Thoughts


  1. RAG & reading paper (done in scChat)
  2. Based on paper, presume possible clusters and markers. Run initial cluster based only on marker genes to establish a rough cell type assignment. Then refine clustering with the full gene set while maintaining the initial structure
  3. Use distances between clusters (e.g. UMAP)?
  4. Use gene expr proportion in clusters? But consider drop out
  5. Multiple AI average (scTriangulate, leverages cooperative game theory (Shapley Value))
  6. Generate report

Questions


  1. How to deal with multiple results from AIs
  2. Drop out

Evaluation


  1. Sankey plot. See A web app for comparing cell annotations or clusterings • tagtangoPasted image 20250114155945.png