OpenADMET PXR Challenge retro: co-folding struggles to find right poses across 184 crystal structures
anshulkundaje · x · 2026-10-17
A retrospective on the Structure Track of the OpenADMET PXR challenge, where 100 teams blindly predicted ligand poses in the notoriously large, flexible binding pocket of the pregnane X receptor (PXR) across 184 unpublished crystal structures. Unintended PXR agonism upregulates CYP3A4 and is a major drug-discovery liability. Key lessons: co-folding dominates protein-ligand prediction but finding the right pose remains hard, and physics-based force fields still lead pose ranking. Part II of a series, following an earlier Activity Track retro on predicting PXR induction amid activity cliffs.
- 184 new crystal structures, 100 teams
- Co-folding architectures, fine-tuning, and force fields compared
- Authors: Maria Castellanos, Jon Swain, Hugo MacDermott-Opeskin
More from Research
- Contact-UAN: MIT's residual world model fixes humanoid sim-to-real with 6.5 minutes of data — kevin_zakka · 2026-10-17
- ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-17
- New paper asks how seriously to take AI welfare, with constraints from consciousness epistemology — birchlse · 2026-10-17
- GPT-6 Astra fastest-rising method on Papers with Code, 27 papers in 30 days — NielsRogge · 2026-10-17
- Embodied Astra tops RoboMME at 92.1% — beating humans by just keeping full visual history in context — hankyang94 · 2026-10-17
- Citations are oddly asymmetrical: unlimited times cited, but capped references — arjunrajlab · 2026-10-17