Speaker
Description
With the upgrade from SLS to SLS 2.0, a fourth-generation synchrotron, the macromolecular crystallography (MX) beamlines have undergone significant hardware and software enhancements, enabling fully automated data collection workflows. By leveraging the on-the-fly data processing capabilities of Jungfraujoch (Leonarski, F. et al., 2023), together with integrated machine learning and artificial intelligence, automation now spans the entire experimental pipeline. This includes robotic sample exchange, machine learning assisted automated loop centering, dose estimation, diffraction data acquisition, and data processing. A real time diffraction viewer (Jungfraujoch Viewer) was developed for monitoring data collection on the fly. Alongside optimizing established beamline operations, we are exploring new modes of interaction between users, samples, and instrumentation to improve consistency and efficiency.
This presentation will describe the current beamline configuration and software suites (Aare Suite). Uses Beamline and Experiment Control (BEC) (Wakonig, K., et al. 2024) as a foundation, our team updated the graphical user interface (AareGUI) and data acquisition workflow (AareDAQ), developed database (AareDB) and investigated different ways of working with fine tuning YOLO models. In addition, we will outline our roadmap for further incorporating AI into the local contact workflow, e.g. automatic beamline recovery, ideally ensuring more restful nights for our local contacts.
- F. Leonarski, J. Nan, Z. Matěj, et al., IUCrJ, 10, 729–737 (2023). https://doi.org10.1107/S2052252523008618
- Wakonig, K., Appel, C., Ashton, A., Augustin, S., Holler, M., Usov, I., Wyzula, J. & Yao, X. (marie) (2024). Proceedings of ICALEPCS2023 https://doi.org/10.18429/JACOW-ICALEPCS2023-MO2AO02.
