Stefan Schmid

Last Name

Schmid

First Name

Stefan

ORCID

0000-0002-0965-0208

Organisational unit

09781 - Jorner, Kjell / Jorner, Kjell

Show all metadata

Search Results

Publications1 - 5 of 5

Self-Driving Laboratories for Chemistry and Materials Science
Tom, Gary; Schmid, Stefan; Baird, Sterling G.; et al. (2024)
Chemical Reviews ~ 124
Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.
Educating Future Chemists in the Age of AI: A Digital Chemistry Course
Jacot-Descombes, Lauriane; Schmid, Stefan; Jorner, Kjell (2025)
Chimia
Artificial intelligence (AI) and machine learning (ML) are developing fast and are increasingly adopted in both chemical industry and academic research. With the projected role such tools will play in the future, for every chemist, these developments call for a fundamental and sound education for future generations of scientists in these areas. In this perspective, we describe the development of the course Digital Chemistry at ETH Zurich, which addresses these topics. In particular, we outline our approach to teaching ML and its applications in chemistry. We especially emphasize that the skills of understanding, applying and critically assessing ML models will be fundamental for future chemists. We hope that this article will serve as inspiration for educators in this field and help to enhance the teaching in this area of future significance.
Rapid Generation of Transition-State Conformer Ensembles via Constrained Distance Geometry
Schmid, Stefan; Seng, Henrik; Kläy, Thibault; et al. (2026)
Journal of Chemical Information and Modeling
Consideration of transition-state (TS) conformer ensembles is required to accurately model a reaction, and thus plays a key role in computational catalyst design. While CREST and GOAT are established methods for TS conformer ensemble generation, the associated computational cost remains a major bottleneck in computational chemistry pipelines, including for the generation of large machine learning data sets for catalyst design. To this end, we present racerTS (RApid Conformer Ensembles with RDKit for Transition States), a method for efficient TS conformer ensemble generation. In this work, we describe the algorithm behind racerTS, which is based on constrained distance geometry. To benchmark the performance of racerTS against CREST and GOAT, we created conformer ensembles for transition states of 20 diverse reactions. To assess the utility of each conformer generator in computational chemistry workflows, we optimize selected low-energy and diverse conformers at the DFT level. We use the generated conformer ensembles and the results of this pipeline to assess conformer generators according to the following metrics: computational cost, exhaustiveness, validity, and accuracy in low-energy regions. Considering the generated ensembles, we find that racerTS covers the conformer space similarly to CREST and slightly less comprehensively than GOAT, while the validity of the DFT-optimized TSs is better and the accuracy in the low-energy region is sufficient for computational chemistry applications (median error of 0.17 kcal/mol). Remarkably, racerTS achieves these results with a significant reduction in required wall-time. Our results demonstrate that racerTS is a highly efficient TS conformer ensemble generator, allowing for rapid TS conformer sampling in computational chemistry pipelines. Additionally, racerTS paves the way to create meaningful TS data sets to advance machine learning methods for the discovery of novel and sustainable catalysts.
Catalysing (organo-)catalysis: Trends in the application of machine learning to enantioselective organocatalysis
Schmid, Stefan; Schlosser, Leon; Glorius, Frank; et al. (2024)
Beilstein Journal of Organic Chemistry
Organocatalysis has established itself as a third pillar of homogeneous catalysis, besides transition metal catalysis and biocatalysis, as its use for enantioselective reactions has gathered significant interest over the last decades. Concurrent to this development, machine learning (ML) has been increasingly applied in the chemical domain to efficiently uncover hidden patterns in data and accelerate scientific discovery. While the uptake of ML in organocatalysis has been comparably slow, the last two decades have showed an increased interest from the community. This review gives an overview of the work in the field of ML in organocatalysis. The review starts by giving a short primer on ML for experimental chemists, before discussing its application for predicting the selectivity of organocatalytic transformations. Subsequently, we review ML employed for privileged catalysts, before focusing on its application for catalyst and reaction design. Concluding, we give our view on current challenges and future directions for this field, drawing inspiration from the application of ML to other scientific domains.
Intervertebral disc deformation in the lower lumbar spine during object lifting measured in vivo using indwelling bone pins
Schmid, Stefan; Kramers-de Quervain, Inès; Baumgartner, Walter (2024)
Journal of Biomechanics
Object lifting is often categorized into squat and stoop techniques, with the former believed to protect the back by maintaining a neutral spine, and the latter considered harmful due to spinal flexion. Despite the widespread promotion of these beliefs, there is no evidence to support such dichotomy, as spinal flexion is not conclusively linked to low back pain. This study aimed to investigate intervertebral disc deformation in the lower lumbar spine during squat and stoop lifting using indwelling bone pins. Five healthy males underwent insertion of Kirschner wires into the L3, L4, and L5 spinous processes, followed by biomechanical data collection using magnetic and optical tracking systems during upright standing, isolated flexion/extension, and object lifting with both squat and stoop techniques. Except for one subject, stoop lifting resulted in up to 90 % greater disc wedging compared to squat lifting, with a significant difference at L4/L5 (p = 0.042). The anterior annulus fibrosus experienced 10 % to 40 % more compression during stoop lifting, but no significant differences were found in posterior annulus fibrosus expansion between techniques. Lever arms were about 35 % longer during stoop compared to squat lifting. These results indicate that even though stoop lifting generally led to greater disc deformation, significant deformation was also observed during squat lifting, challenging the notion of maintaining a neutral spine with this technique. Moreover, the considerable variability observed among participants raises concerns about the suitability of current one-size-fits-all lifting guidelines.

Publications1 - 5 of 5

Stefan Schmid

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results