Ayla Schröder

My PhD project is part of the ERC starting grand "ORIGIN - Learning Isoform Fingerprints to Discover the Molecular Diversity of Life" (https://www.mls.ls.tum.de/en/compms/research/grants/origin-learning-isoform-fingerprints-to-discover-the-molecular-diversity-of-life/). The overarching goal of the ORIGIN project is to utilize a combination of features in mass spectrometry (MS) based proteomics data (fingerprints), that are acquired but currently unused, to improve and streamline peptide and protein identification as well as quantification from MS data. In the first phase of the ORIGIN project several deep learning models are developed, each predicting a particular MS peptide or protein feature from protein and peptide sequences. My contribution to this first work package is the creation of a Transformer-based model predicting peptide precursor charge state distributions (CSD) from peptide sequences. The challenge of this task lies in the fact, that the CSD of a peptide is influenced not only by the underlying peptide sequence, but also by a variety of experimental factors.

Find me on LinkedIn!