Interest in the use of machine learning for peptide fragmentation spectrum prediction has been strongly on the rise over the past year s, especiall y for applications in challenging proteomics identification workflows such as immunopeptidomics and the full-proteome identification of data independent acquisition spectra. Since its inception, the MS 2 PIP peptide spectrum predictor has been widely used f or v arious do wnstream applications, mostl y thanks to its accuracy, ease-of-use, and broad applicability. We here present a thoroughly updated version of the MS 2 PIP web server, which includes new and more performant prediction models for both trypticand non-tryptic peptides, for immunopeptides, and for CID-fragmented TMT-labeled peptides. Additionall y, we ha ve also added ne w functionality to greatl y facilitate the generation of proteome-wide predicted spectral libraries, requiring only a FASTA protein file as input. These libraries also include retention time predictions from DeepLC. Moreover, we now pr o vide pre-b uilt and read y-to-do wnload spectral libraries f or v arious model organisms in multiple DIAcompatible spectral library formats. Besides upgrading the back-end models, the user experience on the MS 2 PIP web server is thus also greatly enhanced, extending its applicability to new domains, including immunopeptidomics and MS3-based TMT quantification experiments. MS 2 PIP is freely available at https:// iomics.ugent.be/ ms2pip/ .