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.

我们提出了 Thought Graph 作为一种新颖的框架，用于支持复杂推理，并以基因集分析为例，揭示生物过程之间的语义关系。我们的框架在提供对基因集的更深入理解方面表现出色，与基于余弦相似性到人类注释的 GSEA 相比，超过了 40.28％，并且超过了 LLM 基线 5.38％。我们的分析进一步为生物过程命名的未来方向和生物信息学以及精准医学的意义提供了见解。

思维图：生物推理的思维过程生成

Thought Graph: Generating Thought Process for Biological Reasoning

Gene set analysis is a mainstay of functional genomics, but it relies on
manually curated databases of gene functions that are incomplete and unaware of
biological context. Here we evaluate the ability of OpenAI's GPT-4, a Large
Language Model (LLM), to develop hypotheses about common gene functions from
its embedded biomedical knowledge. We created a GPT-4 pipeline to label gene
sets with names that summarize their consensus functions, substantiated by
analysis text and citations. Benchmarking against named gene sets in the Gene
Ontology, GPT-4 generated very similar names in 50% of cases, while in most
remaining cases it recovered the name of a more general concept. In gene sets
discovered in 'omics data, GPT-4 names were more informative than gene set
enrichment, with supporting statements and citations that largely verified in
human review. The ability to rapidly synthesize common gene functions positions
LLMs as valuable functional genomics assistants.

OpenAI 的 GPT-4 是一个基于生物医学知识的大型语言模型，能够从嵌入式知识中提出关于普遍基因功能的假设，为基因集分析提供可靠的功能概述和支持。