GeDiNe-Lab/garreau_2026 ? reverse-engineered prompt
Reverse engineered prompt
Build me a reproducible R project for this holoprosencephaly study. I want it to take the input data, build a context specific co expression network from early forebrain genes, run patient wise network propagation from seed variants, and then produce the same analysis outputs and supplementary tables described in the README.
Please wire the scripts together so the workflow is easy to run from start to finish, with clear data loading, preprocessing, network analysis, random walk propagation, signal gene calling, enrichment testing, and candidate subnetwork generation. Also make sure the figure and table analysis scripts can be run without a lot of manual tweaking, and that the supplementary tables are saved in a clean, organized way.
If anything depends on external resources or current package behavior, look up the latest docs online if you need to. Keep the code readable, reproducible, and ready for someone else to rerun the whole analysis from scratch.
Are you gonna build this?
make sure you review the code using coderabbit