Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Thought Graph: Generating Thought Process for Biological Reasoning

Chi-Yang Hsu, Kyle Cox, Jiawei Xu, Zhen Tan, Tianhua Zhai, Mengzhou Hu, Dexter Pratt, Tianlong Chen, Ziniu Hu, Ying Ding

TL;DR

The Thought Graph is presented as a novel framework to support complex reasoning and use gene set analysis as an example to uncover semantic relationships between biological processes and provides insights into future directions of biological processes naming and implications for bioinformatics and precision medicine.

Abstract

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.

Thought Graph: Generating Thought Process for Biological Reasoning

TL;DR

The Thought Graph is presented as a novel framework to support complex reasoning and use gene set analysis as an example to uncover semantic relationships between biological processes and provides insights into future directions of biological processes naming and implications for bioinformatics and precision medicine.

Abstract

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.
Paper Structure (17 sections, 2 figures, 1 table)

This paper contains 17 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. LLM Reasoning
  4. Knowledge Graph for LLM Reasoning
  5. LLM Reasoning in Biomedical Domain
  6. Methodology
  7. Problem Formulation
  8. Infrastructure of Thought Graph
  9. Thoughts expansion
  10. Thought Graph
  11. Experiment & Evaluation
  12. Data Collection
  13. Baselines and Model Description
  14. Evaluation Methods
  15. Performance Evaluation
  16. ...and 2 more sections

Figures (2)

  • Figure 1: The flowchart presents the application of the Thought Graph to the Gene Ontology (GO) database. First, Thought Graph uses a gene set and initial prompt to generate three Biological Processes (BPs). Then, a voter evaluates and selects the best BP (dark green) and second best BP (light green), which are more accurately descriptive of the gene set. Each chosen BP, along with a subsequent prompt, is utilized to generate two additional, more specific BPs. This procedure is conducted recursively until Thought Graph has reached five layers. Finally, a voter chooses the final answer from the last layer.
  • Figure 2: The distribution of the mean similarity score at each layer using Thought Graph (p). The blue line denotes the median of layer 3.