Litcius/Paper detail

Multimodal learning enables chat-based exploration of single-cell data

Moritz Schaefer, Peter Peneder, Daniel Malzl, Salvo Danilo Lombardo, Mihaela Peycheva, Jake Burton, Anna Hakobyan, Varun Sharma, Thomas Krausgruber, Celine Sin, Jörg Menche, Eleni M. Tomazou, Christoph Bock

2025Nature Biotechnology27 citationsDOIOpen Access PDF

Abstract

Single-cell sequencing characterizes biological samples at unprecedented scale and detail, but data interpretation remains challenging. Here, we present CellWhisperer, an artificial intelligence (AI) model and software tool for chat-based interrogation of gene expression. We establish a multimodal embedding of transcriptomes and their textual annotations, using contrastive learning on 1 million RNA sequencing profiles with AI-curated descriptions. This embedding informs a large language model that answers user-provided questions about cells and genes in natural-language chats. We benchmark CellWhisperer's performance for zero-shot prediction of cell types and other biological annotations and demonstrate its use for biological discovery in a meta-analysis of human embryonic development. We integrate a CellWhisperer chat box with the CELLxGENE browser, allowing users to interactively explore gene expression through a combined graphical and chat interface. In summary, CellWhisperer leverages large community-scale data repositories to connect transcriptomes and text, thereby enabling interactive exploration of single-cell RNA-sequencing data with natural-language chats.

Topics & Concepts

Computer scienceBenchmark (surveying)EmbeddingSoftwareArtificial intelligenceBiological dataWord embeddingDeep learningInterpretation (philosophy)Machine learningKey (lock)Data typeData scienceEncoding (memory)Human–computer interactionTranscriptomeScale (ratio)World Wide WebInterrogationSynthetic dataComputational biologyFeature learningExpression (computer science)Data modelingMultimodal learningSingle-cell and spatial transcriptomicsBiomedical Text Mining and OntologiesDomain Adaptation and Few-Shot Learning
Multimodal learning enables chat-based exploration of single-cell data | Litcius