moTSart: accelerating automated transition state search with generative models in a low-data regime
Leonard Galustian, Johannes Karwounopoulos, Tori Demuth, Jasper De Landsheere, Konstantin Mark, Maximilian P.-P. Kovar, Anton Zamyatin, Dennis Svatunek, Esther Heid · 2026
Read moTSart: accelerating automated transition state search with generative models in a low-data regime by Leonard Galustian, Johannes Karwounopoulos, Tori Demuth, Jasper De Landsheere, Konstantin Mark, Maximilian P.-P. Kovar, Anton Zamyatin, Dennis Svatunek, Esther Heid (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13592236.txt.
Description
Leonard Galustian and co-authors present a 2026 paper on a generative AI pipeline that speeds the hunt for transition states, the peak structures that set how fast a reaction runs. Finding them is slow expert work. Their system drafts candidate shapes, then checks them with physics based tools.
A test on click chemistry showed the learning loop cutting needed refinement steps by nearly two fifths after seeing only a few hundred reactions. The more reactions it processes, the fewer costly quantum checks each new one needs. The authors frame it as a step toward self driving exploration of reaction space, with scarce data no longer a hard wall.
Catalog record
| CREATOR | Leonard Galustian, Johannes Karwounopoulos, Tori Demuth, Jasper De Landsheere, Konstantin Mark, Maximilian P.-P. Kovar, Anton Zamyatin, Dennis Svatunek, Esther Heid |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |