references.bib

@ARTICLE{Huang2020-lu,
  title    = "{MSstatsTMT}: Statistical Detection of Differentially Abundant
              Proteins in Experiments with Isobaric Labeling and Multiple
              Mixtures",
  author   = "Huang, Ting and Choi, Meena and Tzouros, Manuel and Golling,
              Sabrina and Pandya, Nikhil Janak and Banfai, Balazs and Dunkley,
              Tom and Vitek, Olga",
  journal  = "Mol. Cell. Proteomics",
  volume   =  19,
  number   =  10,
  pages    = "1706--1723",
  abstract = "Tandem mass tag (TMT) is a multiplexing technology widely-used in
              proteomic research. It enables relative quantification of proteins
              from multiple biological samples in a single MS run with high
              efficiency and high throughput. However, experiments often require
              more biological replicates or conditions than can be accommodated
              by a single run, and involve multiple TMT mixtures and multiple
              runs. Such larger-scale experiments combine sources of biological
              and technical variation in patterns that are complex, unique to
              TMT-based workflows, and challenging for the downstream
              statistical analysis. These patterns cannot be adequately
              characterized by statistical methods designed for other
              technologies, such as label-free proteomics or transcriptomics.
              This manuscript proposes a general statistical approach for
              relative protein quantification in MS- based experiments with TMT
              labeling. It is applicable to experiments with multiple
              conditions, multiple biological replicate runs and multiple
              technical replicate runs, and unbalanced designs. It is based on a
              flexible family of linear mixed-effects models that handle complex
              patterns of technical artifacts and missing values. The approach
              is implemented in MSstatsTMT, a freely available open-source
              R/Bioconductor package compatible with data processing tools such
              as Proteome Discoverer, MaxQuant, OpenMS, and SpectroMine.
              Evaluation on a controlled mixture, simulated datasets, and three
              biological investigations with diverse designs demonstrated that
              MSstatsTMT balanced the sensitivity and the specificity of
              detecting differentially abundant proteins, in large-scale
              experiments with multiple biological mixtures.",
  month    =  oct,
  year     =  2020,
  keywords = "Mass spectrometry; TMT; bioinformatics software; hypothesis
              testing; mathematical modeling; multiple mixtures; protein
              quantification; quantification; statistics",
  language = "en"
}

@ARTICLE{Goeminne2016-tr,
  title    = "Peptide-level Robust Ridge Regression Improves Estimation,
              Sensitivity, and Specificity in Data-dependent Quantitative
              Label-free Shotgun Proteomics",
  author   = "Goeminne, Ludger J E and Gevaert, Kris and Clement, Lieven",
  journal  = "Mol. Cell. Proteomics",
  volume   =  15,
  number   =  2,
  pages    = "657--668",
  abstract = "Peptide intensities from mass spectra are increasingly used for
              relative quantitation of proteins in complex samples. However,
              numerous issues inherent to the mass spectrometry workflow turn
              quantitative proteomic data analysis into a crucial challenge. We
              and others have shown that modeling at the peptide level
              outperforms classical summarization-based approaches, which
              typically also discard a lot of proteins at the data preprocessing
              step. Peptide-based linear regression models, however, still
              suffer from unbalanced datasets due to missing peptide
              intensities, outlying peptide intensities and overfitting. Here,
              we further improve upon peptide-based models by three modular
              extensions: ridge regression, improved variance estimation by
              borrowing information across proteins with empirical Bayes and
              M-estimation with Huber weights. We illustrate our method on the
              CPTAC spike-in study and on a study comparing wild-type and ArgP
              knock-out Francisella tularensis proteomes. We show that the fold
              change estimates of our robust approach are more precise and more
              accurate than those from state-of-the-art summarization-based
              methods and peptide-based regression models, which leads to an
              improved sensitivity and specificity. We also demonstrate that
              ionization competition effects come already into play at very low
              spike-in concentrations and confirm that analyses with
              peptide-based regression methods on peptide intensity values
              aggregated by charge state and modification status (e.g.
              MaxQuant's peptides.txt file) are slightly superior to analyses on
              raw peptide intensity values (e.g. MaxQuant's evidence.txt file).",
  month    =  feb,
  year     =  2016,
  language = "en"
}

