Feature-derived graph regularized matrix factorization for predicting drug side effects

Zhang, Wen; Liu, Xinrui; Chen, Yanlin; Wu, Wenjian; Wang, Wei; Li, Xiaohong

doi:10.1016/j.neucom.2018.01.085

Cited by 74 publications

(58 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental setting Following previous approaches [6,8,10,11,12], we frame the side effect prediction problem as a binary classification problem. We applied ten-fold cross-validation, while [29] 0.827 ± 0.0031 0.071 ± 0.0028 0.010±0.0014 LP [8] 0.888 ± 0.0021 0.126 ± 0.0033 0.018 ± 0.0032 IMCZeros 0.892 ± 0.0045 0.194 ± 0.0100 317.149 ± 16.09 FGRMF [11] 0.911 ± 0.0029 0.237 ± 0.0059 209.27 ± 9.43 PPNs [6] 0.923 ± 0.0020 0.208 ± 0.0056 186 ± 5.91 MF [10] 0.929 ± 0.0019 0.274 ± 0.0071 31.12 ± 4.73 FGRMF-DDI [11] 0.931 ± 0.0020 0.285 ± 0.0075 30 optimizing the hyperparameters using an inner loop of five-fold cross-validation within each of the ten folds (nested cross-validation for model selection [28]). The performance of the classifier is measured using the area under the receiver operating curve (AUROC) and the area under the precision-recall curve (AUPRC).…”

Section: Resultsmentioning

confidence: 99%

“…We report the mean values of the ten folds for each metric (AUROC and AUPRC). We compared the performance of our method against Matrix factorization (MF) [10], Inductive Matrix Completion (IMC) [12], Predictive PharmacoSafety Networks (PPNs) [6], Label propagation (LP) [8], Feature-derived graph regularized matrix factorization (FGRMF) [11], and side effect popularity (TopPop) [29]. While every algorithm used the drug side effect matrix X, only IMC, PPNs, LP and FGRMF could also make use of the drug side information graphs (see section S3 for a details for each model).…”

Section: Resultsmentioning

confidence: 99%

“…We prove that our multiplicative learning algorithm, which does not require to set a learning rate nor applying projection functions to guaranteed non-negative constraints, convergences to a globally optimal solution point with a first-order convergence rate. And unlike non-convex matrix decomposition models proposed previously for the side effect prediction problem [10,11,12], these theoretical guarantees of convergence imply the reproducibility of the solutions under arbitrary initializations: a desirable property for biological interpretation.…”

Section: Contributionsmentioning

confidence: 99%

“…Galeano and Paccanaro [10] used this type of model to predict missing associations in a binary matrix of drugs side effect associations. A similar approach was used by Zhang et al [11], that also included smoothness constraints derived from drug side information. Li et al [12] proposed an inductive matrix completion approach that integrates side information using kernel matrices of drugs and side effects.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Geometric Sparse Matrix Completion Model for Predicting Drug Side effects

Galeano

Paccanaro

2019

Preprint

View full text Add to dashboard Cite

Pair-input associations for drug-side effects are obtained through expensive placebocontrolled experiments in human clinical trials. An important challenge in computational pharmacology is to predict missing associations given a few entries in the drug-side effect matrix, as these predictions can be used to direct further clinical trials. Here we introduce the Geometric Sparse Matrix Completion (GSMC) model for predicting drug side effects. Our high-rank matrix completion model learns non-negative sparse matrices of coefficients for drugs and side effects by imposing smoothness priors that exploit a set of pharmacological side information graphs, including information about drug chemical structures, drug interactions, molecular targets, and disease indications. Our learning algorithm is based on the diagonally rescaled gradient descend principle of non-negative matrix factorization. We prove that it converges to a globally optimal solution with a first-order rate of convergence. Experiments on large-scale side effect data from human clinical trials show that our method achieves better prediction performance than six state-of-the-art methods for side effect prediction while offering biological interpretability and favouring explainable predictions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Geometric Sparse Matrix Completion Model for Predicting Drug Side effects

Galeano

Paccanaro

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…But, the standard Matrix Factorization and Deep Matrix Factorization algorithms cannot accommodate such metadata. There are a couple of recent works which do use standard similarities for drugs and targets with matrix factorization [24,50] and matrix completion [23] frameworks. It is imperative that DMF should be able to take into account the standard similarity information as well as more types and combinations of similarities.…”

Section: Proposed Formulation: Multi-graph Regularized Deep Matrix Famentioning

confidence: 99%

Drug-Target Interaction prediction using Multi-Graph Regularized Deep Matrix Factorization

Mongia

Majumdar

2019

Preprint

View full text Add to dashboard Cite

Drug discovery is an important field in the pharmaceutical industry with one of its crucial chemogenomic process being drug-target interaction prediction. This interaction determination is expensive and laborious, which brings the need for alternative computational approaches which could help reduce the search space for biological experiments. This paper proposes a novel framework for drug-target interaction (DTI) prediction: Multi-Graph Regularized Deep Matrix Factorization (MGRDMF). The proposed method, motivated by the success of deep learning, finds a low-rank solution which is structured by the proximities of drugs and targets (drug similarities and target similarities) using deep matrix factorization. Deep matrix factorization is capable of learning deep representations of drugs and targets for interaction prediction. It is an established fact that drug and target similarities incorporation preserves the local geometries of the data in original space and learns the data manifold better. However, there is no literature on which the type of similarity matrix (apart from the standard biological chemical structure similarity for drugs and genomic sequence similarity for targets) could best help in DTI prediction. Therefore, we attempt to take into account various types of similarities between drugs/targets as multiple graph Laplacian regularization terms which take into account the neighborhood information between drugs/targets. This is the first work which has leveraged multiple similarity/neighborhood information into the deep learning framework for drug-target interaction prediction. The cross-validation results on four benchmark data sets validate the efficacy of the proposed algorithm by outperforming shallow state-of-the-art computational methods on the grounds of AUPR and AUC.September 18, 2019 1/17 interaction not only assists drug discovery but also affects other fields such as drug repositioning, drug resistance and side-effect prediction [10]. As an example, Drug repositioning [11,12] (using an existing drug for new indications) can grant polypharmacology (multi-target effect) to a drug. Gleevec (imatinib mesylate) is one of the many such examples which was successfully repositioned. Earlier, it was known to interact only with the Bcr-Abl fusion gene which is indicative of leukemia. However, later discoveries showing that it also interacts with PDGF and KIT, repositioned it for the treatment of gastrointestinal stromal tumors [13,14]. The methods available for prediction of DTI can be divided into the following three broad categories: Ligand-based approaches, Docking based approaches, and Chemogenomic approaches. Ligand-based approaches predict interactions by deploying the similarity between the ligands of target proteins [15]. The idea is that molecules with similar structure/property would bind similar proteins [16]. But, the reliability of results might get compromised due to limited information about known ligands per protein. Docking-based approaches use the three-dimensional structure of both ...

show abstract

Prediction of Thermophilic Proteins Using Voting Algorithm

Zhu

Zou

2019

Bioinformatics and Biomedical Engineering

View full text Add to dashboard Cite

Feature-derived graph regularized matrix factorization for predicting drug side effects

Cited by 74 publications

References 34 publications

The Geometric Sparse Matrix Completion Model for Predicting Drug Side effects

The Geometric Sparse Matrix Completion Model for Predicting Drug Side effects

Drug-Target Interaction prediction using Multi-Graph Regularized Deep Matrix Factorization

Prediction of Thermophilic Proteins Using Voting Algorithm

Contact Info

Product

Resources

About