Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states
- 1Novartis Biomedical Research
Abstract
Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.
Related
- Impression-regularized finetuning enables small language models to extract cervical spine fractures from radiology reports
- AAV-DJ Enables Targeted Gene Modulation in Human Ovarian Cells
- Ultrasonic local anesthetic uncaging enables noninvasive, targeted, and transient knock-out of brain function
- Nanomaterial-genetics enables near-infrared-driven genetically targeted neuromodulation
- Targeted eDNA Survey Enables Consistent Detection of the Invasive Blue Crab in Trans‐Border Adriatic Coastal‐Marine Ecosystems
BibTeX
@misc{gorantla2026targeted,
title = {{Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states}},
author = {R. Gorantla and C. Schleberger and F. Sesterhenn},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.21.752570},
url = {https://www.biorxiv.org/content/10.64898/2026.09.21.752570v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states
AU - R. Gorantla
AU - C. Schleberger
AU - F. Sesterhenn
PY - 2026
DA - 2026/09/21
PB - bioRxiv
DO - 10.64898/2026.09.21.752570
UR - https://www.biorxiv.org/content/10.64898/2026.09.21.752570v1
AB - Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.
ER -