@ARTICLE{Sticker2020-rl,
  title    = "Robust Summarization and Inference in Proteome-wide Label-free
              Quantification",
  author   = "Sticker, Adriaan and Goeminne, Ludger and Martens, Lennart and
              Clement, Lieven",
  journal  = "Mol. Cell. Proteomics",
  volume   =  19,
  number   =  7,
  pages    = "1209--1219",
  abstract = "Label-Free Quantitative mass spectrometry based workflows for
              differential expression (DE) analysis of proteins impose important
              challenges on the data analysis because of peptide-specific
              effects and context dependent missingness of peptide intensities.
              Peptide-based workflows, like MSqRob, test for DE directly from
              peptide intensities and outperform summarization methods which
              first aggregate MS1 peptide intensities to protein intensities
              before DE analysis. However, these methods are computationally
              expensive, often hard to understand for the non-specialized
              end-user, and do not provide protein summaries, which are
              important for visualization or downstream processing. In this
              work, we therefore evaluate state-of-the-art summarization
              strategies using a benchmark spike-in dataset and discuss why and
              when these fail compared with the state-of-the-art peptide based
              model, MSqRob. Based on this evaluation, we propose a novel
              summarization strategy, MSqRobSum, which estimates MSqRob's model
              parameters in a two-stage procedure circumventing the drawbacks of
              peptide-based workflows. MSqRobSum maintains MSqRob's superior
              performance, while providing useful protein expression summaries
              for plotting and downstream analysis. Summarizing peptide to
              protein intensities considerably reduces the computational
              complexity, the memory footprint and the model complexity, and
              makes it easier to disseminate DE inferred on protein summaries.
              Moreover, MSqRobSum provides a highly modular analysis framework,
              which provides researchers with full flexibility to develop data
              analysis workflows tailored toward their specific applications.",
  month    =  jul,
  year     =  2020,
  keywords = "Biostatistics; bioinformatics; bioinformatics software;
              differential expression; label-free quantification; mass
              spectrometry; ridge regression; shotgun proteomics; summarization",
  language = "en"
}

@ARTICLE{Vandenbulcke2025-sj,
  title     = "{Msqrob2TMT}: Robust linear mixed models for inferring
               differential abundant proteins in labeled experiments with
               arbitrarily complex design",
  author    = "Vandenbulcke, Stijn and Vanderaa, Christophe and Crook, Oliver
               and Martens, Lennart and Clement, Lieven",
  journal   = "Mol. Cell. Proteomics",
  publisher = "Elsevier BV",
  volume    =  24,
  number    =  7,
  pages     =  101002,
  abstract  = "Labeling strategies in mass spectrometry-based proteomics enhance
               sample throughput by enabling the acquisition of multiplexed
               samples within a single run. However, contemporary experiments
               often involve increasingly complex designs, where the number of
               samples exceeds the capacity of a single run, resulting in a
               complex correlation structure that must be addressed for accurate
               statistical inference and reliable biomarker discovery. To this
               end, we introduce msqrob2TMT, a suite of mixed model-based
               workflows specifically designed for differential abundance
               analysis in labeled mass spectrometry-based proteomics data.
               msqrob2TMT accommodates both sample-specific and feature-specific
               (e.g., peptide or protein) covariates, facilitating inference in
               experiments with arbitrarily complex designs and allowing for
               explicit correction of feature-specific covariates. We benchmark
               our innovative workflows against state-of-the-art tools,
               including DEqMS, MSstatsTMT, and msTrawler, using two spike-in
               studies. Our findings demonstrate that msqrob2TMT offers greater
               flexibility, improved modularity, and enhanced performance,
               particularly through the application of robust ridge regression.
               Finally, we demonstrate the practical relevance of msqrob2TMT in
               a real mouse study, highlighting its capacity to effectively
               account for the complex correlation structure in the data.",
  month     =  may,
  year      =  2025,
  keywords  = "TMT labeling; differential proteomics; mass spectrometry; mixed
               models; statistics",
  language  = "en"
}


