# OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning

Source: [OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning](<https://www.sota2.com/research/paper/6a016284dbc836b87d823009>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-12T05:00:04.826Z

Authors: Maciej Sypetkowski, Joanna Krawczyk, {\\L}ukasz Smoli\\'nski, Remigiusz Kinas, Przemys{\\l}aw Pietrzak, Tomasz Jetka, Rafa{\\l} Powalski

Published: 2026-05-07T11:27:11.000Z

## Abstract

Interpreting transcriptomic data is one of the most common analytical tasks in modern biology. Yet most current models either consume expression profiles without producing natural-language biological explanations, or reason in language without direct access to quantitative omics measurements. We introduce OmicsLM, a multimodal LLM that connects quantitative omics profiles with natural-language biological tasks. OmicsLM represents each transcriptomic profile as a compact continuous representation within the LLM context. This interface preserves quantitative expression signal while allowing natural-language instructions, explicit gene mentions, and multiple interleaved biological samples to be processed together in one model context. We train OmicsLM on more than 5.5 million instruction-following examples spanning over 70 task types, combining continuous transcriptomic inputs, experimental data rendered through diverse language templates, and free-text biological knowledge and question-answering data. This mixture covers cell type annotation, perturbation prediction, clinical prediction, pathway reasoning, and open-ended biological question answering. Existing benchmarks evaluate either profile-level prediction or text-only biological QA, leaving language-guided, multi-sample reasoning over real expression profiles unmeasured. To close this gap, we introduce GEO-OmicsQA, a benchmark for multi-sample biological question answering built from real Gene Expression Omnibus (GEO) studies. We demonstrate that OmicsLM can use expression profiles directly and perform comparably to specialized omics models on profile-level tasks, while outperforming both omics-specialized models and general LLMs on language-guided biological reasoning over expression data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.06728>)

[PDF](<https://arxiv.org/pdf/2605.06728.pdf>)