cell2sentence
Google × Yale Gemma model that auto-generates and validates cancer treatment hypotheses
A Google × Yale Gemma model that automatically generates and validates cancer treatment hypotheses.
AI for biology and medicine — research tools, not medical advice.
Key features
- Applies LLMs to single-cell transcriptomics via rank-ordered cell sentences
- C2S-Scale models up to 27B on Pythia and Gemma-2 architectures
- Tasks: perturbation prediction, cluster captioning, QA, summarization
- PyPI package cell2sentence with tutorial notebooks
- Optional flash-attention for long-sequence inference
Good for
- Single-cell analysis with LLMs
- Cell type prediction and biological question answering
Stack & tags
Pythonsingle-cellgenomicsllmbioinformaticsopen-sourcecell-typetranscriptomics
Quick start
pip install cell2sentence==1.1.0From the project README on GitHub.
Similar open-source projects
scientific-agent-skills
★ 49,303Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
HealthGPT
★ 1,662Unified visual medical model — 7 medical understanding + 5 generation tasks