Samantha N Fischer

The paper develops a proteomics-based machine learning workflow to identify cell-type-specific protein complexes in mouse embryonic stem cells, revealing 3,986 complexes and 1,388 unique interactions specific to mESC.

DirectContacts2 identifies direct protein interactions using mass spectrometry data and machine learning, improving accuracy over existing resources and providing structural models for disease-related complexes.

Machine learning integration of over 25,000 mass spectrometry experiments yields 15,326 human protein complexes covering 13,769 proteins, plus 511 AlphaFold-derived mutually exclusive subunit pairs.