analysis of biological data [6,15,27] In these applications, the PD matrices are capturing the similarity between objects of interest (e.g., users, items, observations or features) and they are usually the result of the multiplication of a data matrix with its transpose.…”

Section: Introductionmentioning

confidence: 99%

Active Positive-Definite Matrix Completion

Mavroforakis

Erdős

Crovella

et al. 2017

Proceedings of the 2017 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

In many applications, e.g., recommender systems and biological data analysis, the datasets of interest are positive definite (PD) matrices. Such matrices are usually similarity matrices, obtained by the multiplication of a matrix of preferences or observations with its transpose. Oftentimes, such real-world matrices are missing many entries and a fundamental data-analysis task, known by the term PD-matrix completion, is the inference of these missing entries. In this paper, we introduce the active version of PD-matrix completion, in which we assume access to an oracle that, at a given cost, returns the value of an unobserved entry of the PD matrix. In this setting, we consider the following question: "given a fixed budget, which entries should we query so that the completion of the new matrix is much more indicative of the underlying data?". The main contribution of the paper is the formalization of the above question as the ActivePDCompletion problem and the design of novel and effective algorithms for solving it in practice.

show abstract

Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces

Cited by 322 publications

References 15 publications

Drug-target interaction prediction: A Bayesian ranking approach

Drug-target interaction prediction: A Bayesian ranking approach

SDTRLS: Predicting Drug-Target Interactions for Complex Diseases Based on Chemical Substructures

Active Positive-Definite Matrix Completion

Contact Info

Product

Resources

About