@ARTICLE{Savitski2011-qi,
  title     = "Delayed fragmentation and optimized isolation width settings for
               improvement of protein identification and accuracy of isobaric
               mass tag quantification on Orbitrap-type mass spectrometers",
  author    = "Savitski, Mikhail M and Sweetman, Gavain and Askenazi, Manor and
               Marto, Jarrod A and Lang, Manja and Zinn, Nico and Bantscheff,
               Marcus",
  journal   = "Anal. Chem.",
  publisher = "American Chemical Society (ACS)",
  volume    =  83,
  number    =  23,
  pages     = "8959--8967",
  abstract  = "Fragmentation of multiple peptides in a single tandem mass scan
               impairs accuracy of isobaric mass tag based quantification.
               Consequently, practitioners aim at fragmenting peptide ions with
               the highest possible purity without compromising on sensitivity
               and coverage achieved in the experiment. Here we report the first
               systematic study optimizing delayed fragmentation options on
               Orbitrap instruments. We demonstrate that by delaying peptide
               fragmentation to occur closer to the apex of the chromatographic
               peak in liquid chromatography-tandem mass spectrometry (LC-MS/MS)
               experiments cofragmentation is reduced by 2-fold and peptides are
               fragmented with 2.8-fold better signal-to-noise ratios. This
               results in significantly improved accuracy of isobaric mass tag
               quantification. Further, we measured cofragmentation dependence
               on isolation width. In comparison to Orbitrap XL instruments the
               reduced space charging in the Orbitrap Velos enables isolation
               widths as narrow as 1 Th without impairing coverage, thus
               substantially reducing cofragmentation. When delayed peptide
               fragmentation and narrow isolation width settings were both
               applied, cofragmentation-induced ratio compression could be
               reduced by 32\% on a log2 scale under otherwise identical
               conditions.",
  month     =  dec,
  year      =  2011,
  language  = "en"
}

@ARTICLE{O-Brien2024-lr,
  title     = "A data analysis framework for combining multiple batches
               increases the power of isobaric proteomics experiments",
  author    = "O'Brien, Jonathon J and Raj, Anil and Gaun, Aleksandr and Waite,
               Adam and Li, Wenzhou and Hendrickson, David G and Olsson, Niclas
               and McAllister, Fiona E",
  journal   = "Nat. Methods",
  publisher = "Springer Science and Business Media LLC",
  volume    =  21,
  number    =  2,
  pages     = "290--300",
  abstract  = "We present a framework for the analysis of multiplexed mass
               spectrometry proteomics data that reduces estimation error when
               combining multiple isobaric batches. Variations in the number and
               quality of observations have long complicated the analysis of
               isobaric proteomics data. Here we show that the power to detect
               statistical associations is substantially improved by utilizing
               models that directly account for known sources of variation in
               the number and quality of observations that occur across
               batches.In a multibatch benchmarking experiment, our open-source
               software (msTrawler) increases the power to detect changes,
               especially in the range of less than twofold changes, while
               simultaneously increasing quantitative proteome coverage by
               utilizing more low-signal observations. Further analyses of
               previously published multiplexed datasets of 4 and 23 batches
               highlight both increased power and the ability to navigate
               complex missing data patterns without relying on unverifiable
               imputations or discarding reliable measurements.",
  month     =  feb,
  year      =  2024,
  language  = "en"
}

