@article{tarricone_end-to-end_2026,
    author = {Lorenzo Tarricone  and Stefan P. Schmid  and Vera Jost  and Marius Lutz  and Gisbert Schneider  and Georg Wuitschik  and Kjell Jorner },
    title = {End-to-End Conditions Generation for High-Throughput Experimentation under Practical Constraints},
    journal = {ChemRxiv},
    volume = {2026},
    number = {0624},
    pages = {},
    year = {2026},
    doi = {10.26434/chemrxiv.15005138/v1},
    URL = {https://chemrxiv.org/doi/abs/10.26434/chemrxiv.15005138/v1},
    eprint = {https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15005138/v1},
    abstract = {C–N and C–C cross-coupling reactions are central to medicinal chemistry, but selecting effective conditions remains a major bottleneck because outcomes depend on strongly coupled choices of catalyst/ligand, base, solvent, and additives. In high-throughput experimentation (HTE), these choices must also be translated into concrete plate layouts that obey practical constraints for which components can be combined together. Here we present an end-to-end machine-learning workflow that connects data curation, condition generation, and constraint-aware plate design. We curate and share two industrial HTE datasets for Buchwald–Hartwig amination and Suzuki–Miyaura coupling that include a substantial number of reactions with negative outcomes. Using these data, we develop a conditional variational autoencoder (cVAE) that generates candidate conditions while explicitly modelling both productive and unproductive regions of condition space, and we introduce a Frequency Chain baseline that is competitive under limited sampling budgets. The cVAE outperforms the baselines for low-to-moderate (below 100) sampled conditions, with improvements compared to previous cVAEs in six of eight tested metrics on the Buchwald–Hartwig reaction and one of eight on the Suzuki–Miyaura reaction. In single-transformation case studies, moving from a zero-shot to a few-shot regime improves key component recovery from 33\% to 75\% (Buchwald–Hartwig) and from 25\% to 67\% (Suzuki–Miyaura). Finally, an integer linear programming (ILP)-based plate design algorithm converts model predictions into executable HTE plates, matching or outperforming greedy positive-condition coverage while reducing predicted negative wells by 6.1 on average across ten evaluated transformations. Our integrated, data-driven plate design that combines machine learning predictions and lab automation has the potential to enable closed-loop optimisation of reaction conditions for rapid hit-to-lead optimisation.}
}