biblio.bib

% 32321741
@article{pride2022,
    author = {Perez-Riverol, Yasset and Bai, Jingwen and Bandla, Chakradhar and García-Seisdedos, David and Hewapathirana, Suresh and Kamatchinathan, Selvakumar and Kundu, Deepti J and Prakash, Ananth and Frericks-Zipper, Anika and Eisenacher, Martin and Walzer, Mathias and Wang, Shengbo and Brazma, Alvis and Vizcaíno, Juan Antonio},
    title = "{The PRIDE database resources in 2022: a hub for mass spectrometry-based proteomics evidences}",
    journal = {Nucleic Acids Research},
    volume = {50},
    number = {D1},
    pages = {D543-D552},
    year = {2021},
    month = {11},
    abstract = "{The PRoteomics IDEntifications (PRIDE) database (https://www.ebi.ac.uk/pride/) is the world's largest data repository of mass spectrometry-based proteomics data. PRIDE is one of the founding members of the global ProteomeXchange (PX) consortium and an ELIXIR core data resource. In this manuscript, we summarize the developments in PRIDE resources and related tools since the previous update manuscript was published in Nucleic Acids Research in 2019. The number of submitted datasets to PRIDE Archive (the archival component of PRIDE) has reached on average around 500 datasets per month during 2021. In addition to continuous improvements in PRIDE Archive data pipelines and infrastructure, the PRIDE Spectra Archive has been developed to provide direct access to the submitted mass spectra using Universal Spectrum Identifiers. As a key point, the file format MAGE-TAB for proteomics has been developed to enable the improvement of sample metadata annotation. Additionally, the resource PRIDE Peptidome provides access to aggregated peptide/protein evidences across PRIDE Archive. Furthermore, we will describe how PRIDE has increased its efforts to reuse and disseminate high-quality proteomics data into other added-value resources such as UniProt, Ensembl and Expression Atlas.}",
    issn = {0305-1048},
    doi = {10.1093/nar/gkab1038},
    url = {https://doi.org/10.1093/nar/gkab1038},
    eprint = {https://academic.oup.com/nar/article-pdf/50/D1/D543/42057564/gkab1038.pdf},
}




@ARTICLE{Wilhelm2021,
  title    = "Deep learning boosts sensitivity of mass spectrometry-based
              immunopeptidomics",
  author   = "Wilhelm, Mathias and Zolg, Daniel P and Graber, Michael and
              Gessulat, Siegfried and Schmidt, Tobias and Schnatbaum, Karsten
              and Schwencke-Westphal, Celina and Seifert, Philipp and de
              Andrade Kr{\"a}tzig, Niklas and Zerweck, Johannes and Knaute,
              Tobias and Br{\"a}unlein, Eva and Samaras, Patroklos and
              Lautenbacher, Ludwig and Klaeger, Susan and Wenschuh, Holger and
              Rad, Roland and Delanghe, Bernard and Huhmer, Andreas and Carr,
              Steven A and Clauser, Karl R and Krackhardt, Angela M and Reimer,
              Ulf and Kuster, Bernhard",
  abstract = "Characterizing the human leukocyte antigen (HLA) bound ligandome
              by mass spectrometry (MS) holds great promise for developing
              vaccines and drugs for immune-oncology. Still, the identification
              of non-tryptic peptides presents substantial computational
              challenges. To address these, we synthesized and analyzed
              >300,000 peptides by multi-modal LC-MS/MS within the
              ProteomeTools project representing HLA class I \& II ligands and
              products of the proteases AspN and LysN. The resulting data
              enabled training of a single model using the deep learning
              framework Prosit, allowing the accurate prediction of fragment
              ion spectra for tryptic and non-tryptic peptides. Applying Prosit
              demonstrates that the identification of HLA peptides can be
              improved up to 7-fold, that 87\% of the proposed proteasomally
              spliced HLA peptides may be incorrect and that dozens of
              additional immunogenic neo-epitopes can be identified from
              patient tumors in published data. Together, the provided
              peptides, spectra and computational tools substantially expand
              the analytical depth of immunopeptidomics workflows.",
  journal  = "Nature Communications",
  volume   =  12,
  number   =  1,
  pages    = "3346",
  month    =  jun,
  year     =  2021,
  language = "en"
}

