Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.19535421 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901746644680704 |
|---|---|
| author | Sri Vishnu Jagan N Syed Ahamed K Mrs. R. Creesy, M.E |
| author_facet | Sri Vishnu Jagan N Syed Ahamed K Mrs. R. Creesy, M.E |
| contents | <p>Artificial Intelligence (AI) has emerged as a <br>promising approach for accelerating drug discovery and enabling <br>personalized treatment strategies in modern healthcare. <br>Traditional drug development is a time-consuming, expensive, and <br>high-risk process, often requiring more than a decade for <br>successful clinical approval. Although several AI-based drug <br>discovery models have been proposed, most existing systems suffer <br>from limited clinical applicability due to dataset bias, lack of <br>interpretability, and poor generalization across diseases. This <br>research proposes an AI-driven drug repurposing framework that <br>leverages publicly available biomedical datasets to identify <br>potential therapeutic candidates for specific diseases. The <br>proposed system utilizes machine learning and deep learning <br>techniques, including graph-based molecular representations, to <br>predict drug-target interactions and molecular properties. By <br>focusing on drug repurposing rather than novel drug creation, the <br>system aims to reduce development time, cost, and safety risks. <br>Additionally, explainable AI techniques are incorporated to <br>improve transparency and trust in model predictions. The <br>proposed approach demonstrates a practical, scalable, and real<br>world applicable solution for personalized treatment support in <br>clinical decision-making. </p> <p>Keywords—Drug Repurposing, Graph Neural Networks, <br>Explainable AI, Drug-Target Interaction, Clinical Decision <br>Support. </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19535421 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Interpretable Graph-Based Artificial Intelligence for Molecular Drug Repurposing and Target Interaction Inference Sri Vishnu Jagan N Syed Ahamed K Mrs. R. Creesy, M.E <p>Artificial Intelligence (AI) has emerged as a <br>promising approach for accelerating drug discovery and enabling <br>personalized treatment strategies in modern healthcare. <br>Traditional drug development is a time-consuming, expensive, and <br>high-risk process, often requiring more than a decade for <br>successful clinical approval. Although several AI-based drug <br>discovery models have been proposed, most existing systems suffer <br>from limited clinical applicability due to dataset bias, lack of <br>interpretability, and poor generalization across diseases. This <br>research proposes an AI-driven drug repurposing framework that <br>leverages publicly available biomedical datasets to identify <br>potential therapeutic candidates for specific diseases. The <br>proposed system utilizes machine learning and deep learning <br>techniques, including graph-based molecular representations, to <br>predict drug-target interactions and molecular properties. By <br>focusing on drug repurposing rather than novel drug creation, the <br>system aims to reduce development time, cost, and safety risks. <br>Additionally, explainable AI techniques are incorporated to <br>improve transparency and trust in model predictions. The <br>proposed approach demonstrates a practical, scalable, and real<br>world applicable solution for personalized treatment support in <br>clinical decision-making. </p> <p>Keywords—Drug Repurposing, Graph Neural Networks, <br>Explainable AI, Drug-Target Interaction, Clinical Decision <br>Support. </p> |
| title | Interpretable Graph-Based Artificial Intelligence for Molecular Drug Repurposing and Target Interaction Inference |
| url | https://doi.org/10.5281/zenodo.19535421 |