Reproduce “APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Romain Ferrara, Martin Soucail, Victor Gertner, Adil Moussali, Joris Cocquebert, Sandrine Oziel-Taieb, Julien Nicolas, Florence Gattacceca and 2 more
APOD uses a language-model agent to discover population ordinary differential equation models through open-ended search and multiple diagnostics. It individualizes a platelet model from sparse first-cycle measurements. In a later same-centre cohort of 19 patients, forecasts had R-squared 0.84 versus 0.06 without individualization, and all nadirs fell within 90% prediction intervals. This temporal validation does not establish that schedule changes improve outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.