This model can be used to generate embeddings of genomic regions or region sets. Once embeddings are obtained, they can be directly used for clustering, classification, or search and retrieval tasks. It is limited to hg38. It is not recommended to use this model for data outside ATAC-seq.
You can download and start encoding new genomic region data using the following code:
1from gitk.region2vec import Region2VecExModel
2
3model = Region2VecExModel("databio/r2v-ChIP-atlas")
4embeddings = model.encode("path/to/file.bed")
5
6print(embeddings.shape)