Abstract
Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-scarce biological contexts. However, existing generative approaches to atomistic modeling remain highly specialized to scientific disciplines (chemistry vs. biology) or do not leverage both high-volume organic (molecule) and inorganic (material) data for general-purpose pretraining. To this end, we introduce Zatom-2, an atomistic generative model pretrained on approximately five million structures from the OMol25 and OMat24 electronic structure datasets. Zatom-2 features a multiscale Transformer architecture coupled with conditional flow matching that supports force conditioning and foundational pretraining tasks such as generation, structure prediction, and prediction of molecular and material energies and forces. Empirically, Zatom-2 achieves better molecular distribution fidelity than Zatom-1 and achieves strong performance on existing molecule and material generation benchmarks. Zatom-2 demonstrates the ability to control sample generation across low- and high-force regimes, and enhances protein generation in a low-data setting through joint generative-predictive pretraining and transfer learning, increasing protein backbone designability in a length extrapolation setting from 67.8% without pretraining to 74.8% after finetuning on 2,000 protein domains.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Cretu, M., Abrudan, A., Panescu, A., Perez, T., Anand, R., Erichson, N. B., Mahoney, M. W., Blau, S., Jacobson, J., Gómez-Bombarelli, R., Ying, R., Knowles, T., Liò, P., & Morehead, A. (2026). Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains. https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains
MLA 9
Cretu, Miruna, et al. "Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains." https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains.
Chicago (author–date)
Cretu, Miruna, Alex Abrudan, Antonia Panescu, Tynan Perez, Rishabh Anand, N. Benjamin Erichson, Michael W. Mahoney, Samuel Blau, Joseph Jacobson, Rafael Gómez-Bombarelli, Rex Ying, Tuomas Knowles, Pietro Liò, and Alex Morehead. 2026. "Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains." https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains.
Harvard
Cretu, M., Abrudan, A., Panescu, A., Perez, T., Anand, R., Erichson, N. B., Mahoney, M. W., Blau, S., Jacobson, J., Gómez-Bombarelli, R., Ying, R., Knowles, T., Liò, P. and Morehead, A. (2026) 'Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains', Available at: https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains.
Vancouver
Cretu M, Abrudan A, Panescu A, Perez T, Anand R, Erichson NB, et al. Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains. https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains
IEEE
M. Cretu, A. Abrudan, A. Panescu, T. Perez, R. Anand, N. B. Erichson, M. W. Mahoney, S. Blau, J. Jacobson, R. Gómez-Bombarelli, R. Ying, T. Knowles, P. Liò, and A. Morehead, "Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains," https://omanscience.com/en/articles/zatom-2-multitask-pretraining-on-atomistic-data-for-generative-modeling-across-domains.