arXiv cs.AI· Maciej Sypetkowski, {\L}ukasz Smoli{\'n}ski, Remigiusz Kinas, Joanna Krawczyk, Bart{\l}omiej Hofman, Aleksandra Mo{\.z}wi{\l}{\l}o, Micha{\l} Pikusa, Tomasz Jetka, Rafa{\l} Powalski·· 4 小时前AI 评分39
OmicsLM：面向多样本组学推理的 9B 多模态大语言模型
OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
AI 导读
研究者推出 OmicsLM，一个 9B 多模态大语言模型，将 bulk 或单细胞转录组表示为紧凑的连续 embedding，可与自然语言指令及其他样本交织在同一上下文中。
正文 · 原文
Abstract:Large language models can reason over biological knowledge, but they are not naturally equipped to work with quantitative omics measurements. Existing approaches either convert expression profiles into long textual representations, often losing quantitative information, or connect omics encoders to language models for narrow tasks. We introduce OmicsLM, a 9B multimodal language model that represents each bulk or single-cell transcriptome as a compact continuous embedding that can be interleaved with natural-language instructions and with other samples in the same context. An key contribution is a training corpus that connects experimental measurements with biological knowledge and task supervision. We combine templates linking transcriptomic profiles to annotations and experimental outcomes, reasoning examples connecting evidence across sources, and LLM-generated supervision with task-specific quality checks. The instruction-tuning corpus spans 157 biological and general-purpose task groups. Training includes continued pretraining on 20 billion tokens and supervised fine-tuning on 5.21 million conversations. We further introduce GEO-OmicsQA, a publication-disjoint benchmark of 3,000 questions requiring models to interpret and compare expression profiles from real GEO studies. OmicsLM achieves the best results among the evaluated models on three of four held-out annotation tasks and on all six GEO-OmicsQA variants, and the best average performance among compared methods on PerturbQA perturbation-response prediction. Ablations show a clear advantage for continuous omics representations over a text-only gene-list representation. Together, these results show that quantitative transcriptomic measurements and biological language can be integrated within a general conversational model, enabling both predictive tasks and language-guided interpretation of experimental samples.
| Comments: | 47 pages (10 pages main text, 29 pages appendix), 1 figure, 16 tables |
| Subjects: | Genomics (q-bio.GN); Artificial Intelligence (cs.AI); Cell Behavior (q-bio.CB) |
| Cite as: | arXiv:2605.06728 [q-bio.GN] |
| (or arXiv:2605.06728v2 [q-bio.GN] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06728 arXiv-issued DOI via DataCite |
Submission history
From: Tomasz Jetka Dr. [view email]
[v1]
Thu, 7 May 2026 11:27:11 UTC (250 KB)
[v2]
Sun, 25 Oct 2026 08:32:57 UTC (241 KB)
来源：arXiv cs.AI · arxiv.org