AlphaDIA

AlphaDIA is an open-source, feature-free DIA (data-independent acquisition) proteomics search engine that performs machine learning directly on raw mass spectrometry signals, achieving end-to-end transfer learning across instruments without requiring spectral library features. Benchmarked at >120,000 precursors per run, it matches or exceeds other leading search engines. Published in Nature Biotechnology (2025); part of the AlphaX proteomics ecosystem from the Mann Lab.

Source: Mann Labs (MPI of Biochemistry) — Nature Biotechnology, 2025

Feature-free DIA search: ML applied directly to raw signal, no traditional feature extraction
End-to-end transfer learning across TOF and Orbitrap instruments
Imports AlphaPept, DIA-NN, MaxQuant, Spectronaut, and FragPipe spectral libraries
>120,000 precursors per run — top-tier benchmark performance
Part of the AlphaX suite: integrates with AlphaPept, AlphaPeptStats, and AlphaQuant
Python — Apache-2.0; available on PyPI and conda

Docs: alphadia.readthedocs.io — Paper: Nature Biotechnology