Improving SWATH-MS analysis by Deep-learning
Ontology highlight
ABSTRACT: To be able to reliably generate theoretical libraries that can be used in SWATH experiments, we developed a prediction framework, deep-learning for SWATH analysis (dpSWATH), to improve the sensitivity and specificity of data generated by Q-TOF mass spectrometers. The theoretical library built by dpSWATH allowed us to increase the identification rate of proteins and peptides compared to traditional or library-free methods. Especially, the in-silico library built based on the transcriptome scale identified the most proteins while kept a similar FDR as DDA library. Based on our analysis we conclude that dpSWATH is superior in predicting libraries that can be used for SWATH-MS measurements compared to other algorithms that are based on Orbitrap data.
INSTRUMENT(S): TripleTOF 6600
ORGANISM(S): Drosophila Melanogaster (fruit Fly)
TISSUE(S): Embryo
SUBMITTER: Bo Sun
LAB HEAD: Prof. Dr. Axel Imhof
PROVIDER: PXD038407 | Pride | 2023-01-16
REPOSITORIES: Pride
ACCESS DATA