DIA-NN: Neural networks and interference correction enable deep coverage in high-throughput proteomics

Abstract Data-independent acquisition (DIA-MS) boosts reproducibility, depth of coverage and quantification precision in label-free proteomic experiments. We present DIA-NN, a software that employs deep neural networks to distinguish real signals from noise in complex DIA datasets and a new quantification algorithm, that is able to subtract signal interferences. DIA-NN vastly outperforms the existing cutting-edge DIA-MS analysis workflows, particularly in combination with fast chromatographic methods, enabling deep and precise proteome coverage in high-throughput experiments.

[1]  Oliver M. Bernhardt,et al.  Extending the Limits of Quantitative Proteome Profiling with Data-Independent Acquisition and Application to Acetaminophen-Treated Three-Dimensional Liver Microtissues* , 2015, Molecular & Cellular Proteomics.

[2]  Henry H. N. Lam,et al.  PeptideAtlas: a resource for target selection for emerging targeted proteomics workflows , 2008, EMBO reports.

[3]  Dongbo Bu,et al.  MS-Simulator: predicting y-ion intensities for peptides with two charges based on the intensity ratio of neighboring ions. , 2012, Journal of proteome research.

[4]  Samuel H Payne,et al.  PECAN: Library Free Peptide Detection for Data-Independent Acquisition Tandem Mass Spectrometry Data , 2017, Nature Methods.

[5]  John D. Storey.  A direct approach to false discovery rates , 2002 .

[6]  Michael J MacCoss,et al.  Specter: linear deconvolution for targeted analysis of data-independent acquisition mass spectrometry proteomics , 2018, Nature Methods.

[7]  Brett Larsen,et al.  Multi-laboratory assessment of reproducibility, qualitative and quantitative performance of SWATH-mass spectrometry , 2016, bioRxiv.

[8]  Lars Malmström,et al.  DIANA - algorithmic improvements for analysis of data-independent acquisition MS data , 2015, Bioinform..

[9]  Kate Campbell,et al.  Saccharomyces cerevisiae single-copy plasmids for auxotrophy compensation, multiple marker selection, and for designing metabolically cooperating communities , 2016, F1000Research.

[10]  Danielle B. Gutierrez,et al.  Micro-Data-Independent Acquisition for High-Throughput Proteomics and Sensitive Peptide Mass Spectrum Identification. , 2018, Analytical chemistry.

[11]  Oliver M. Bernhardt,et al.  Optimization of Experimental Parameters in Data-Independent Mass Spectrometry Significantly Increases Depth and Reproducibility of Results* , 2017, Molecular & Cellular Proteomics.

[12]  Ben C. Collins,et al.  OpenSWATH enables automated, targeted analysis of data-independent acquisition MS data , 2014, Nature Biotechnology.

[13]  Brendan MacLean,et al.  Bioinformatics Applications Note Gene Expression Skyline: an Open Source Document Editor for Creating and Analyzing Targeted Proteomics Experiments , 2022 .

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Matthias Mann,et al.  BoxCar acquisition method enables single-shot proteomics at a depth of 10,000 proteins in 100 minutes , 2018, Nature Methods.

[16]  Natalie I. Tasman,et al.  A Cross-platform Toolkit for Mass Spectrometry and Proteomics , 2012, Nature Biotechnology.

[17]  Yasset Perez-Riverol,et al.  A multi-center study benchmarks software tools for label-free proteome quantification , 2016, Nature Biotechnology.

[18]  Ruedi Aebersold,et al.  Mass-spectrometric exploration of proteome structure and function , 2016, Nature.

[19]  John D. Venable,et al.  Automated approach for quantitative analysis of complex peptide mixtures from tandem mass spectra , 2004, Nature Methods.

[20]  R. Aebersold,et al.  mProphet: automated data processing and statistical validation for large-scale SRM experiments , 2011, Nature Methods.

[21]  John R Yates,et al.  Proteomics by mass spectrometry: approaches, advances, and applications. , 2009, Annual review of biomedical engineering.

[22]  Ludovic C. Gillet,et al.  Targeted Data Extraction of the MS/MS Spectra Generated by Data-independent Acquisition: A New Concept for Consistent and Accurate Proteome Analysis* , 2012, Molecular & Cellular Proteomics.

[23]  Roland Bruderer,et al.  Cost-effective generation of precise label-free quantitative proteomes in high-throughput by microLC and data-independent acquisition , 2018, Scientific Reports.

[24]  Steven P Gygi,et al.  Target-decoy search strategy for increased confidence in large-scale protein identifications by mass spectrometry , 2007, Nature Methods.

[25]  K. Reinert,et al.  OpenMS: a flexible open-source software platform for mass spectrometry data analysis , 2016, Nature Methods.

[26]  Ludovic C. Gillet,et al.  Data‐independent acquisition‐based SWATH‐MS for quantitative proteomics: a tutorial , 2018, Molecular systems biology.

[27]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.