Carbon (Hugging Face, 2026)

github.com/huggingface/carbon
Active199updated 1 month ago
Python
Apache-2.0

Family of causal genomic foundation models trained on 1T tokens (~6T DNA base pairs) from the Carbon Pretraining Corpus, combining eukaryote genes, mRNA transcripts, and prokaryote genomes with a hybrid text/6-mer tokenizer; Carbon-3B matches or beats Evo2-7B on zero-shot DNA evaluations including sequence recovery, variant effect prediction, and perturbations (Apache 2.0, 201+ stars)

Sourced from

  • Awesome AI for Sciencegithub.com/huggingface/carbon
  • GitHubgithub.com/huggingface/carbon

Related resources

Gene expression prediction

Active15K1 month ago
Jupyter Notebook
Apache-2.0

Arc Institute's 40B-parameter genome foundation model trained on 9 trillion nucleotides from all domains of life, supporting 1M base pair context for generalist DNA/RNA/protein prediction and design (Nature 2026)

Active4K3 weeks ago
Jupyter Notebook
Apache-2.0

Deep learning-based variant caller

Active3.7K3 months ago
Python
BSD-3-Clause

Google DeepMind's unified DNA sequence foundation model predicting molecular consequences of genetic variants from single-base resolution up to 1 megabase context, jointly outputting thousands of regulatory tracks (RNA expression, splicing, chromatin accessibility, TF binding, contact maps) for human and mouse genomes via a Python client and non-commercial API (2025)

Active1.9K2 weeks ago
Python
Apache-2.0

Deep probabilistic framework for single-cell and spatial omics analysis, integrating scVI, scANVI, totalVI and other VAE-based models for batch correction, cell annotation, multi-omics integration, and RNA velocity (scverse/NumFOCUS, Nature Methods 2018/2024)

Active1.6K1 month ago
Python
BSD-3-Clause

Single-cell analysis with transformers

Active1.6K2 months ago
Jupyter Notebook
MIT