Neural Circuit Function Inference with LLMs

📅 2026-07-27
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the challenge of systematically inferring cell-type identities and circuit functions from known connectomic data. To this end, we propose LLantia, a novel approach that, for the first time, integrates large language models (LLMs) with the whole-brain connectome atlas of Drosophila. By distilling knowledge from scientific literature, LLantia automatically extracts functional annotations for neurons and organizes them within a hierarchical reasoning framework contextualized by behavior and physiology. This enables automated, traceable, and verifiable inference of neural circuit functions at the whole-brain scale. Experimental results demonstrate that LLantia successfully annotates all cell types in the adult Drosophila brain and elucidates the functions of multiple key circuits, with predictions showing strong concordance with subsequently published findings, thereby exhibiting high interpretability and biological plausibility.
📝 Abstract
The success of connectome mapping now shifts the challenge of understanding the nervous system to the interpretation of neural circuits. Here, we devise a new automated method, LLantia (LLM automated neural circuit inference and analysis), to systematically infer neural circuit function and the role of its component neural cell types. Our approach distills descriptions of cell type function from the literature and, in combination with the connectome, then infers the function for all other cell types, which serves as a basis for subsequent neural circuit function inference. Results are structured hierarchically, with different possible circuit functions organised under multiple possible behavioural and physiological contexts, and each circuit function composed of subcircuit descriptions alongside relevant cell types to facilitate both backtracking to known, published information and support further experimental research. We illustrate our method by inferring cell type function for all cell types of the adult fruit fly brain and for select broader circuits within, and validate our findings, including by cross-checking with literature published after the release date of our analysis.
Problem

Research questions and friction points this paper is trying to address.

neural circuit function
connectome
cell type function
nervous system interpretation
neural circuit inference
Innovation

Methods, ideas, or system contributions that make the work stand out.

neural circuit inference
large language models
connectome
cell type function
automated analysis