All You Need is LOVE: Large Optimized Vector Embeddings Network for Drug Repurposing
Keywords: heterogeneous graph, knowledge graph, Large Language model, Llama2, drug discovery, drug repurposing, drug-disease association, AI
TL;DR: LOVENet: a novel approach to combine heterogeneous neural network and large language model to discover repurposing drugs.
Abstract: Traditional drug development is a resource-intensive and time-consuming process with a high rate of failure. To expedite this process, researchers have turned to computational approaches to construct comprehensive graphs of drug-disease associations and explore drug repurposing, finding novel therapeutic applications for existing medications. In parallel, the rapid advancement of the machine-learning field, coupled with the evolution of Natural Language Processing, shows capabilities for reasoning and extracting relationships across various domains. In this paper, we introduce LOVENet (Large Optimized Vector Embeddings Network), a new framework maximizing the synergistic effects of knowledge graphs and large language models (LLMs) to discover novel therapeutic uses for pre-existing drugs. Specifically, our approach fuses information from pairs of embedding from Llama2 and heterogeneous knowledge graphs to derive complex relations of drugs and diseases. To empirically validate our methodology, we conducted benchmarking experiments against state-of-the-art algorithms, utilizing three distinct datasets. Our results demonstrate that LOVENet consistently outperforms all other baselines. The code for this project is available at https://github.com/KlickInc/brave-foundry-drug-repurposing.
Submission Number: 69
Loading