@ARTICLE{Van_Puyvelde2022,
  title    = "A comprehensive {LFQ} benchmark dataset on modern day acquisition
              strategies in proteomics",
  author   = "Van Puyvelde, Bart and Daled, Simon and Willems, Sander and
              Gabriels, Ralf and Gonzalez de Peredo, Anne and Chaoui, Karima
              and Mouton-Barbosa, Emmanuelle and Bouyssi{\'e}, David and
              Boonen, Kurt and Hughes, Christopher J and Gethings, Lee A and
              Perez-Riverol, Yasset and Bloomfield, Nic and Tate, Stephen and
              Schiltz, Odile and Martens, Lennart and Deforce, Dieter and
              Dhaenens, Maarten",
  abstract = "In the last decade, a revolution in liquid chromatography-mass
              spectrometry (LC-MS) based proteomics was unfolded with the
              introduction of dozens of novel instruments that incorporate
              additional data dimensions through innovative acquisition
              methodologies, in turn inspiring specialized data analysis
              pipelines. Simultaneously, a growing number of proteomics
              datasets have been made publicly available through data
              repositories such as ProteomeXchange, Zenodo and Skyline
              Panorama. However, developing algorithms to mine this data and
              assessing the performance on different platforms is currently
              hampered by the lack of a single benchmark experimental design.
              Therefore, we acquired a hybrid proteome mixture on different
              instrument platforms and in all currently available families of
              data acquisition. Here, we present a comprehensive Data-Dependent
              and Data-Independent Acquisition (DDA/DIA) dataset acquired using
              several of the most commonly used current day instrumental
              platforms. The dataset consists of over 700 LC-MS runs, including
              adequate replicates allowing robust statistics and covering over
              nearly 10 different data formats, including scanning quadrupole
              and ion mobility enabled acquisitions. Datasets are available via
              ProteomeXchange (PXD028735).",
  journal  = "Sci Data",
  volume   =  9,
  number   =  1,
  pages    = "126",
  month    =  mar,
  year     =  2022,
  language = "en"
}

@ARTICLE{Vaudel2012,
  title    = "A complex standard for protein identification, designed by
              evolution",
  author   = "Vaudel, Marc and Burkhart, Julia M and Breiter, Daniela and
              Zahedi, Ren{\'e} P and Sickmann, Albert and Martens, Lennart",
  abstract = "Shotgun proteomic investigations rely on the algorithmic
              assignment of mass spectra to peptides. The quality of these
              matches is therefore a cornerstone in the analysis and has been
              the subject of numerous recent developments. In order to
              establish the benefits of novel algorithms, they are applied to
              reference samples of known content. However, these were recently
              shown to be either too simple to resemble typical real-life
              samples or as leading to results of lower accuracy as the method
              itself. Here, we describe how to use the proteome of Pyrococcus
              furiosus , a hyperthermophile, as a standard to evaluate
              proteomics identification workflows. Indeed, we prove that the
              Pyrococcus furiosus proteome provides a valid method for
              detecting random hits, comparable to the decoy databases
              currently in popular use, but we also prove that the Pyrococcus
              furiosus proteome goes squarely beyond the decoy approach by also
              providing many hundreds of highly reliable true positive hits.
              Searching the Pyrococcus furiosus proteome can thus be used as a
              unique test that provides the ability to reliably detect both
              false positives as well as proteome-scale true positives,
              allowing the rigorous testing of identification algorithms at the
              peptide and protein level.",
  journal  = "Journal Proteome Research",
  volume   =  11,
  number   =  10,
  pages    = "5065--5071",
  month    =  oct,
  year     =  2012,
  language = "en"
}



@ARTICLE{Barsnes2018,
  title    = "{SearchGUI}: A Highly Adaptable Common Interface for Proteomics
              Search and de Novo Engines",
  author   = "Barsnes, Harald and Vaudel, Marc",
  abstract = "Mass-spectrometry-based proteomics has become the standard
              approach for identifying and quantifying proteins. A vital step
              consists of analyzing experimentally generated mass spectra to
              identify the underlying peptide sequences for later mapping to
              the originating proteins. We here present the latest developments
              in SearchGUI, a common open-source interface for the most
              frequently used freely available proteomics search and de novo
              engines that has evolved into a central component in numerous
              bioinformatics workflows.",
  journal  = "Journal of Proteome Research",
  volume   =  17,
  number   =  7,
  pages    = "2552--2555",
  month    =  jul,
  year     =  2018,
  keywords = "bioinformatics; de novo algorithms; protein identification;
              search engines",
  language = "en"
}

