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
In the era of exponential growth in biological data, the quest for artificial intelligence (AI) that can function as a true scientific assistant to automate and interpret complex scientific analyses has never been more urgent. Recently, large language models (LLMs) have demonstrated surprising breadth in factual recall and reasoning prowess [73,26,32,22], prompting the question: Can LLMs be harnessed as genuine scientific partners to revolutionize traditional biological discovery pipeline? Yet, translating these general LLM capabilities into the realm of single-cell biology remains challenging. The surge of single-cell omics has shifted biology from bulk averages to million-cell matrices [63,9,14], but analysis pipelines still depend on implicit, human-only reasoning [39,54,17] (Figure 1). While LLMs excel at natural-language explanation and reasoning, most current uses in computational biology utilize LLMs simply as interfaces that invoke existing bioinformatics tools [75,11,31], relying solely on these tools' inherent functionalities. Other approaches heavily train foundation models to embed single-cell counts into opaque, high-dimensional vector spaces [77,15,67], resulting in less interpretable analyses critical to biological discovery.
We propose to bridge this gap with omics-native reasoning (ONR)-a new interactive paradigm in which an LLM (i) receives a concise textual summary derived from the single-cell expression matrix, (ii) explicitly articulates biological hypotheses in natural language, (iii) invokes targeted bioinformatics operations directly on the raw data, (iv) evaluates and interprets numerical evidence, and (v) iteratively refines its reasoning until arriving at biologically coherent conclusions. As shown in Figure 1, by closely coupling reasoning to raw omics data, ONR generates transparent and auditable analyses, facilitating interpretability, scientific rigor, and human validation. This paper operationalizes ONR through SCPILOT, a systematic framework that harnesses the reasoning capabilities of an off-the-shelf LLM integrated with a problem-to-text converter and a curated bioinformatics tool library. SCPILOT explicitly formulates and iteratively refines hypotheses, addressing three canonical single-cell challenges: cell-type annotation, developmental-trajectory reconstruction, and transcription-factor targeting, producing transparent and biologically insightful reasoning processes. To systematically quantify progress, we further introduce SCBENCH, the first benchmark for omics-native reasoning that scores numerical accuracy and reveals the biological validity of the model’s narrative across nine expertly curated single-cell tasks. Our contributions are fourfold:
• LLM-driven single-cell analysis framework. We formulate the first omics-native reasoning, language-centric workflow that automates key analytic stages-cell-type annotation, trajectory inference, and gene-regulatory network prediction-while preserving scientific transparency.
• Comprehensive benchmark suit. SCBENCH offers task-specific metrics and expert-verified ground truth, enabling objective comparison of LLMs on biologically meaningful problems.
• Empirical insights and validation. Comprehensive experiments across nine benchmark datasets demonstrate the effectiveness of SCPILOT: iterative omics-native reasoning lifts average cell-type annotation accuracy by 11%, reduces trajectory graph-edit distance by 26%, and improves GRN prediction AUROC by 0.03 over direct prompting and conventional baselines.
• Biological interpretability and diagnostic reasoning. SCPILOT generates transparent reasoning traces that expose marker ambiguities, lineage inconsistencies, and tissue-specific regulatory logic, enabling biologically interpretable and diagnostically informative single-cell analyses.
Large Language Models in Single-Cell Analysis. Early biomedical LLMs, e.g., BioGPT [48], BioMedLM [8], and Galactica [66], showed that pre-training on PubMed abstracts or full-text markedly improves factual recall and zero-shot QA, while newer general LLMs (e.g., GPT-4o, Claude-3) now rival or exceed them with broader literature coverage. In parallel, a growing family of single-cell foundation models [77,21,15,67,59,25,58,41,6,65,37], mostly encoder-style LLMs that treat genes as tokens to learn gene-and cell-level embeddings for imputation, perturbation prediction, and cross-dataset transfer. Cell2Sentence and C2S-Scale [41,56] encode each cell as a “sentence,” enabling natural-language queries, while other works build LLM interfaces for single-cell data via fine-tuning [46,61,42] or autonomous tool agents [27,19,57,75,11]. General-purpose biomedical agents such as Biomni [31] demonstrate autonomous problem-solving across domains.
Despite their progress, these approaches sidestep the core cognitive load of single-cell analysis: embedding models speak in vectors with no explanations, chat wrappers and tool agents re-package fixed results
This content is AI-processed based on open access ArXiv data.