BindVAE: Dirichlet variational autoencoders for de novo motif discovery from accessible chromatin

Source code, raw and processed datasets, trained model files from BindVAE trained on GM12878 ATAC-seq and A549 ATAC-seq data for this paper which will be soon published in Genome Biology. The source code is also maintained here on GitHub:

microsoft/BindVAE: Variational Auto Encoders for learning binding signatures of transcription factors (github.com)

Please contact the corresponding authors for any further data / model info you need.

Dirichlet variational autoencoders for de novo motif discovery from accessible chromatin | bioRxiv