Analysis of number of nodes having/missing 'details'

[varsha1206]

@awmulyadi Here's the Notebook (in pdf as ipynb is not supported)
Node_composition.pdf
that shows the Node detail composition in StarkQA, as requested yesterday. I think I would like to start working on the 'effect/phenotype' node type as I had some success with it during the hackathon. Let me know if that works :)

[awmulyadi]

Hi @varsha1206 🙂 Thanks for sharing this essential information on the statistic of node information composition over the StarQA dataset. Regarding your idea(s), for sure you can contribute to this particular node enrichment. It is always a good idea to start with the task that you are already familiar with.

As I mentioned yesterday, I am currently preparing the basic setup for enrichment. I will let you know once it is ready to be checked out at the main branch. Meanwhile, you can check my implementation code in the following link:
https://github.com/VirtualPatientEngine/AIAgents4Pharma/tree/feat/textual-enrichment

We can always set up a follow-up online meeting if you have a concern/question 👍