Difficulty in visualizing both cluster separation and cluster substructure
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.3k
- Forks
- 871
- Avg merge
- 1d 13h
- Merged PRs (30d)
- 5
Description
Hi,
I'm using UMAP to visualize single cell gene expression data in [scanpy](https://github.com/theislab/scanpy). I have some difficulty in setting UMAP parameters to make intuitive visualization. I'm not sure which repo to post the question, so I first posted here: https://github.com/theislab/scanpy/issues/174
Would you provide some suggestions on how to preserve the coarse-level cluster separation and still allow each cluster to occupy more space so that we can better visualize the continuous substructures within them? Thanks!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked Scanpy issue and the discussion in this issue about UMAP parameters for single-cell data. Determine whether a concrete parameter change or new capability is needed to preserve coarse cluster separation while exposing substructure; done should be defined by an agreed visualization and reproducible example.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data-visualization, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100