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

TL;DR

This work introduces Omics-Native Reasoning (ONR), a paradigm in which large language models reason directly over raw single-cell omics data while invoking specialized bioinformatics tools. Operationalized as scPilot, ONR automates three canonical single-cell analyses—cell-type annotation, trajectory inference, and gene regulatory network prediction—through an iterative, reasoning-first workflow that yields auditable, interpretable traces. The authors also present scBench, a nine-task benchmark with ground-truth references to rigorously evaluate omics-native reasoning across diverse datasets. Across multiple models, scPilot demonstrates improved accuracy, reduced structural errors in trajectories, and higher AUROC in GRN inference, while offering transparent explanations that support biological validation and discovery.

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

Figures (9)

• Figure 1: Human-like reasoning + established bioinformatics tools = hands-free single cell analysis
• Figure 2: Overview of the scPilot framework. The system integrates a problem-to-text converter, an LLM planner, and a bio-tool library to perform iterative reasoning and tool calls for three workflows: cell-type annotation, trajectory inference, and gene-regulatory prediction.
• Figure 3: Ablation on metadata and GO context.
• Figure 4: Ablation on trajectory inference input.
• Figure 5: Example of scPilot multi-gene reasoning in PBMC3k annotation.