bioRxivBioinformaticsPreprint
Representing cells as sentences enables natural-language processing for single-cell transcriptomics
Abstract
AO_SCPLOWBSTRACTC_SCPLOWGene expression matrices commonly used in single-cell transcriptomics, cannot be directly analyzed with tools developed for natural languages. By restructuring these matrices as abundance-ordered sequences of genes, we generate cell sentences: rank-normalized, positionally encoded expression data. We show that these cell sentences can be analyzed using existing tools from natural language processing to unify cell and gene representations across species.
- Citations
- 4
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Cell2Sentence: Teaching Large Language Models the Language of Biology
Daniel M. Levine, Syed Asad Rizvi, … David van Dijk·bioRxiv·Sep 11, 2023
- scConcept enables concept-level exploration of single-cell transcriptomic data
Hegang Chen, Yue Li·bioRxiv·Apr 24, 2026
- Emergent Statistical Laws in Single-Cell Transcriptomic Data
Silvia Lazzardi, Filippo Valle, … Matteo Osella·Physical review. EPeer-reviewed·Apr 27, 2023
- Tokenizing single-cell transcriptomes as a native language for large language models
Chuxi Xiao, Yuang Ding, … Xuegong Zhang·bioRxiv·Oct 22, 2025
- GeneVector: Identification of transcriptional programs using dense vector representations defined by mutual information.
Nicholas Ceglia, Zachary M. Sethna, … Andrew McPherson·Nature CommunicationsPeer-reviewed·Jul 20, 2023
- COTAN: Co-expression Table Analysis for scRNA-seq data
Silvia Giulia Galfrè, Francesco Morandin, … Manuela Helmer‐Citterich·NAR Genomics and BioinformaticsPeer-reviewed·Jun 23, 2021