@ARTICLE{Gatto2023-kk,
  title    = "Initial recommendations for performing, benchmarking and reporting
              single-cell proteomics experiments",
  author   = "Gatto, Laurent and Aebersold, Ruedi and Cox, Juergen and Demichev,
              Vadim and Derks, Jason and Emmott, Edward and Franks, Alexander M
              and Ivanov, Alexander R and Kelly, Ryan T and Khoury, Luke and
              Leduc, Andrew and MacCoss, Michael J and Nemes, Peter and Perlman,
              David H and Petelski, Aleksandra A and Rose, Christopher M and
              Schoof, Erwin M and Van Eyk, Jennifer and Vanderaa, Christophe and
              Yates, 3rd, John R and Slavov, Nikolai",
  journal  = "Nat. Methods",
  volume   =  20,
  number   =  3,
  pages    = "375--386",
  abstract = "Analyzing proteins from single cells by tandem mass spectrometry
              (MS) has recently become technically feasible. While such analysis
              has the potential to accurately quantify thousands of proteins
              across thousands of single cells, the accuracy and reproducibility
              of the results may be undermined by numerous factors affecting
              experimental design, sample preparation, data acquisition and data
              analysis. We expect that broadly accepted community guidelines and
              standardized metrics will enhance rigor, data quality and
              alignment between laboratories. Here we propose best practices,
              quality controls and data-reporting recommendations to assist in
              the broad adoption of reliable quantitative workflows for
              single-cell proteomics. Resources and discussion forums are
              available at https://single-cell.net/guidelines .",
  month    =  mar,
  year     =  2023,
  language = "en"
}

@ARTICLE{Plubell2017-th,
  title     = "Extended multiplexing of tandem mass tags ({TMT}) labeling
               reveals age and high fat diet specific proteome changes in mouse
               epididymal adipose tissue",
  author    = "Plubell, Deanna L and Wilmarth, Phillip A and Zhao, Yuqi and
               Fenton, Alexandra M and Minnier, Jessica and Reddy, Ashok P and
               Klimek, John and Yang, Xia and David, Larry L and Pamir, Nathalie",
  journal   = "Mol. Cell. Proteomics",
  publisher = "Mol Cell Proteomics",
  volume    =  16,
  number    =  5,
  pages     = "873--890",
  abstract  = "The lack of high-throughput methods to analyze the adipose tissue
               protein composition limits our understanding of the protein
               networks responsible for age and diet related metabolic response.
               We have developed an approach using multiple-dimension liquid
               chromatography tandem mass spectrometry and extended multiplexing
               (24 biological samples) with tandem mass tags (TMT) labeling to
               analyze proteomes of epididymal adipose tissues isolated from
               mice fed either low or high fat diet for a short or a long-term,
               and from mice that aged on low versus high fat diets. The
               peripheral metabolic health (as measured by body weight,
               adiposity, plasma fasting glucose, insulin, triglycerides, total
               cholesterol levels, and glucose and insulin tolerance tests)
               deteriorated with diet and advancing age, with long-term high fat
               diet exposure being the worst. In response to short-term high fat
               diet, 43 proteins representing lipid metabolism (e.g. AACS,
               ACOX1, ACLY) and red-ox pathways (e.g. CPD2, CYP2E, SOD3) were
               significantly altered (FDR < 10\%). Long-term high fat diet
               significantly altered 55 proteins associated with immune response
               (e.g. IGTB2, IFIT3, LGALS1) and rennin angiotensin system (e.g.
               ENPEP, CMA1, CPA3, ANPEP). Age-related changes on low fat diet
               significantly altered only 18 proteins representing mainly urea
               cycle (e.g. OTC, ARG1, CPS1), and amino acid biosynthesis (e.g.
               GMT, AKR1C6). Surprisingly, high fat diet driven age-related
               changes culminated with alterations in 155 proteins involving
               primarily the urea cycle (e.g. ARG1, CPS1), immune
               response/complement activation (e.g. C3, C4b, C8, C9, CFB, CFH,
               FGA), extracellular remodeling (e.g. EFEMP1, FBN1, FBN2, LTBP4,
               FERMT2, ECM1, EMILIN2, ITIH3) and apoptosis (e.g. YAP1, HIP1,
               NDRG1, PRKCD, MUL1) pathways. Using our adipose tissue tailored
               approach we have identified both age-related and high fat diet
               specific proteomic signatures highlighting a pronounced
               involvement of arginine metabolism in response to advancing age,
               and branched chain amino acid metabolism in early response to
               high fat feeding. Data are available via ProteomeXchange with
               identifier PXD005953.",
  month     =  may,
  year      =  2017,
  language  = "en"
}

