Implement `sc.tl.mde`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 779
- Avg merge
- 1d 4h
- Merged PRs (30d)
- 27
Description
- Additional function parameters / changed functionality / changed defaults?
- New analysis tool: A simple analysis tool you have been using and are missing in
sc.tools? - New plotting function: A kind of plot you would like to seein
sc.pl? - External tools: Do you know an existing package that should go into
sc.external.*? - Other?
PyMDE is a nice visualization method that to me seems to effectively serve the same purpose as UMAP in analyses (discussion about appropriateness of these methods can be in another issue :) ). It's super fast because after running pynndescent it puts the graph on the GPU optionally (using pytorch). I would love to see this in scanpy. There might be a way to use the scanpy neighbors graph from sc.pp.neighbors directly in pymde as the function below is a wrapper of some internal classes.
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 reviewing the requested sc.tl.mde analysis tool and how sc.pp.neighbors provides the existing neighbors graph. Investigate the PyMDE wrapper and its optional PyTorch GPU use, then determine the integration scope and validation needed. The issue does not name implementation files, tests, or a precise completion criterion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- data-visualization, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100