Open lzamparo opened 7 years ago
Now that I'm primarily working with embedding ATAC-seq peaks, tests (2) is not so useful, but they can perhaps be re-imagined as subpeaks within different types of elements. Possibly also between similar elements of similar celltypes for the Corces data set?
To interpret the learned codes it would help to have the following visualizations:
Maybe something like exemplar-based clustering could work in the embedding space?
Further down the line, for a given probe, can we decode along a probe to find important Kmers (that might resemble motifs??)