Reproduce “Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokinetics” 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
César Ojeda, Niklas Hartung, Wilhelm Huisinga, Tim Jahn, Purity Kamene Kavwele, Marian Klose, Piyush Kumar, Ramsés J. Sánchez and 1 more
PFF uses sparse, irregular measurements to generate virtual concentration profiles and forecast an individual trajectory from samples. It learns a distribution over trajectories conditioned on study context and the patient’s observed prefix for forecasting. In caffeine forecasting, PFF reports log-RMSE of 0.174 ± 0.086 versus AICMET at 0.399 ± 0.205. It is pretrained on synthetic data; evaluation focuses on single-dose studies.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.