@ARTICLE{Segers2025-ce,
  title    = "{omicsGMF}: a multi-tool for dimensionality reduction, batch
              correction and imputation applied to bulk- and single cell
              proteomics data",
  author   = "Segers, Alexandre and Castiglione, Cristian and Vanderaa,
              Christophe and De Baere, Elfride and Martens, Lennart and Risso,
              Davide and Clement, Lieven",
  journal  = "bioRxiv",
  pages    = "2025.03.24.644996",
  abstract = "The unprecedented speed and sensitivity of mass spectrometry (MS)
              unlocked large-scale applications of proteomics and even enabled
              proteome profiling of single cells. However, this fast-evolving
              field is hindered by a lack of scalable dimensionality reduction
              tools that can compensate for substantial batch effects and
              missingness across MS runs. Therefore, we present omicsGMF, a
              fast, scalable, and interpretable matrix factorization method,
              tailored for bulk and single-cell proteomics data. Unlike current
              workflows that sequentially apply imputation, batch correction,
              and principal component analysis, omicsGMF integrates these steps
              into a unified framework, dramatically enhancing data processing
              and dimensionality reduction. Additionally, omicsGMF provides
              robust imputation of missing values, outperforming bespoke
              state-of-the-art imputation tools. We further demonstrate how this
              integrated approach increases statistical power to detect
              differentially abundant proteins in the downstream data analysis.
              Hence, omicsGMF is a highly scalable approach to dimensionality
              reduction in proteomics, that dramatically improves many important
              steps in proteomics data analysis. \#\#\# Competing Interest
              Statement The authors have declared no competing interest.",
  month    =  mar,
  year     =  2025,
  language = "en"
}

@article{PAULOVICH2010242,
title = {Interlaboratory Study Characterizing a Yeast Performance Standard for Benchmarking LC-MS Platform Performance*},
journal = {Molecular & Cellular Proteomics},
volume = {9},
number = {2},
pages = {242-254},
year = {2010},
issn = {1535-9476},
doi = {https://doi.org/10.1074/mcp.M900222-MCP200},
url = {https://www.sciencedirect.com/science/article/pii/S1535947620337968},
author = {Amanda G. Paulovich and Dean Billheimer and Amy-Joan L. Ham and Lorenzo Vega-Montoto and Paul A. Rudnick and David L. Tabb and Pei Wang and Ronald K. Blackman and David M. Bunk and Helene L. Cardasis and Karl R. Clauser and Christopher R. Kinsinger and Birgit Schilling and Tony J. Tegeler and Asokan Mulayath Variyath and Mu Wang and Jeffrey R. Whiteaker and Lisa J. Zimmerman and David Fenyo and Steven A. Carr and Susan J. Fisher and Bradford W. Gibson and Mehdi Mesri and Thomas A. Neubert and Fred E. Regnier and Henry Rodriguez and Cliff Spiegelman and Stephen E. Stein and Paul Tempst and Daniel C. Liebler},
abstract = {Optimal performance of LC-MS/MS platforms is critical to generating high quality proteomics data. Although individual laboratories have developed quality control samples, there is no widely available performance standard of biological complexity (and associated reference data sets) for benchmarking of platform performance for analysis of complex biological proteomes across different laboratories in the community. Individual preparations of the yeast Saccharomyces cerevisiae proteome have been used extensively by laboratories in the proteomics community to characterize LC-MS platform performance. The yeast proteome is uniquely attractive as a performance standard because it is the most extensively characterized complex biological proteome and the only one associated with several large scale studies estimating the abundance of all detectable proteins. In this study, we describe a standard operating protocol for large scale production of the yeast performance standard and offer aliquots to the community through the National Institute of Standards and Technology where the yeast proteome is under development as a certified reference material to meet the long term needs of the community. Using a series of metrics that characterize LC-MS performance, we provide a reference data set demonstrating typical performance of commonly used ion trap instrument platforms in expert laboratories; the results provide a basis for laboratories to benchmark their own performance, to improve upon current methods, and to evaluate new technologies. Additionally, we demonstrate how the yeast reference, spiked with human proteins, can be used to benchmark the power of proteomics platforms for detection of differentially expressed proteins at different levels of concentration in a complex matrix, thereby providing a metric to evaluate and minimize preanalytical and analytical variation in comparative proteomics experiments.}
}

