biocore / biocore/gemelli

Tying features to modalities in joint-RPCA

Open
#63 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
92
Forks
20
PR merge metrics
No merged PRs in 30d

Description

Is there a way to easily tie which feature came from which modality at the moment? As far as I can tell, the current implementation stores all features across tables in an `OrdinationResults` instance. You can certainly make a bespoke mapping of feature:table but I think it would be useful to incorporate this into the codebase. Specifically, this would be useful for visualization if, for example, you wanted to plot a network and color the nodes by 16S/18S/ITS/etc.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by tracing the joint-RPCA results into the OrdinationResults instance and inspect how features from the input tables are currently stored. Determine how a feature-to-modality mapping could be exposed for downstream visualization; done means callers can identify whether each feature came from 16S, 18S, ITS, or another modality.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.