SwiftDossier: Tailored Automatic Dossier for Drug Discovery with LLMs and Agents
This work addresses the need for more efficient and accurate AI tools in the expensive and time-consuming drug discovery process, though it appears incremental by combining existing methods like RAG and tool integration.
The authors tackled the problem of LLMs lacking domain-specific knowledge and tool-use capabilities in drug discovery by implementing an advanced RAG system to improve answer accuracy and creating an automatic dossier generator that integrates external tools, resulting in a production-ready dossier with summarized PDF and PowerPoint outputs.
The advancement of artificial intelligence algorithms has expanded their application to several fields such as the biomedical domain. Artificial intelligence systems, including Large Language Models (LLMs), can be particularly advantageous in drug discovery, which is a very long and expensive process. However, LLMs by themselves lack in-depth knowledge about specific domains and can generate factually incorrect information. Moreover, they are not able to perform more complex actions that imply the usage of external tools. Our work is focused on these two issues. Firstly, we show how the implementation of an advanced RAG system can help the LLM to generate more accurate answers to drug-discovery-related questions. The results show that the answers generated by the LLM with the RAG system surpass in quality the answers produced by the model without RAG. Secondly, we show how to create an automatic target dossier using LLMs and incorporating them with external tools that they can use to execute more intricate tasks to gather data such as accessing databases and executing code. The result is a production-ready target dossier containing the acquired information summarized into a PDF and a PowerPoint presentation.