An official website of the United States government
Polymorphism in molecular crystals influences their properties and performance. Crystal structure prediction (CSP) can help explore the crystal structure landscape and discover potentially stable polymorphs computationally. We present a new version of the Genarris open-source code, which generates random molecular crystal structures in all space groups and applies physical constraints on intermolecular distances. The main new feature in Genarris 3.0 is the ``Rigid Press algorithm, which uses a regularized hard-sphere potential to compress the unit cell and achieve a maximally close-packed structure based on purely geometric considerations without performing any energy evaluations. In addition, Genarris 3.0 is interfaced with machine-learned interatomic potentials (MLIPs) to accelerate the exploration of the potential energy landscape. We present a new clustering and down-selection workflow that employs the MACE-OFF23(L) MLIPs to perform geometry optimization and energy ranking in the early stages. We use Genarris 3.0 to successfully predict the structure of six targets: aspirin, Target I and Target XXII from previous CSP blind tests, and the energetic materials HMX, CL-20, and DNI. We further analyze the performance of MACE-OFF23(L) compared to dispersion-inclusive density functional theory (DFT) for geometry relaxation and energy ranking. We find significant variability in the performance of MACE-OFF23(L) across chemically diverse targets with particularly poor performance for energetic materials, which is mitigated by our clustering and down-selection procedure. Genarris 3.0 can thus be used effectively to perform CSP and to generate molecular crystal datasets for training ML models.
more »
« less
This content will become publicly available on June 25, 2026
Efficient Molecular Crystal Structure Prediction and Stability Assessment with AIMNet2 Neural Network Potentials
Identifying thermodynamically stable crystal structures remains a key challenge in materials chemistry. Computational crystal structure prediction (CSP) workflows typically rank candidate structures by lattice energy to assess relative stability. Approaches using self-consistent first-principles calculations become prohibitively expensive, especially when millions of energy evaluations are required for complex molecular systems with many atoms per unit cell. Here, we provide a detailed analysis of our methodology and results from the seventh blind test of crystal structure prediction organized by the Cambridge Crystallographic Data Centre (CCDC). We present an approach that significantly accelerates CSP by training target-specific machine learned interatomic potentials (MLIPs). AIMNet2 MLIPs are trained on density functional theory (DFT) calculations of molecular clusters, herein referred to as n-mers. We demonstrate that potentials trained on gas phase dispersion-corrected DFT reference data of n-mers successfully extend to crystalline environments, accurately characterizing the CSP landscape and correctly ranking structures by relative stability. Our methodology effectively captures the underlying physics of thermodynamic crystal stability using only molecular cluster data, avoiding the need for expensive periodic calculations. The performance of target-specific AIMNet2 interatomic potentials is illustrated across diverse chemical systems relevant to pharmaceutical, optoelectronic, and agrochemical applications, demonstrating their promise as efficient alternatives to full DFT calculations for routine CSP tasks.
more »
« less
- Award ID(s):
- 2131944
- PAR ID:
- 10609850
- Publisher / Repository:
- ChemRxiv
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A seventh blind test of crystal structure prediction has been organized by the Cambridge Crystallographic Data Centre. The results are presented in two parts, with this second part focusing on methods for ranking crystal structures in order of stability. The exercise involved standardized sets of structures seeded from a range of structure generation methods. Participants from 22 groups applied several periodic DFT-D methods, machine learned potentials, force fields derived from empirical data or quantum chemical calculations, and various combinations of the above. In addition, one non-energy-based scoring function was used. Results showed that periodic DFT-D methods overall agreed with experimental data within expected error margins, while one machine learned model, applying system-specific AIMnet potentials, agreed with experiment in many cases demonstrating promise as an efficient alternative to DFT-based methods. For target XXXII, a consensus was reached across periodic DFT methods, with consistently high predicted energies of experimental forms relative to the global minimum (above 4 kJ mol−1at both low and ambient temperatures) suggesting a more stable polymorph is likely not yet observed. The calculation of free energies at ambient temperatures offered improvement of predictions only in some cases (for targets XXVII and XXXI). Several avenues for future research have been suggested, highlighting the need for greater efficiency considering the vast amounts of resources utilized in many cases.more » « less
-
Abstract We present machine‐learning interatomic potentials (MLIPs) for simulations of Si–C–O–H compounds. The MLIPs are constructed from moment tensor potentials (MTPs) and were trained to a library of configurations that included polysiloxane structures, hypothetical crystalline and amorphous SiCOH structures, and trajectories of Si–C–O–H systems obtained via ab initio molecular dynamic (aiMD) simulations at elevated temperatures. Passive, active, and hybrid learning strategies were implemented to develop the MLIPs. The MLIPs reproduce vibrational properties of polymers and SiCOH structures obtained from aiMD simulations, thus providing a tool to identify chemical units and distinct structural characteristics through their vibrational properties. Simulations of the polymer‐to‐ceramic transformation show the development of mixed tetrahedra in SiCO ceramics and align with experimental observations. Million‐atom simulations for several nanoseconds highlight the precipitation of graphitic nanosheets from a carbon‐rich SiCO precursor. Atomistic simulations with the MLIPs deliver details of chemical reaction mechanisms during the pyrolysis of polysiloxanes, including methane abstraction and Kumada‐like rearrangements that transform the siloxane backbone. While the MLIPs still leave room for systematic improvement, they deliver simulations with “density functional theory (DFT)‐like” quality at low and high temperatures.more » « less
-
The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spirit of this review is to help such researchers by serving as a practical, accessible guide to the state-of-the-art in MLIPs. This review paper covers a broad range of topics related to MLIPs, including (i) central aspects of how and why MLIPs are enablers of many exciting advancements in molecular modeling, (ii) the main underpinnings of different types of MLIPs, including their basic structure and formalism, (iii) the potentially transformative impact of universal MLIPs for both organic and inorganic systems, including an overview of the most recent advances, capabilities, downsides, and potential applications of this nascent class of MLIPs, (iv) a practical guide for estimating and understanding the execution speed of MLIPs, including guidance for users based on hardware availability, type of MLIP used, and prospective simulation size and time, (v) a manual for what MLIP a user should choose for a given application by considering hardware resources, speed requirements, energy and force accuracy requirements, as well as guidance for choosing pre-trained potentials or fitting a new potential from scratch, (vi) discussion around MLIP infrastructure, including sources of training data, pre-trained potentials, and hardware resources for training, (vii) summary of some key limitations of present MLIPs and current approaches to mitigate such limitations, including methods of including long-range interactions, handling magnetic systems, and treatment of excited states, and finally (viii) we finish with some more speculative thoughts on what the future holds for the development and application of MLIPs over the next 3–10+ years.more » « less
-
null (Ed.)The application of machine learning models and algorithms towards describing atomic interactions has been a major area of interest in materials simulations in recent years, as machine learning interatomic potentials (MLIPs) are seen as being more flexible and accurate than their classical potential counterparts. This increase in accuracy of MLIPs over classical potentials has come at the cost of significantly increased complexity, leading to higher computational costs and lower physical interpretability and spurring research into improving the speeds and interpretability of MLIPs. As an alternative, in this work we leverage “machine learning” fitting databases and advanced optimization algorithms to fit a class of spline-based classical potentials, showing that they can be systematically improved in order to achieve accuracies comparable to those of low-complexity MLIPs. These results demonstrate that high model complexities may not be strictly necessary in order to achieve near-DFT accuracy in interatomic potentials and suggest an alternative route towards sampling the high accuracy, low complexity region of model space by starting with forms that promote simpler and more interpretable inter- atomic potentials.more » « less
