Thought Graph: Generating Thought Process for Biological Reasoning
This addresses the need for better semantic analysis of biological processes in bioinformatics and precision medicine, though it appears incremental as it builds on existing methods like GSEA and LLMs.
The paper tackles the problem of complex biological reasoning by introducing the Thought Graph framework, which improves understanding of gene sets by 40.28% over GSEA and 5.38% over LLM baselines in cosine similarity to human annotations.
We present the Thought Graph as a novel framework to support complex reasoning and use gene set analysis as an example to uncover semantic relationships between biological processes. Our framework stands out for its ability to provide a deeper understanding of gene sets, significantly surpassing GSEA by 40.28% and LLM baselines by 5.38% based on cosine similarity to human annotations. Our analysis further provides insights into future directions of biological processes naming, and implications for bioinformatics and precision medicine.