ProteomicsML provides ready-made datasets for machine learning models accompanied by tutorials on how to work with even the most complex data types in the field of proteomics. The resource is set up to evolve together with the field, and we welcome everyone to contribute to the project by adding new datasets and accompanying notebooks.

ProteomicsML was set up as a joint effort of SDU, CompOmics, LUMC, PeptideAtlas, NIST, PRIDE, and MSAID. We believe that ProteomicsML is solid step forward for the field towards more open and reproducible science!