@ARTICLE{Ramond2015-rz,
  title     = "Importance of host cell arginine uptake in Francisella phagosomal
               escape and ribosomal protein amounts",
  author    = "Ramond, Elodie and Gesbert, Gael and Guerrera, Ida Chiara and
               Chhuon, Cerina and Dupuis, Marion and Rigard, Mélanie and Henry,
               Thomas and Barel, Monique and Charbit, Alain",
  journal   = "Mol. Cell. Proteomics",
  publisher = "Elsevier BV",
  volume    =  14,
  number    =  4,
  pages     = "870--881",
  abstract  = "Upon entry into mammalian host cells, the pathogenic bacterium
               Francisella must import host cell arginine to multiply actively
               in the host cytoplasm. We identified and functionally
               characterized an arginine transporter (hereafter designated ArgP)
               whose inactivation considerably delayed bacterial phagosomal
               escape and intracellular multiplication. Intramacrophagic growth
               of the ΔargP mutant was fully restored upon supplementation of
               the growth medium with excess arginine, in both F. tularensis
               subsp. novicida and F. tularensis subsp. holarctica LVS,
               demonstrating the importance of arginine acquisition in these two
               subspecies. High-resolution mass spectrometry revealed that
               arginine limitation reduced the amount of most of the ribosomal
               proteins in the ΔargP mutant. In response to stresses such as
               nutritional limitation, repression of ribosomal protein synthesis
               has been observed in all kingdoms of life. Arginine availability
               may thus contribute to the sensing of the intracellular stage of
               the pathogen and to trigger phagosomal egress. All MS data have
               been deposited in the ProteomeXchange database with identifier
               PXD001584
               (http://proteomecentral.proteomexchange.org/dataset/PXD001584).",
  month     =  apr,
  year      =  2015,
  language  = "en"
}

@ARTICLE{Shen2018-gw,
  title     = "{IonStar} enables high-precision, low-missing-data proteomics
               quantification in large biological cohorts",
  author    = "Shen, Xiaomeng and Shen, Shichen and Li, Jun and Hu, Qiang and
               Nie, Lei and Tu, Chengjian and Wang, Xue and Poulsen, David J and
               Orsburn, Benjamin C and Wang, Jianmin and Qu, Jun",
  journal   = "Proc. Natl. Acad. Sci. U. S. A.",
  publisher = "Proc Natl Acad Sci U S A",
  volume    =  115,
  number    =  21,
  pages     = "E4767--E4776",
  abstract  = "Reproducible quantification of large biological cohorts is
               critical for clinical/pharmaceutical proteomics yet remains
               challenging because most prevalent methods suffer from
               drastically declined commonly quantified proteins and
               substantially deteriorated quantitative quality as cohort size
               expands. MS2-based data-independent acquisition approaches
               represent tremendous advancements in reproducible protein
               measurement, but often with limited depth. We developed IonStar,
               an MS1-based quantitative approach enabling in-depth,
               high-quality quantification of large cohorts by combining
               efficient/reproducible experimental procedures with unique
               data-processing components, such as efficient 3D chromatographic
               alignment, sensitive and selective direct ion current extraction,
               and stringent postfeature generation quality control. Compared
               with several popular label-free methods, IonStar exhibited far
               lower missing data (0.1\%), superior quantitative
               accuracy/precision [∼5\% intragroup coefficient of variation
               (CV)], the widest protein abundance range, and the highest
               sensitivity/specificity for identifying protein changes (7,000
               unique protein groups (>99.8\% without missing data across the
               100 samples) with a low false discovery rate (FDR), two or more
               unique peptides per protein, and high quantitative precision.
               IonStar represents a reliable and robust solution for precise and
               reproducible protein measurement in large cohorts.",
  month     =  may,
  year      =  2018,
  keywords  = "MS1 ion current-based methods; label-free quantification;
               large-cohort analysis; missing data; quantitative proteomics",
  language  = "en"
}

