FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
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_ | 1866918113752121344 |
|---|---|
| author | Gharakhanyan, Vahe Yang, Yi Barroso-Luque, Luis Shuaibi, Muhammed Levine, Daniel S. Michel, Kyle Bernat, Viachaslau Dzamba, Misko Fu, Xiang Gao, Meng Liu, Xingyu Noori, Keian Purvis, Lafe J. Rao, Tingling Wood, Brandon M. Rizvi, Ammar Uyttendaele, Matt Ouderkirk, Andrew J. Daraio, Chiara Zitnick, C. Lawrence Boromand, Arman Marom, Noa Ulissi, Zachary W. Sriram, Anuroop |
| author_facet | Gharakhanyan, Vahe Yang, Yi Barroso-Luque, Luis Shuaibi, Muhammed Levine, Daniel S. Michel, Kyle Bernat, Viachaslau Dzamba, Misko Fu, Xiang Gao, Meng Liu, Xingyu Noori, Keian Purvis, Lafe J. Rao, Tingling Wood, Brandon M. Rizvi, Ammar Uyttendaele, Matt Ouderkirk, Andrew J. Daraio, Chiara Zitnick, C. Lawrence Boromand, Arman Marom, Noa Ulissi, Zachary W. Sriram, Anuroop |
| contents | Crystal Structure Prediction (CSP) of molecular crystals plays a central role in applications, such as pharmaceuticals and organic electronics. CSP is challenging and computationally expensive due to the need to explore a large search space with sufficient accuracy to capture energy differences of a few kJ/mol between polymorphs. Dispersion-inclusive density functional theory (DFT) provides the required accuracy but its computational cost is impractical for a large number of putative structures. We introduce FastCSP, an open-source, high-throughput CSP workflow based on machine learning interatomic potentials (MLIPs). FastCSP combines random structure generation using Genarris 3.0 with geometry relaxation and free energy calculations powered entirely by the Universal Model for Atoms (UMA) MLIP. We benchmark FastCSP on a curated set of 28 mostly rigid molecules, demonstrating that our workflow consistently generates known experimental structures and ranks them within 5 kJ/mol per molecule of the global minimum. Our results demonstrate that universal MLIPs can be used across diverse compounds without requiring system-specific tuning. Moreover, the speed and accuracy afforded by UMA eliminate the need for classical force fields in the early stages of CSP and for final re-ranking with DFT. The open-source release of the entire FastCSP workflow significantly lowers the barrier to accessing CSP. CSP results for a single system can be obtained within hours on tens of modern GPUs, making high-throughput crystal structure prediction feasible for a broad range of scientific applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02641 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms Gharakhanyan, Vahe Yang, Yi Barroso-Luque, Luis Shuaibi, Muhammed Levine, Daniel S. Michel, Kyle Bernat, Viachaslau Dzamba, Misko Fu, Xiang Gao, Meng Liu, Xingyu Noori, Keian Purvis, Lafe J. Rao, Tingling Wood, Brandon M. Rizvi, Ammar Uyttendaele, Matt Ouderkirk, Andrew J. Daraio, Chiara Zitnick, C. Lawrence Boromand, Arman Marom, Noa Ulissi, Zachary W. Sriram, Anuroop Chemical Physics Machine Learning Crystal Structure Prediction (CSP) of molecular crystals plays a central role in applications, such as pharmaceuticals and organic electronics. CSP is challenging and computationally expensive due to the need to explore a large search space with sufficient accuracy to capture energy differences of a few kJ/mol between polymorphs. Dispersion-inclusive density functional theory (DFT) provides the required accuracy but its computational cost is impractical for a large number of putative structures. We introduce FastCSP, an open-source, high-throughput CSP workflow based on machine learning interatomic potentials (MLIPs). FastCSP combines random structure generation using Genarris 3.0 with geometry relaxation and free energy calculations powered entirely by the Universal Model for Atoms (UMA) MLIP. We benchmark FastCSP on a curated set of 28 mostly rigid molecules, demonstrating that our workflow consistently generates known experimental structures and ranks them within 5 kJ/mol per molecule of the global minimum. Our results demonstrate that universal MLIPs can be used across diverse compounds without requiring system-specific tuning. Moreover, the speed and accuracy afforded by UMA eliminate the need for classical force fields in the early stages of CSP and for final re-ranking with DFT. The open-source release of the entire FastCSP workflow significantly lowers the barrier to accessing CSP. CSP results for a single system can be obtained within hours on tens of modern GPUs, making high-throughput crystal structure prediction feasible for a broad range of scientific applications. |
| title | FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms |
| topic | Chemical Physics Machine Learning |
| url | https://arxiv.org/abs/2508.02641 |