
by BioMap
scFoundation is a large pretrained model for single-cell transcriptomics with 100 million parameters. The repository provides weights, code and downstream task examples.
Web appFree
Step 1: Download the pretrained weights and code from the model folder.
Step 2: Generate cell or gene embeddings for your data following the documentation.
Step 3: Pick a downstream task folder such as annotation or enhancement.
Step 4: Follow that folder's README and run its script.
Step 5: Or use the online platform for inference.
Over 50 million human single-cell transcriptomics profiles.
Read depth enhancement, drug response prediction, perturbation prediction, gene module inference, cell mapping and cell type annotation.
No. It was discontinued on April 30th, 2024, and users are asked to move to the new platform at aigp.biomap.com.
The README gives [email protected] for API issues.
CoArenaLive evaluation arena where computer-use AI models race on the same real tasks and human judgments produce comparative agent-performance data
ProteinMPNNProteinMPNN is a deep learning code base for designing protein sequences that fit a given backbone structure. You run it from the command line on PDB files.
StarDistDeep-learning microscopy segmentation tool for detecting star-convex cell nuclei and biological objects