active · EUR Spectrum · 3iA Côte d'Azur
Deep reinforcement learning for MS data acquisition
Offline reinforcement learning that dynamically adjusts mass-spectrometer configurations in real time to maximise the quality and coverage of fragmentation spectra.
Madina Bekbergenova's doctoral research optimises real-time mass-spectrometry data acquisition. By employing offline reinforcement learning to dynamically adjust instrument configurations, the project maximises the quality and coverage of fragmentation spectra — promising to uncover metabolites currently overlooked. Part of an international PhD program with Prof. Wout Bittremieux (University of Antwerp), funded by EUR Spectrum of Université Côte d'Azur and 3iA Côte d'Azur (€120k, 2024–2027).