Pearl: A Foundation Model for Placing Every Atom in the Right Location
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908618225352704 |
|---|---|
| author | Genesis Research Team Dobles, Alejandro Jovic, Nina Leidal, Kenneth Murugan, Pranav Williams, David C. Wulsin, Drausin Gruver, Nate Ji, Christina X. Pruegsanusak, Korrawat Scarpellini, Gianluca Sharma, Ansh Swiderski, Wojciech Bootsma, Andrea Bowen, Richard Strong Chen, Charlotte Chen, Jamin Dämgen, Marc André DiFrancesco, Benjamin Fishman, J. D. Ivanova, Alla Kagin, Zach Li-Bland, David Liu, Zuli Morozov, Igor Ouyang-Zhang, Jeffrey Pickard IV, Frank C. Shah, Kushal S. Shor, Ben da Silva, Gabriel Monteiro Tal, Roy Tessmer, Maxx Tilbury, Carl Vetcher, Cyr Zeng, Daniel Al-Shedivat, Maruan Faust, Aleksandra Feinberg, Evan N. LeVine, Michael V. Pan, Matteus |
| author_facet | Genesis Research Team Dobles, Alejandro Jovic, Nina Leidal, Kenneth Murugan, Pranav Williams, David C. Wulsin, Drausin Gruver, Nate Ji, Christina X. Pruegsanusak, Korrawat Scarpellini, Gianluca Sharma, Ansh Swiderski, Wojciech Bootsma, Andrea Bowen, Richard Strong Chen, Charlotte Chen, Jamin Dämgen, Marc André DiFrancesco, Benjamin Fishman, J. D. Ivanova, Alla Kagin, Zach Li-Bland, David Liu, Zuli Morozov, Igor Ouyang-Zhang, Jeffrey Pickard IV, Frank C. Shah, Kushal S. Shor, Ben da Silva, Gabriel Monteiro Tal, Roy Tessmer, Maxx Tilbury, Carl Vetcher, Cyr Zeng, Daniel Al-Shedivat, Maruan Faust, Aleksandra Feinberg, Evan N. LeVine, Michael V. Pan, Matteus |
| contents | Accurately predicting the three-dimensional structures of protein-ligand complexes remains a fundamental challenge in computational drug discovery that limits the pace and success of therapeutic design. Deep learning methods have recently shown strong potential as structural prediction tools, achieving promising accuracy across diverse biomolecular systems. However, their performance and utility are constrained by scarce experimental data, inefficient architectures, physically invalid poses, and the limited ability to exploit auxiliary information available at inference. To address these issues, we introduce Pearl (Placing Every Atom in the Right Location), a foundation model for protein-ligand cofolding at scale. Pearl addresses these challenges with three key innovations: (1) training recipes that include large-scale synthetic data to overcome data scarcity; (2) architectures that incorporate an SO(3)-equivariant diffusion module to inherently respect 3D rotational symmetries, improving generalization and sample efficiency, and (3) controllable inference, including a generalized multi-chain templating system supporting both protein and non-polymeric components as well as dual unconditional/conditional modes. Pearl establishes a new state-of-the-art performance in protein-ligand cofolding. On the key metric of generating accurate (RMSD < 2 Å) and physically valid poses, Pearl surpasses AlphaFold 3 and other open source baselines on the public Runs N' Poses and PoseBusters benchmarks, delivering 14.5% and 14.2% improvements, respectively, over the next best model. In the pocket-conditional cofolding regime, Pearl delivers $3.6\times$ improvement on a proprietary set of challenging, real-world drug targets at the more rigorous RMSD < 1 Å threshold. Finally, we demonstrate that model performance correlates directly with synthetic dataset size used in training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24670 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pearl: A Foundation Model for Placing Every Atom in the Right Location Genesis Research Team Dobles, Alejandro Jovic, Nina Leidal, Kenneth Murugan, Pranav Williams, David C. Wulsin, Drausin Gruver, Nate Ji, Christina X. Pruegsanusak, Korrawat Scarpellini, Gianluca Sharma, Ansh Swiderski, Wojciech Bootsma, Andrea Bowen, Richard Strong Chen, Charlotte Chen, Jamin Dämgen, Marc André DiFrancesco, Benjamin Fishman, J. D. Ivanova, Alla Kagin, Zach Li-Bland, David Liu, Zuli Morozov, Igor Ouyang-Zhang, Jeffrey Pickard IV, Frank C. Shah, Kushal S. Shor, Ben da Silva, Gabriel Monteiro Tal, Roy Tessmer, Maxx Tilbury, Carl Vetcher, Cyr Zeng, Daniel Al-Shedivat, Maruan Faust, Aleksandra Feinberg, Evan N. LeVine, Michael V. Pan, Matteus Machine Learning Quantitative Methods Accurately predicting the three-dimensional structures of protein-ligand complexes remains a fundamental challenge in computational drug discovery that limits the pace and success of therapeutic design. Deep learning methods have recently shown strong potential as structural prediction tools, achieving promising accuracy across diverse biomolecular systems. However, their performance and utility are constrained by scarce experimental data, inefficient architectures, physically invalid poses, and the limited ability to exploit auxiliary information available at inference. To address these issues, we introduce Pearl (Placing Every Atom in the Right Location), a foundation model for protein-ligand cofolding at scale. Pearl addresses these challenges with three key innovations: (1) training recipes that include large-scale synthetic data to overcome data scarcity; (2) architectures that incorporate an SO(3)-equivariant diffusion module to inherently respect 3D rotational symmetries, improving generalization and sample efficiency, and (3) controllable inference, including a generalized multi-chain templating system supporting both protein and non-polymeric components as well as dual unconditional/conditional modes. Pearl establishes a new state-of-the-art performance in protein-ligand cofolding. On the key metric of generating accurate (RMSD < 2 Å) and physically valid poses, Pearl surpasses AlphaFold 3 and other open source baselines on the public Runs N' Poses and PoseBusters benchmarks, delivering 14.5% and 14.2% improvements, respectively, over the next best model. In the pocket-conditional cofolding regime, Pearl delivers $3.6\times$ improvement on a proprietary set of challenging, real-world drug targets at the more rigorous RMSD < 1 Å threshold. Finally, we demonstrate that model performance correlates directly with synthetic dataset size used in training. |
| title | Pearl: A Foundation Model for Placing Every Atom in the Right Location |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2510.24670 |