Tahoe-x1: perturbation-trained single-cell foundation model weights (70M, 1.3B, 3B)
- Provider
- Tahoe Therapeutics
- License
- Apache-2.0 (source)
- Size
- 24 files
- Format
- JSON (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/tahoebio/Tahoe-x1)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Genomics & Bioinformatics
- Source
- https://www.biorxiv.org/content/10.1101/2025.10.23.683759v1
About this dataset
Open weights for Tahoe-x1 (Tx1), Tahoe Therapeutics' family of single-cell foundation models trained on perturbation data. The models were pretrained on 266 million single-cell transcriptomic profiles, including the Tahoe-100M drug perturbation compendium, and produce cell and gene embeddings for tasks such as cell type annotation, perturbation response and drug sensitivity prediction. Three sizes are provided, each in its own folder: 70m-model, 1b-model (about 1.3B parameters) and 3b-model (about 3B parameters). Each folder holds model.safetensors (and the original best-model.pt checkpoint), model_config.yml, collator_config.yml and vocab.json. Load them with the tahoe_x1 package (ComposerTX) pointed at the mounted folder, and pair them with the Tahoe-100M, CELLxGENE Census or SEA-AD archives to embed cells next to the data. Apache 2.0.
How to load this dataset in Python
import os, json
base = "/mnt/archive" # this model repo, mounted read-only
files = sorted(os.listdir(base)); print(files)
print(json.dumps(json.load(open(os.path.join(base, "config.json"))), indent=1)[:800])
import struct
with open(os.path.join(base, "1b-model/model.safetensors"), "rb") as f:
hdr = json.loads(f.read(struct.unpack("<Q", f.read(8))[0]))
tensors = {k: v for k, v in hdr.items() if k != "__metadata__"}
print(len(tensors), "tensors, e.g.", list(tensors.items())[:3])
# To load them: pip install safetensors torch, then safetensors.torch.load_file(path)Written for a Scigantic notebook, where /mnt/archive is the mounted dataset.
Data structure
File types in sampled files: JSON
Files
Example file: 1b-model/best-model.pt
Analyze this dataset without downloading it
On Scigantic, Tahoe-x1: perturbation-trained single-cell foundation model weights (70M, 1.3B, 3B) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Genomics & Bioinformatics datasets
- COVID-19 Data Lake
- Harvard Personal Genome Project Whole Genomes (Complete Genomics)
- KOLF2.1J Perturbation Cell Atlas
- Gabriella Miller Kids First Pediatric Research Program (Kids First)
- Supplementary Data for The salmon louse genome: copepod features and parasitic adaptations
- TCGA-PAAD Pancreatic Adenocarcinoma (GDC open-access tables, 185 cases)
- The complete reference genome for grapevine (Vitis vinifera L.) genetics and breeding
- PRIDE Archive (proteomics mass spectrometry repository)