@article{Staes2024,
  author       = {Staes, An and Mendes Maia, Teresa and Dufour, Sara and Bouwmeester, Robbin and Gabriels, Ralf and Martens, Lennart and Gevaert, Kris and Impens, Francis and Devos, Simon},
  title        = {Benefit of In Silico Predicted Spectral Libraries in Data‑Independent Acquisition Data Analysis Workflows},
  journal      = {Journal of Proteome Research},
  year         = {2024},
  volume       = {23},
  number       = {6},
  pages        = {2078--2089},
  doi          = {10.1021/acs.jproteome.4c00048},
  pmid         = {38666436}
}

@article {VanPuyveldeEtal2026,
	author = {Van Puyvelde, Bart and Devreese, Robbe and Chiva, Cristina and Sabid{\'o}, Eduard and Pfammatter, Sibylle and Panse, Christian and Rijal, Jeewan Babu and Keller, Charline and Batruch, Ihor and Pribil, Patrick and Vincendet, Jean-Baptiste and Fontaine, Fr{\'e}d{\'e}ric and Lefever, Lars and Magalh{\~a}es, Pedro and Deforce, Dieter and Nanni, Paolo and Ghesqui{\`e}re, Bart and Perez-Riverol, Yasset and Martens, Lennart and Carapito, Christine and Bouwmeester, Robbin and Dhaenens, Maarten},
	title = {LFQ Benchmark Dataset - Generation Beta: Assessing Modern Proteomics Instruments and Acquisition Workflows with High-Throughput LC Gradients},
	elocation-id = {2026.01.29.702266},
	year = {2026},
	doi = {10.64898/2026.01.29.702266},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Recent advances in liquid chromatography{\textendash}mass spectrometry (LC-MS) have accelerated the adoption of high-throughput workflows that deliver deep proteome coverage using minimal sample amounts. This trend is largely driven by clinical and single-cell proteomics, where sensitivity and reproducibility are essential. Here, we extend our previous benchmark dataset (PXD028735) using next-generation LC-MS platforms optimized for rapid proteome analysis. We generated an extensive DDA/DIA dataset using a human-yeast-E. coli hybrid proteome. The proteome sample was distributed across multiple laboratories together with standardized analytical protocols specifying two short LC gradients (5 and 15 min) and low sample input amounts. This dataset includes data acquired on four different platforms, and features new scanning quadrupole-based implementations, extending coverage across different instruments and acquisition strategies. Our comprehensive evaluation highlights how technological advances and reduced LC gradients may affect proteome depth, quantitative precision, and cross-instrument consistency. The release of this benchmark dataset via ProteomeXchange (PXD070049 and PXD071205), allows for the acceleration of cross-platform algorithm development, enhance data mining strategies, and supports standardization of short-gradient, high-throughput LC-MS-based proteomics.Competing Interest StatementFrederic Fontaine is employed by Thermo Fisher Scientific. Ihor Batruch, Patrick Pribil and Jean-Baptiste Vincendet are employed by SCIEX. Bart Van Puyvelde joined SCIEX after the completion of this work.Research Foundation - Flanders, https://ror.org/03qtxy027, 1278023N, 1SH9O24N, G010023N, 12A6L24NGhent University Special Research Fund, BOF/PDO/2025/049, BOF21/GOA/033Horizon Europe, 101080544, 101191739CHIST-ERA, G0GDV23NEuropean Molecular Biology Laboratory, 208391/Z/17/Z, 223745/Z/21/ZBBSRC, BB/X001911/1Agence Nationale de la Recherche - French Proteomic Infrastructure (ProFI), ProFI UAR2048, ANR-10-INBS08-03, ANR-24-INBS-0015Region Grand-Est, SC-Proteomics projectITMO Cancer of Aviesanthe Interdisciplinary Thematic Institute IMSIdEx Unistra, ANR-10-IDEX-0002SFRI-STRAT{\textquoteright}US, ANR-20-SFRI-0012},
	URL = {https://www.biorxiv.org/content/early/2026/02/09/2026.01.29.702266},
	eprint = {https://www.biorxiv.org/content/early/2026/02/09/2026.01.29.702266.full.pdf},
	journal = {bioRxiv}
}

