@article{Fahrner_Foll_Gruning-Democ_data_acqui-2022,
author = {Fahrner, Matthias and Foll, Melanie Christine and Grüning, 
          Björn A. and Bernt, Matthias and Rost, Hannes and 
          Schilling, Oliver},
title = {Democratizing data-independent acquisition proteomics 
         analysis on public cloud infrastructures via the {Galaxy} 
         framework},
journal = {Gigascience},
year = {2022},
doi = {10.1093/gigascience/giac005},
volume = {11},
user = {backofen},
pmid = {35166338},
pages = {},
number = {},
issn = {2047-217X},
abstract = {BACKGROUND: Data-independent acquisition (DIA) has become 
            an important approach in global, mass spectrometric 
            proteomic studies because it provides in-depth insights into 
            the molecular variety of biological systems. However, DIA 
            data analysis remains challenging owing to the high 
            complexity and large data and sample size, which require 
            specialized software and vast computing infrastructures. 
            Most available open-source DIA software necessitates basic 
            programming skills and covers only a fraction of a complete 
            DIA data analysis. In consequence, DIA data analysis often 
            requires usage of multiple software tools and compatibility 
            thereof, severely limiting the usability and 
            reproducibility. FINDINGS: To overcome this hurdle, we have 
            integrated a suite of open-source DIA tools in the Galaxy 
            framework for reproducible and version-controlled data 
            processing. The DIA suite includes OpenSwath, PyProphet, 
            diapysef, and swath2stats. We have compiled functional 
            Galaxy pipelines for DIA processing, which provide a 
            web-based graphical user interface to these pre-installed 
            and pre-configured tools for their use on freely accessible, 
            powerful computational resources of the Galaxy framework. 
            This approach also enables seamless sharing workflows with 
            full configuration in addition to sharing raw data and 
            results. We demonstrate the usability of an all-in-one DIA 
            pipeline in Galaxy by the analysis of a spike-in case study 
            dataset. Additionally, extensive training material is 
            provided to further increase access for the proteomics 
            community. CONCLUSION: The integration of an open-source DIA 
            analysis suite in the web-based and user-friendly Galaxy 
            framework in combination with extensive training material 
            empowers a broad community of researches to perform 
            reproducible and transparent DIA data analysis.}
}