Back

Simulate Scientific Reasoning with Multiple Large Language Models: An Application to Alzheimer's Disease Combinatorial Therapy

Xu, Q.; Liu, X.; Jiang, X.; Kim, Y.

2024-12-12 pharmacology and therapeutics
10.1101/2024.12.10.24318800 medRxiv
Show abstract

MotivationThis study aims to develop an AI-driven framework that leverages large language models (LLMs) to simulate scientific reasoning and peer review to predict efficacious combinatorial therapy when data-driven prediction is infeasible. ResultsOur proposed framework achieved a significantly higher accuracy (0.74) than traditional knowledge-based prediction (0.52). An ablation study highlighted the importance of high quality few-shot examples, external knowledge integration, self-consistency, and review within the framework. The external validation with private experimental data yielded an accuracy of 0.82, further confirming the frameworks ability to generate high-quality hypotheses in biological inference tasks. Our framework offers an automated knowledge-driven hypothesis generation approach when data-driven prediction is not a viable option. Availability and implementationOur source code and data are available at https://github.com/QidiXu96/Coated-LLM

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.