Maximilian T. Strauss

FastaLake constructs compact metaproteomic databases from sequence resources to improve peptide identification without requiring matched metagenomic sequencing.

This study uses AI-driven proteomics to identify molecular transitions in pancreatic cancer precursors, revealing early molecular changes in histologically normal tissue.

ProteoBench provides a centralized platform for comparing proteomics data analysis workflows, enabling benchmarking and community collaboration.

AlphaQuant improves proteoform regulation detection in bottom-up proteomics by using tree-based quantification and deep learning, revealing new patterns in mouse tissues.

AlphaDIA enables end-to-end transfer learning for feature-free proteomics, improving identification and quantification of post-translational modifications.

AlphaPept is an open-source framework for efficient processing of large MS-based proteomics datasets, achieving significant speed improvements using Python and machine learning.

The paper develops a high-throughput AP-MS method to map a comprehensive yeast interactome, doubling the number of proteins and tripling reliable interactions.

The paper introduces scDVP, a spatial single-cell proteomics method, and finds that half of the murine hepatocyte proteome varies spatially within liver tissue.

AlphaPeptDeep predicts peptide properties using deep learning, offering a modular framework that matches or exceeds existing tools for retention time, ion mobility, and fragment intensity prediction.

AlphaViz validates proteomics results by visualizing raw data and comparing with automated analysis outputs.

The paper determines the structural context of PTMs across the human proteome and identifies regulatory sites by analyzing their distribution in folded and disordered regions.

AlphaMap visually annotates proteomics data with sequence-specific knowledge, enabling integration of experimental results with UniProt annotations and proteolytic cleavage sites.

The paper measures CCS values for a million peptides across five organisms and develops a method to predict CCS for any peptide and organism.

This study uses urinary proteomics and machine learning to identify biomarkers for stratifying Parkinson's disease patients and LRRK2 mutation carriers.

AlphaTims enables fast access and visualization of high-dimensional LC-TIMS-QTOF proteomics data through efficient indexing and just-in-time compilation.