Predicting drug-disease associations by using similarity constrained matrix factorization

Abstract

BackgroundDrug-disease associations provide important information for the drug discovery. Wet experiments that identify drug-disease associations are time-consuming and expensive. However, many drug-disease associations are still unobserved or unknown. The development of computational methods for predicting unobserved drug-disease associations is an important and urgent task.ResultsIn this paper, we proposed a similarity constrained matrix factorization method for the drug-disease association prediction (SCMFDD), which makes use of known drug-disease associations, drug features and disease semantic information. SCMFDD projects the drug-disease association relationship into two low-rank spaces, which uncover latent features for drugs and diseases, and then introduces drug feature-based similarities and disease semantic similarity as constraints for drugs and diseases in low-rank spaces. Different from the classic matrix factorization technique, SCMFDD takes the biological context of the problem into account. In computational experiments, the proposed method can produce high-accuracy performances on benchmark datasets, and outperform existing state-of-the-art prediction methods when evaluated by five-fold cross validation and independent testing.ConclusionWe developed a user-friendly web server by using known associations collected from the CTD database, available at http://www.bioinfotech.cn/SCMFDD/. The case studies show that the server can find out novel associations, which are not included in the CTD database.

Network-principled deep generative models for designing drug combinations as graph sets

“…Since our proposed method is the first to generate drug combinations for specific diseases, we consider the following baseline methods to compare with: 1) random selection of 1,000 pairs from 8,724 small-molecule drugs in Drugbank (Wishart et al, 2018); 2) 628 FDA-approved drug combinations curated by (Cheng et al, 2019) for hypertension and cancers (our case studies are on 4 types of cancers); 3) random selection of 1,000 pairs of FDA-approved drugs for the given disease, based on drug-disease dataset "SCMFDD-L" (Zhang et al, 2018).…”

MeSHHeading2vec: A new method for representing MeSH headings as feature vectors based on graph embedding algorithm

“…After standardizing the identifiers via the Correspondence Table and STRING database, we got of 7,739 different drugs and 4,975 different proteins. In order to avoid sparsity of associations, we selected drugs and proteins that are associated with more than 5 corresponding objects similar to the article described by Zhang et al (Zhang, et al, 2018). Finally, we obtained 7,318 experimental valid drug-target interactions containing 641 different drugs and 317 different proteins.…”

Biomarker2vec: Attribute- and Behavior-driven Representation for Multi-type Relationship Prediction between Various Biomarkers

“…A case study of Ataxia was implemented to assess the performance of the proposed method in a real-world environment. As mentioned above, we have collected 17414 drugdisease associations from CTD database [45] and processed them as described in the article of Zhang et al [54]. In order to verify the predicted effect of the proposed model on new disease, we removed 61 association pairs related to Ataxia, the remaining 17353 drugdisease associations were utilized as the training set to generate feature and construct the model, and each drug is connected to Ataxia in turn to form the test set.…”