scDFM (ICLR 2026)

github.com/ai4science-westlakeu/scdfm
Active41updated 2 months ago
Python
MIT

Distributional flow matching model for robust single-cell perturbation prediction, modeling the full distribution of perturbed cellular expression profiles conditioned on control states via PAD-Transformer and multi-kernel MMD regularization; reduces MSE by 19.6% over the strongest baseline in combinatorial settings (Westlake University, 41+ stars, MIT License)

Sourced from

  • Awesome AI for Sciencegithub.com/ai4science-westlakeu/scdfm
  • GitHubgithub.com/ai4science-westlakeu/scdfm

Related resources

Single-cell analysis with transformers

Active1.6K2 months ago
Jupyter Notebook
MIT

Unified Python framework for bulk, single-cell, and spatial RNA-seq multi-omics analysis with deep learning deconvolution (VAE) and graph neural networks, bridging Bindea, Bindea, scanpy and squidpy ecosystems (Nature Communications 2024)

Active1.1K1 week ago
Python
GPL-3.0

Automated cell type annotation tool for single-cell transcriptomics using gradient boosting and logistic regression with reference atlases, enabling standardized classification across datasets (Wellcome Sanger Institute, Nature Biotechnology 2022)

Active4861 month ago
Python
MIT

A diffusion language model for genome-scale perturbation prediction across diverse cellular contexts.

Active03 months ago

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