# Cell2Text: Multimodal LLM for Generating Single-Cell Descriptions from RNA-Seq Data

arXiv: https://arxiv.org/abs/2509.24840 · HTML: https://mlsanity.com/paper/2509.24840/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 49 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers](https://mlsanity.com/paper/2307.14367/) (2023)
- [Cell-ontology guided transcriptome foundation model](https://mlsanity.com/paper/2408.12373/) (2024)
- [Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment](https://mlsanity.com/paper/2505.11194/) (2025)

## Built on by (most cited first, 2 of 2)

- [LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology](https://mlsanity.com/paper/2510.07793/) (2025)
- [ES-Merging: Biological MLLM Merging via Embedding Space Signals](https://mlsanity.com/paper/2603.14405/) (2026)

## Abstract (arXiv)

Single-cell RNA sequencing has transformed biology by enabling the measurement of gene expression at cellular resolution, providing information for cell types, states, and disease contexts. Recently, single-cell foundation models have emerged as powerful tools for learning transferable representations directly from expression profiles, improving performance on classification and clustering tasks. However, these models are limited to discrete prediction heads, which collapse cellular complexity into predefined labels that fail to capture the richer, contextual explanations biologists need. We introduce Cell2Text, a multimodal generative framework that translates scRNA-seq profiles into structured natural language descriptions. By integrating gene-level embeddings from single-cell foundation models with pretrained large language models, Cell2Text generates coherent summaries that capture cellular identity, tissue origin, disease associations, and pathway activity, generalizing to unseen cells. Empirically, Cell2Text outperforms baselines on classification accuracy, demonstrates strong ontological consistency using PageRank-based similarity metrics, and achieves high semantic fidelity in text generation. These results demonstrate that coupling expression data with natural language offers both stronger predictive performance and inherently interpretable outputs, pointing to a scalable path for label-efficient characterization of unseen cells.