Maximilian P.-P. Kovar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maximilian P.-P. Kovar has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Esther Heid
Institute of Materials Chemistry, TU Wien, A-1060 Vienna, Austria
2 shared publications - Johannes Karwounopoulos
Institute of Materials Chemistry, TU Wien, A-1060 Vienna, Austria
2 shared publications Anton Zamyatin
Institute of Materials Chemistry, TU Wien, A-1060 Vienna, Austria
1 shared publication- Christian Schröder
University of Vienna, Faculty of Chemistry, Department of Computational Biological Chemistry, 1090 Vienna, Austria
1 shared publication - Dennis Svatunek
Institute of Applied Synthetic Chemistry, TU Wien, Getreidemarkt 9, 1060 Vienna, Austria
1 shared publication Florian Joerg
Faculty of Chemistry, Department of Computational Biological Chemistry, University of Vienna, Währinger Straße 17, Vienna 1090, Austria
1 shared publication
Latest Publications
- Open Access
- 14 October 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (10) , 4499-4511
moTSart: accelerating automated transition state search with generative models in a low-data regime
We introduce moTSart, a framework for generative AI accelerated, automated transition state search.
- 14 October 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (10) , 4499-4511
Open AccessmoTSart: accelerating automated transition state search with generative models in a low-data regime
We introduce moTSart, a framework for generative AI accelerated, automated transition state search.
- Open Access
- 8 October 2025
- Published by American Chemical Society (ACS) in ChemRxiv
GoFlow: Efficient Transition State Geometry Prediction with Flow Matching and E(3)-Equivariant Neural Networks
Transition state (TS) geometries of chemical reactions are key to understanding reaction mechanisms and estimating kinetic properties. Inferring these directly from 2D reaction graphs offers chemists a powerful tool for rapid and accessible reaction analysis. Quantum chemical methods for computing TSs are computationally intensive and often infeasible for larger molecular systems. Recently, deep learning–based diffusion models have shown promise in generating TSs from 2D reaction graphs for single-step reactions. However, framing TS generation as a diffusion process, by design, requires a prohibitively large number of sampling steps during inference. Here we show that modeling TS generation as an optimal transport flow problem, solved via E(3)-equivariant flow matching with geometric tensor networks, achieves over a hundredfold speedup in inference while improving geometric accuracy compared to the state-of-the-art. This breakthrough increase in sampling efficiency and predictive accuracy enables the practical use of deep learning-based TS generators in high-throughput settings for larger and more complex chemical systems. Our method, GoFlow, thus represents a significant methodological advancement in machine learning-based TS generation, bringing it closer to widespread use in computational chemistry workflows.
- 8 October 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessGoFlow: Efficient Transition State Geometry Prediction with Flow Matching and E(3)-Equivariant Neural Networks
Transition state (TS) geometries of chemical reactions are key to understanding reaction mechanisms and estimating kinetic properties. Inferring these directly from 2D reaction graphs offers chemists a powerful tool for rapid and accessible reaction analysis. Quantum chemical methods for computing TSs are computationally intensive and often infeasible for larger molecular systems. Recently, deep learning–based diffusion models have shown promise in generating TSs from 2D reaction graphs for single-step reactions. However, framing TS generation as a diffusion process, by design, requires a prohibitively large number of sampling steps during inference. Here we show that modeling TS generation as an optimal transport flow problem, solved via E(3)-equivariant flow matching with geometric tensor networks, achieves over a hundredfold speedup in inference while improving geometric accuracy compared to the state-of-the-art. This breakthrough increase in sampling efficiency and predictive accuracy enables the practical use of deep learning-based TS generators in high-throughput settings for larger and more complex chemical systems. Our method, GoFlow, thus represents a significant methodological advancement in machine learning-based TS generation, bringing it closer to widespread use in computational chemistry workflows.
- Open Access
- 1 April 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (14) , 3416-3426
Updates to Protex for Simulating Proton Transfers in an Ionic Liquid
The Python-based program Protex was initially developed for simulating proton transfers in a pure protic ionic liquid via polarizable molecular dynamics simulations. This method employs a single topology approach wherein deprotonated species retain a dummy atom, which is transformed into a real hydrogen atom during the protonation process. In this work, we extended Protex to include more intricate systems and to facilitate the simulation of the Grotthuss mechanism to enhance alignment with the empirical findings. The handling of proton transfer events within Protex was further refined for increased flexibility. In the original model, each deprotonated molecule contained a single dummy atom connected to the hydrogen acceptor atom. This model posed limitations for molecules with multiple atoms that could undergo protonation. To mitigate this issue, Protex was extended to execute a proton transfer when one of these potential atoms was within a suitable proximity for the transfer event. For the purpose of maintaining simplicity, Protex continues to utilize only a single dummy atom per deprotonated molecule. Another new feature pertains to the determination of the eligibility for a proton transfer event. A range of acceptable distances can now be defined within which the transfer probability is gradually turned off. These modifications allow for a more nuanced approach to simulating proton transfer events, offering greater accuracy and control of the modeling process.
- 1 April 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (14) , 3416-3426
Open AccessUpdates to Protex for Simulating Proton Transfers in an Ionic Liquid
The Python-based program Protex was initially developed for simulating proton transfers in a pure protic ionic liquid via polarizable molecular dynamics simulations. This method employs a single topology approach wherein deprotonated species retain a dummy atom, which is transformed into a real hydrogen atom during the protonation process. In this work, we extended Protex to include more intricate systems and to facilitate the simulation of the Grotthuss mechanism to enhance alignment with the empirical findings. The handling of proton transfer events within Protex was further refined for increased flexibility. In the original model, each deprotonated molecule contained a single dummy atom connected to the hydrogen acceptor atom. This model posed limitations for molecules with multiple atoms that could undergo protonation. To mitigate this issue, Protex was extended to execute a proton transfer when one of these potential atoms was within a suitable proximity for the transfer event. For the purpose of maintaining simplicity, Protex continues to utilize only a single dummy atom per deprotonated molecule. Another new feature pertains to the determination of the eligibility for a proton transfer event. A range of acceptable distances can now be defined within which the transfer probability is gradually turned off. These modifications allow for a more nuanced approach to simulating proton transfer events, offering greater accuracy and control of the modeling process.