Drug-Drug interactions prediction calculations between cardiovascular drugs and antidepressants for discovering the potential co-medication risks
Tie Hua Zhou, Tian Yu Jin, Xi Wei Wang, Ling Wang
Abstract
Predicting Drug-Drug Interactions (DDIs) enables cost reduction and time savings in the drug discovery process, while effectively screening and optimizing drugs. The intensification of societal aging and the increase in life stress have led to a growing number of patients suffering from both heart disease and depression. These patients often need to use cardiovascular drugs and antidepressants for polypharmacy, but potential DDIs may compromise treatment effectiveness and patient safety.
Introduction
A drug is a chemical or natural substance employed for disease prevention, diagnosis, treatment and symptom relief. Drug-Drug Interaction (DDI) refers to the changes in PharmacoDynamics (PD) and PharmacoKinetics (PK) that occur when one drug is administered concurrently or at certain intervals with another drug or multiple other drugs [1, 2]. The rational use of DDIs can enhance drug efficacy, alleviate or avoid the toxic side effects of drugs; conversely, it could lead to an increase in toxic side effects or a decrease in drug efficacy, even worsening the condition or endangering life [3–5].
Materials and method
In this section, we present the sources of the data sets used in the experiments, the learning process of MDFLDRR, the objective function and its corresponding solution, the description of drug molecular structure transformation, as well as the core pseudocode.
Results
Evaluation metrics
To balance the consumption of computing resources and more accurately reflect the model’s performance under different data distributions when evaluating machine learning model performance, we ultimately chose to use 5-fold Cross-Validation (5CV). For the two different DDI prediction goals that we proposed, we carried out 5CV separately for each of them.
Discussion
Drug interaction severity level analysis
The preparatory work shown in Table 8 and Fig 13 illustrates two groups of drugs, both involving Drug A interacting with Drug B, and Drug C bearing molecular structural similarity to Drug A, for better understanding. Next, we will introduce this in three steps: First, we obtained the severity level of the interaction between Drug A and Drug B using the drug databases. Second, we identified Drug C, which can interact with Drug B, from the DDIs predicted by MDFLDRR and then calculated the molecular structural similarity between Drug C and Drug A. Third, based on the severity level of the interaction obtained in the first step and the molecular structure similarity obtained in the second step, we speculate on the severity level of the interaction between Drug C and Drug B.
Acknowledgments
The authors would like to express their gratitude to the reviewers for their invaluable suggestions, which greatly contributed to improving the manuscript.
Citation: Zhou TH, Jin TY, Wang XW, Wang L (2025) Drug-Drug interactions prediction calculations between cardiovascular drugs and antidepressants for discovering the potential co-medication risks. PLoS ONE 20(1): e0316021. https://doi.org/10.1371/journal.pone.0316021
Editor: Turki Talal Turki, King Abdulaziz University, SAUDI ARABIA
Received: July 7, 2024; Accepted: December 3, 2024; Published: January 13, 2025
Copyright: © 2025 Zhou et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: Publicly available data sets were analyzed in this study. The link to the DrugBank database is https://go.drugbank.com/releases/latest; the link to the UniProt database is https://www.uniprot.org/id-mapping; and the link to the KEGG database is https://www.genome.jp/kegg/kegg1b.html.
Funding: This research was funded by the National Natural Science Foundation of China (No.62102076) • Ling Wang • No.62102076 • National Natural Science Foundation of China • https://www.nsfc.gov.cn/ • Yes.
Competing interests: The authors have declared that no competing interests exist.