@article{VanLeeneEtal2026,
  title = {Advancing {DIA}-Based Limited Proteolysis Workflows: Introducing {DIA}-{LiPA}},
  author = {Van Leene, Chlo{\'e} and Araftpoor, Emin and Staes, An and Argentini, Andrea and B{\"u}hler, Marcel and Clement, Lieven and Gevaert, Kris},
  journal = {Analytical Chemistry},
  year = {2026},
  volume = {98},
  number = {7},
  pages = {5499–5512},
  doi = {10.1021/acs.analchem.5c07014}
}

@article{AldehoffEtAl2025,
  author  = {Aldehoff, Alix Sarah and Karkossa, Isabel and Broghammer, Hannes and Krupka, Sandra and Weiner, Jan and Goerdeler, Charlotte and Nuwayhid, Rasha and Langer, Stefan and Wabitsch, Martin and Rolle-Kampczyk, Uta and Klöting, Norbert and Blüher, Matthias and Heiker, Joachim T. and von Bergen, Martin and Schubert, Kristin},
  title   = {Advanced Proteomics Approaches Hold Potential for the Risk Assessment of Metabolism-Disrupting Chemicals as Omics-Based NAM: A Case Study Using the Phthalate Substitute DINCH},
  journal = {Environmental Science \& Technology},
  year    = {2025},
  volume  = {59},
  number  = {31},
  pages   = {16193--16216},
  doi     = {10.1021/acs.est.5c01206}
}

@article{DuguetEtAl2017,
  author  = {Duguet, Fanny and Locard-Paulet, Marie and Marcellin, Marl{\`e}ne and Chaoui, Karima and Bernard, Isabelle and Andreoletti, Olivier and Lesourne, Renaud and Burlet-Schiltz, Odile and Gonzalez de Peredo, Anne and Saoudi, Abdelhadi},
  title   = {Proteomic Analysis of Regulatory T Cells Reveals the Importance of Themis1 in the Control of Their Suppressive Function},
  journal = {Molecular \& Cellular Proteomics},
  year    = {2017},
  volume  = {16},
  number  = {8},
  pages   = {1416--1432},
  doi     = {10.1074/mcp.M116.062745},
  pmid    = {28373295}
}

@article{Goeminne2020,
  title   = {MSqRob Takes the Missing Hurdle: Uniting Intensity- and Count-Based Proteomics},
  author  = {Goeminne, Ludger and Sticker, Adriaan and Martens, Lennart and Gevaert, Kris and Clement, Lieven},
  journal = {Analytical Chemistry},
  year    = {2020},
  volume  = {92},
  number  = {9},
  pages   = {6278--6287},
  doi     = {10.1021/acs.analchem.9b04375},
  issn    = {0003-2700},
}

@article{DemeulemeesterEtAl2024,
  title   = {msqrob2PTM: Differential Abundance and Differential Usage Analysis of MS-Based Proteomics Data at the Posttranslational Modification and Peptidoform Level},
  author  = {Demeulemeester, Nina and Gébelin, Marie and Caldi Gomes, Lucas and Lingor, Paul and Carapito, Christine and Martens, Lennart and Clement, Lieven},
  journal = {Molecular \& Cellular Proteomics},
  volume  = {23},
  number  = {2},
  pages   = {100708},
  year    = {2024},
  doi     = {10.1016/j.mcpro.2023.100708},
  issn    = {1535-9476}
}