Drug side effect prediction through linear neighborhoods and multiple data source integration

Zhang, Wen; Chen, Yanlin; Tu, Shikui; Lu, Feng; Qu, Qianlong

doi:10.1109/bibm.2016.7822555

Cited by 57 publications

(64 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since Equation (6) maps drugs and diseases into a lowdimensional space, a natural idea occurs that the lowdimensional representations should preserve the underlying interconnection information of drugs and diseases. Studies on manifold learning (Belkin et al, 2006;Ma and Fu, 2012;Zhang et al, 2018a), spectral graph theory (Chung, 1997;Rana et al, 2015) and their applications (Zhang et al, 2016a(Zhang et al, , 2017a(Zhang et al, ,b,c, 2018bRuan et al, 2017) have shown that the learning performance can be signally enhanced, if the local topological invariant properties are preserved. Cai et al (2011) proposed Laplacian regularizations to achieve this goal.…”

Section: Objective Function Of Cmfmtlmentioning

confidence: 99%

“…Wang et al (2014) designed a computational framework based on a three-layer heterogeneous network model (TL-HGBI). Zhang et al proposed the multi-label learning method (Zhang et al, 2015), and the linear neighborhood similarity-based method (Zhang et al, 2016a(Zhang et al, , 2017c for side effect prediction. Moghadam et al (2016) adopted the kernel fusion technique to combine different drug features and disease features, and then built SVM models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Drug-Disease Associations via Multi-Task Learning Based on Collective Matrix Factorization

Huang

Yang

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Identifying drug-disease associations is integral to drug development. Computationally prioritizing candidate drug-disease associations has attracted growing attention due to its contribution to reducing the cost of laboratory screening. Drug-disease associations involve different association types, such as drug indications and drug side effects. However, the existing models for predicting drug-disease associations merely concentrate on independent tasks: recommending novel indications to benefit drug repositioning, predicting potential side effects to prevent drug-induced risk, or only determining the existence of drug-disease association. They ignore crucial prior knowledge of the correlations between different association types. Since the Comparative Toxicogenomics Database (CTD) annotates the drug-disease associations as therapeutic or marker/mechanism, we consider predicting the two types of association. To this end, we propose a collective matrix factorization-based multi-task learning method (CMFMTL) in this paper. CMFMTL handles the problem as multi-task learning where each task is to predict one type of association, and two tasks complement and improve each other by capturing the relatedness between them. First, drug-disease associations are represented as a bipartite network with two types of links representing therapeutic effects and non-therapeutic effects. Then, CMFMTL, respectively, approximates the association matrix regarding each link type by matrix tri-factorization, and shares the low-dimensional latent representations for drugs and diseases in the two related tasks for the goal of collective learning. Finally, CMFMTL puts the two tasks into a unified framework and an efficient algorithm is developed to solve our proposed optimization problem. In the computational experiments, CMFMTL outperforms several state-of-the-art methods both in the two tasks. Moreover, case studies show that CMFMTL helps to find out novel drug-disease associations that are not included in CTD, and simultaneously predicts their association types.

show abstract

Section: Objective Function Of Cmfmtlmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting Drug-Disease Associations via Multi-Task Learning Based on Collective Matrix Factorization

Huang

Yang

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…However, such experimental predictions are expensive, timeconsuming, and tedious. Recently, several computational methods have been proposed to tackle the side-effect prediction problem based on drug profiles [2,[5][6][7][8][9][10][11][12][13][14][15]. These methods can be categorized into target protein-based methods and chemical structure-based methods.…”

