Abstract
Functional drug actions refer to drug-affected GO terms. They aid in the investigation of drug effects that are therapeutic or adverse. Previous studies have utilized the linkage information between drugs and functions in molecular level biological networks. Since the current knowledge of molecular level mechanisms of biological functions is still limited, such previous studies were incomplete. We expected that the multi-level biological networks would allow us to more completely investigate the functional drug actions. We constructed multi-level biological networks with genes, GO terms, and diseases. Meta-paths were utilized to extract the features of each GO term. We trained 39 SVM models to prioritize the functional drug actions of the various 39 drugs. Through the multi-level networks, more functional drug actions were utilized for the 39 models and inferred by the models. Multi-level based features improved the performance of the models, and the average AUROC value in the cross-validation was 0.86. Moreover, 60% of the candidates were true.
Highlights
Functional drug actions refer to drug-affected GO terms
Functional drug actions are defined as drug actions on biological functions such as GO terms[2]
The features of each function were extracted from linkage information about the function with targets or indications in the multi-level biological networks
Summary
Functional drug actions refer to drug-affected GO terms. They aid in the investigation of drug effects that are therapeutic or adverse. Even though the utilities of functional drug actions have been demonstrated in drug development, information about the functional drug actions in relevant databases is described in plain text without standardized identifiers such as GO terms but is scarce and confined to their own purposes in the drug development. Such information in the DrugBank was produced by only two or more curators using PubMed, drug references, Food and Drug Administration (FDA) labels, etc.[13] wet lab experiments with cells, tissue, or animal models are a clear way to identify functional drug actions; the costs are high. The prioritized candidates will help to collect functional drug actions that have been already identified and to select proper candidates for investigation in wet lab experiments
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
