Our paper titled Combining Deep Learning Models for Improved Drug Repurposing: Advancements and An Extended Solution Methodology, in which we introduced the STING -decision support- system within the project and ensured a general literature review on the use of Deep Learning in drug repositioning, has just started to be indexed in IEEE Xplore!
You can follow the link for the full paper: https://ieeexplore.ieee.org/document/10544998
Combining Deep Learning Models for Improved Drug Repurposing: Advancements and An Extended Solution Methodology
Abstract:
Nowadays, major advancements through Artificial Intelligence (AI) were led by Deep Learning-based solutions. Considering their robust and extensive data processing mechanisms, Deep Learning (DL) models ensure great role in advancing solutions for real-world problems. Especially medical applications have been significantly improved by research studies as a result of intensive DL synergy. At this point, drug discovery has been one of the most remarkable fields where DL has been used in especially last few years. In the context of drug discovery studies, drug repurposing has a unique place to enable known drugs to be used for different diseases. As this is a remarkable way of optimizing discovery and treatment phases, use of DL for drug repurposing applications has still open areas to go. Objective of this paper is to examine the potential of combined DL models for improving drug repurposing and introduce a solution methodology, which includes use of multiple DL models to build a decision support system. It has been also aimed to support the system with computational models and Generative AI route to extend the capabilities towards a Digital Twin related approach.
Be First to Comment