Section: Introductionmentioning

confidence: 99%

Inverse similarity and reliable negative samples for drug side-effect prediction

et al. 2019

View full text Add to dashboard Cite

Background: In silico prediction of potential drug side-effects is of crucial importance for drug development, since wet experimental identification of drug side-effects is expensive and time-consuming. Existing computational methods mainly focus on leveraging validated drug side-effect relations for the prediction. The performance is severely impeded by the lack of reliable negative training data. Thus, a method to select reliable negative samples becomes vital in the performance improvement. Methods: Most of the existing computational prediction methods are essentially based on the assumption that similar drugs are inclined to share the same side-effects, which has given rise to remarkable performance. It is also rational to assume an inverse proposition that dissimilar drugs are less likely to share the same side-effects. Based on this inverse similarity hypothesis, we proposed a novel method to select highly-reliable negative samples for side-effect prediction. The first step of our method is to build a drug similarity integration framework to measure the similarity between drugs from different perspectives. This step integrates drug chemical structures, drug target proteins, drug substituents, and drug therapeutic information as features into a unified framework. Then, a similarity score between each candidate negative drug and validated positive drugs is calculated using the similarity integration framework. Those candidate negative drugs with lower similarity scores are preferentially selected as negative samples. Finally, both the validated positive drugs and the selected highly-reliable negative samples are used for predictions. Results: The performance of the proposed method was evaluated on simulative side-effect prediction of 917 DrugBank drugs, comparing with four machine-learning algorithms. Extensive experiments show that the drug similarity integration framework has superior capability in capturing drug features, achieving much better performance than those based on a single type of drug property. Besides, the four machine-learning algorithms achieved significant improvement in macro-averaging F1-score (e.g., SVM from 0.655 to 0.898), macro-averaging precision (e.g., RBF from 0.592 to 0.828) and macro-averaging recall (e.g., KNN from 0.651 to 0.772) complimentarily attributed to the highly-reliable negative samples selected by the proposed method. Conclusions:The results suggest that the inverse similarity hypothesis and the integration of different drug properties are valuable for side-effect prediction. The selection of highly-reliable negative samples can also make significant contributions to the performance improvement.

show abstract

“…However, their method depends heavily on the availability of gene expression data. Instead of using a single drug feature (e.g., drug chemical structure), researchers tried to predict drug sideeffects by integration of different types of drug features [Yamanishi, Pauwels and Kotera (2012); Zhang, Chen, Tu et al (2016)]. Yamanishi et al [Yamanishi, Pauwels and Kotera (2012)] integrated drug chemical structures and drug target proteins in a unified framework for side-effect prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Extensive experiments demonstrated that the prediction performance was significantly improved owing to the integration. Analogously, impacts of different combination of drug features were investigated in Zhang et al [Zhang, Chen, Tu et al (2016)]. Compared with methods based on a single drug feature, all feature integration methods produced better performances.…”

Section: Introductionmentioning

confidence: 99%

Drug Side-Effect Prediction Using Heterogeneous Features and Bipartite Local Models

Zheng¹,

Zhao²,

Sun³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Drug side-effects impose massive costs on society, leading to almost one-third drug failure in the drug discovery process. Therefore, early identification of potential side-effects becomes vital to avoid risks and reduce costs. Existing computational methods employ few drug features and predict drug side-effects from either drug side or side-effect side separately. In this work, we explore to predict drug side-effects by combining heterogeneous drug features and employing the bipartite local models (BLMs) which fuse predictions from both the drug side and side-effect side. Specifically, we integrate drug chemical structures, drug interacted proteins and drug associated genes into a unified framework to measure the comprehensive similarity between drugs first. Then, high-quality and balanced training samples are selected for individual drugs and individual side-effects using the designed balanced sample selection framework, based on drug comprehensive similarities and side-effect cosine similarities respectively. Trained with corresponding training samples, BLMs first predict drugs associated with a given side-effect, then predict side-effects for a given drug. This produces two independent predictions for each putative drug-side-effect association which are further combined to give a definitive prediction. The performance of the proposed method was evaluated on side-effect prediction for 901 drugs from DrugBank. Particularly, we performed 5-fold cross-validation experiments on the 742 characterized drugs and independent testing experiment on the 159 uncharacterized drugs. The simulative predictions show that the side-effect prediction performance is significantly improved owing to the integration of information from drug chemical, biological and genomic spaces, the proposed sample selection framework, and the implemented BLMs.

show abstract

Drug side effect prediction through linear neighborhoods and multiple data source integration

Cited by 57 publications

References 38 publications

Predicting Drug-Disease Associations via Multi-Task Learning Based on Collective Matrix Factorization

Predicting Drug-Disease Associations via Multi-Task Learning Based on Collective Matrix Factorization

Inverse similarity and reliable negative samples for drug side-effect prediction

Drug Side-Effect Prediction Using Heterogeneous Features and Bipartite Local Models

Contact Info

Product

Resources

About