QFM-BioPred: Quantum Fusion Model for Bioactivity Prediction in Cardiovascular Disease Drug Discovery

Le résumé fourni par la source

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, highlighting the urgent need for more effective treatments. The conventional drug discovery process is time-consuming and expensive; therefore, new approaches are required. Quantum machine learning in compound bioactivity prediction has been demonstrated in drug discovery, but its application in cardiovascular medicine remains limited. Therefore, this work proposed the quantum fusion model (QFM) to enhance the bioactivity predictions for heart disease treatments. The proposed model encoded molecular data into quantum states using the quantum random forest method on the ChEMBL dataset. Logistic regression classifiers were then trained on these encoded data. The QFM, which integrates quantum-inspired algorithms with classical machine learning, achieved an accuracy of 92.7% in classifying bioactive compounds, outperforming individual models and existing methods. It also demonstrated strong precision (0.92), recall (0.93), and F1 score of 0.92, with receiver operating characteristic area under the curve (AUC) and precision-recall AUC values of 0.961 and 0.959, respectively. These results indicate the model’s ability to identify complex molecular structures accurately. This work advances bioactivity prediction to aid drug development for CVDs and aligns with the United Nations Sustainable Development Goal 3: Good Health and Well-being. Future research will apply this approach to other diseases and incorporate more complex quantum circuits to enhance accuracy further. Received: 31 December 2024 | Revised: 12 May 2025 | Accepted: 30 May 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available at https://www.ebi.ac.uk. Author Contribution Statement Gundala Pallavi: Methodology, Software, Data curation, Writing – original draft, Visualization, Project administration. Ali Altalbe: Investigation, Writing – review & editing. Prasanna Kumar Rangarajan: Conceptualization, Validation, Formal analysis, Resources, Writing – review and editing, Supervision.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.