Cell2Sentence

Rating:

Rate it!

Overview

Open-source framework that turns single-cell gene expression into 'cell sentences' so LLMs can analyze and generate biology insights.

Visit website

One more link One more link One more link One more link One more link

Best For Professions:

computational biologists bioinformaticians machine learning researchers genomics scientists data scientists

Cell2Sentence (C2S) is an open-source framework from the van Dijk Lab that represents single-cell RNA-seq profiles as textual “cell sentences” (genes ordered by expression), enabling large language models to natively model biology. The project includes code, docs, and open models (C2S-Scale) released with Google Research/DeepMind for state-of-the-art single-cell tasks like cell typing, perturbation prediction, and virtual cell generation.

Autonomy level

54%

Reasoning: Cell2Sentence (C2S-Scale) demonstrates intermediate autonomy in biological research applications. The model exhibits significant independent reasoning capabilities: it can autonomously generate novel hypotheses about cancer cell behavior, predict cellular responses to drug treatments and perturbations, identify between 10-30% novel drug candidates ...

Comparisons

Custom Comparisons

Some of the use cases of Cell2Sentence:

Transforming scRNA-seq data into text so LLMs can learn cellular patterns.
Training and evaluating LLMs on single-cell tasks (e.g., cell type prediction).
Generating “virtual cells” and simulating perturbation responses.
Integrating biology text and metadata with transcriptomic signals for joint modeling.
Reproducing C2S pipelines with open code, docs, and released models.

Loading Community Opinions...

Pricing model:

free

Code access:

open-source

Popularity level: 70%