A World Model of Molecular Organization Detects Cryptic Pockets from Apo Structure
- 1Eratos Therapeutics
Abstract
Cryptic pockets are druggable sites that are absent in a protein's resting structure and form only upon backbone rearrangement, posing a challenge for detection from static apo structures. Existing methods rely on generating open conformations through sampling or complex prediction, limiting applicability. Here we present a novel detector that reads cryptic pockets directly from a structural world-model latent representation of a single apo structure, without conformational sampling or external pocket finders. Evaluated on CryptoBench and CryptoBank datasets, the method localizes cryptic sites with top-1 accuracy as high as 0.848 and top-5 accuracy exceeding 0.93, and successfully recovers an allosteric site on held-out WRN helicase structures. The detector complements existing approaches and improves with training data scale. These findings suggest that structural world-model latents encode conformational flexibility, enabling effective cryptic pocket identification from apo structures alone, facilitating drug discovery on challenging targets. Benchmarked against the co-folding engine OpenDDE, the detector finds pockets directly rather than by first predicting a bound complex: on 190 targets held out of both training sets it recovers 119 sites OpenDDE misses, against 2 in the other direction, and at top-5 co-folding's recovered sites are a subset of ours. It runs on any structure from the apo coordinates alone, including the mmCIF-only entries all recent depositions carry, and its accuracy keeps climbing as the training corpus grows. The intended use is prospective cryptic-site nomination on the targets that sequence and static structure leave without a starting point.
Related
- What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
- Efficient detection of cryptic pockets on challenging drug targets using MD-free co-vibrational modes
- Quantum Sensing of Lithium Ions with Defect-Engineered Recognition Pockets in a TEMPO-Modified Covalent Organic Framework
- RangeFinder: Predicting Ligand Property Ranges from Protein Pockets
- Mechanism-Based Discovery of New TRIDs Targeting Ribosome Pockets
BibTeX
@misc{shihabi2026world,
title = {{A World Model of Molecular Organization Detects Cryptic Pockets from Apo Structure}},
author = {R. Shihabi and S. Taraman and B. Vaughan},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.21.752781},
url = {https://www.biorxiv.org/content/10.64898/2026.09.21.752781v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A World Model of Molecular Organization Detects Cryptic Pockets from Apo Structure
AU - R. Shihabi
AU - S. Taraman
AU - B. Vaughan
PY - 2026
DA - 2026/09/21
PB - bioRxiv
DO - 10.64898/2026.09.21.752781
UR - https://www.biorxiv.org/content/10.64898/2026.09.21.752781v1
AB - Cryptic pockets are druggable sites that are absent in a protein's resting structure and form only upon backbone rearrangement, posing a challenge for detection from static apo structures. Existing methods rely on generating open conformations through sampling or complex prediction, limiting applicability. Here we present a novel detector that reads cryptic pockets directly from a structural world-model latent representation of a single apo structure, without conformational sampling or external pocket finders. Evaluated on CryptoBench and CryptoBank datasets, the method localizes cryptic sites with top-1 accuracy as high as 0.848 and top-5 accuracy exceeding 0.93, and successfully recovers an allosteric site on held-out WRN helicase structures. The detector complements existing approaches and improves with training data scale. These findings suggest that structural world-model latents encode conformational flexibility, enabling effective cryptic pocket identification from apo structures alone, facilitating drug discovery on challenging targets. Benchmarked against the co-folding engine OpenDDE, the detector finds pockets directly rather than by first predicting a bound complex: on 190 targets held out of both training sets it recovers 119 sites OpenDDE misses, against 2 in the other direction, and at top-5 co-folding's recovered sites are a subset of ours. It runs on any structure from the apo coordinates alone, including the mmCIF-only entries all recent depositions carry, and its accuracy keeps climbing as the training corpus grows. The intended use is prospective cryptic-site nomination on the targets that sequence and static structure leave without a starting point.
ER -