# LangCell: Language-Cell Pre-training for Cell Identity Understanding

Source: [LangCell: Language-Cell Pre-training for Cell Identity Understanding](<https://www.sota2.com/research/paper/68fa5f631e209131ce9e9979>)

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

Data updated: 2025-10-25T19:16:45.428Z

Authors: Suyuan Zhao, Jiahuan Zhang, Yushuai Wu, Yizhen Luo, Zaiqing Nie

Published: 2024-05-09T10:04:05.000Z

## Abstract

Cell identity encompasses various semantic aspects of a cell, including cell type, pathway information, disease information, and more, which are essential for biologists to gain insights into its biological characteristics. Understanding cell identity from the transcriptomic data, such as annotating cell types, has become an important task in bioinformatics. As these semantic aspects are determined by human experts, it is impossible for AI models to effectively carry out cell identity understanding tasks without the supervision signals provided by single-cell and label pairs. The single-cell pre-trained language models (PLMs) currently used for this task are trained only on a single modality, transcriptomics data, lack an understanding of cell identity knowledge. As a result, they have to be fine-tuned for downstream tasks and struggle when lacking labeled data with the desired semantic labels. To address this issue, we propose an innovative solution by constructing a unified representation of single-cell data and natural language during the pre-training phase, allowing the model to directly incorporate insights related to cell identity. More specifically, we introduce $\\textbf{LangCell}$, the first $\\textbf{Lang}$uage-$\\textbf{Cell}$ pre-training framework. LangCell utilizes texts enriched with cell identity information to gain a profound comprehension of cross-modal knowledge. Results from experiments conducted on different benchmarks show that LangCell is the only single-cell PLM that can work effectively in zero-shot cell identity understanding scenarios, and also significantly outperforms existing models in few-shot and fine-tuning cell identity understanding scenarios.

## 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.

- [Cellular Lineage Inference on Weinreb (cell lineage)](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-weinreb-cell-lineage.md>): Cellular Lineage Inference; Weinreb (cell lineage); DP: 47.4.

- [Cellular Lineage Inference on LHCO cell lineage](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-lhco-cell-lineage.md>): Cellular Lineage Inference; LHCO cell lineage; DP: 26.5.

- [Cellular Lineage Inference on Limb (cell lineage)](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-limb-cell-lineage.md>): Cellular Lineage Inference; Limb (cell lineage); DP: 25.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.06708>)

[PDF](<https://arxiv.org/pdf/2405.06708.pdf>)
