AI simulations in chemical compound space

I will present our methods and software tools for speeding up simulations in chemical compound space with AI and demonstrate their applications. The methods include the general-purpose, artificial intelligence-enhanced quantum mechanical method 1 (AIQM1),[1] which for many properties approaches the accuracy of golden-standard, traditional CCSD(T)/CBS approach while being orders of magnitude faster than DFT. This method can be applied for different compounds without retraining. We applied it to calculate enthalpies of formation[2] and reaction[1] with chemical accuracy as well as to perform accurate molecular dynamics and IR spectra simulations.[3] We also used AIQM1 to elucidate the ground- and excited-state properties of large polyparaphenylene nanolassos.[4] AIQM1 along with many other methods such as a host of ML interatomic potentials are implemented in our MLatom program package and Python library for user-friendly atomistic machine learning simulations which can be run online using our MLatom@XACS cloud-based service.[5]

Figure 1. AIQM1 is both faster and more accurate than DFT for large molecules. Adapted from Ref. [5].

1. P. Zheng, R. Zubatyuk, W. Wu, O. Isayev, P. O. Dral, Nat. Commun. 2021, 12, 7022.
2. P. Zheng, W. Yang, W. Wu, O. Isayev, P. O. Dral, J. Phys. Chem. Lett. 2022, 13, 3479–3491.
3. L. Zhang, Y.-F. Hou, F. Ge, P. O. Dral, Phys. Chem. Chem. Phys. 2023, 25, 23467–23476.
4. T. A. Schaub, A. Zieleniewska, R. Kaur, M. Minameyer, W. Yang, C. M. Schüßlbauer, L. Zhang, M. Freiberger, L. N. Zakharov, T. Drewello, P. O. Dral, D. Guldi, R. Jasti, Chem. Eur. J. 2023, 29, e202300668.
5. P. O. Dral, F. Ge, Y.-F. Hou, P. Zheng, Y. Chen, M. Barbatti, O. Isayev, C. Wang, B.-X. Xue, M. Pinheiro Jr, Y. Su, Y. Dai, Y. Chen, S. Zhang, L. Zhang, A. Ullah, Q. Zhang, Y. Ou, J. Chem. Theory Comput. 2024, , DOI: 10.1021/acs.jctc.3c01203. MLatom.com @ XACScloud.com.