scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

TL;DR

scPilot introduces a novel framework where large language models perform step-by-step reasoning directly on single-cell RNA-seq data, improving accuracy and interpretability in bioinformatics analysis.

Contribution

It is the first systematic approach to integrate LLMs with raw omics data for transparent and iterative single-cell analysis tasks.

Findings

11% accuracy improvement in cell-type annotation

30% reduction in trajectory graph-edit distance

Generation of interpretable reasoning traces

Abstract

We present scPilot, the first systematic framework to practice omics-native reasoning: a large language model (LLM) converses in natural language while directly inspecting single-cell RNA-seq data and on-demand bioinformatics tools. scPilot converts core single-cell analyses, i.e., cell-type annotation, developmental-trajectory reconstruction, and transcription-factor targeting, into step-by-step reasoning problems that the model must solve, justify, and, when needed, revise with new evidence. To measure progress, we release scBench, a suite of 9 expertly curated datasets and graders that faithfully evaluate the omics-native reasoning capability of scPilot w.r.t various LLMs. Experiments with o1 show that iterative omics-native reasoning lifts average accuracy by 11% for cell-type annotation and Gemini-2.5-Pro cuts trajectory graph-edit distance by 30% versus one-shot prompting, while generating transparent reasoning traces explain marker gene ambiguity and regulatory logic. By grounding LLMs in raw omics data, scPilot enables auditable, interpretable, and diagnostically informative single-cell analyses. Code, data, and package are available at https://github.com/maitrix-org/scPilot