@ARTICLE{Kim2014,
  title    = "{MS-GF+} makes progress towards a universal database search tool
              for proteomics",
  author   = "Kim, Sangtae and Pevzner, Pavel A",
  abstract = "Mass spectrometry (MS) instruments and experimental protocols are
              rapidly advancing, but the software tools to analyse tandem mass
              spectra are lagging behind. We present a database search tool
              MS-GF+ that is sensitive (it identifies more peptides than most
              other database search tools) and universal (it works well for
              diverse types of spectra, different configurations of MS
              instruments and different experimental protocols). We benchmark
              MS-GF+ using diverse spectral data sets: (i) spectra of varying
              fragmentation methods; (ii) spectra of multiple enzyme digests;
              (iii) spectra of phosphorylated peptides; and (iv) spectra of
              peptides with unusual fragmentation propensities produced by a
              novel alpha-lytic protease. For all these data sets, MS-GF+
              significantly increases the number of identified peptides
              compared with commonly used methods for peptide identifications.
              We emphasize that although MS-GF+ is not specifically designed
              for any particular experimental set-up, it improves on the
              performance of tools specifically designed for these applications
              (for example, specialized tools for phosphoproteomics).",
  journal  = "Nature Communications",
  volume   =  5,
  pages    = "5277",
  month    =  oct,
  year     =  2014,
  language = "en"
}

@ARTICLE{Fenyo2003,
  title    = "A method for assessing the statistical significance of mass
              spectrometry-based protein identifications using general scoring
              schemes",
  author   = "Feny{\"o}, David and Beavis, Ronald C",
  abstract = "This paper investigates the use of survival functions and
              expectation values to evaluate the results of protein
              identification experiments. These functions are standard
              statistical measures that can be used to reduce various protein
              identification scoring schemes to a common, easily interpretably
              representation. The relative merits of scoring systems were
              explored using this approach, as well as the effects of altering
              primary identification parameters. We would advocate the
              widespread use of these simple statistical measures to simplify
              and standardize the reporting of the confidence of protein
              identification results, allowing the users of different
              identification algorithms to compare their results in a
              straightforward and statistically significant manner. A method is
              described for measuring these distributions using information
              that is being discarded by most protein identification search
              engines, resulting in accurate survival functions that are
              specific to any combination of scoring algorithms, sequence
              databases, and mass spectra.",
  journal  = "Analytical Chemistry",
  volume   =  75,
  number   =  4,
  pages    = "768--774",
  month    =  feb,
  year     =  2003,
  language = "en"
}

@ARTICLE{Hulstaert2020,
  title    = "{ThermoRawFileParser}: Modular, Scalable, and {Cross-Platform}
              {RAW} File Conversion",
  author   = "Hulstaert, Niels and Shofstahl, Jim and Sachsenberg, Timo and
              Walzer, Mathias and Barsnes, Harald and Martens, Lennart and
              Perez-Riverol, Yasset",
  abstract = "The field of computational proteomics is approaching the big data
              age, driven both by a continuous growth in the number of samples
              analyzed per experiment as well as by the growing amount of data
              obtained in each analytical run. In order to process these large
              amounts of data, it is increasingly necessary to use elastic
              compute resources such as Linux-based cluster environments and
              cloud infrastructures. Unfortunately, the vast majority of
              cross-platform proteomics tools are not able to operate directly
              on the proprietary formats generated by the diverse mass
              spectrometers. Here, we present ThermoRawFileParser, an
              open-source, cross-platform tool that converts Thermo RAW files
              into open file formats such as MGF and the HUPO-PSI standard file
              format mzML. To ensure the broadest possible availability and to
              increase integration capabilities with popular workflow systems
              such as Galaxy or Nextflow, we have also built Conda package and
              BioContainers container around ThermoRawFileParser. In addition,
              we implemented a user-friendly interface (ThermoRawFileParserGUI)
              for those users not familiar with command-line tools. Finally, we
              performed a benchmark of ThermoRawFileParser and msconvert to
              verify that the converted mzML files contain reliable
              quantitative results.",
  journal  = "Journal of Proteome Research",
  volume   =  19,
  number   =  1,
  pages    = "537--542",
  month    =  jan,
  year     =  2020,
  keywords = "big data; bioinformatics; cloud; file formats; mass spectrometry;
              metadata; mzML; open source; software; workflows",
  language = "en"
}

@ARTICLE{Di_Tommaso2017,
  title    = "Nextflow enables reproducible computational workflows",
  author   = "Di Tommaso, Paolo and Chatzou, Maria and Floden, Evan W and
              Barja, Pablo Prieto and Palumbo, Emilio and Notredame, Cedric",
  journal  = "Nature Biotechnology",
  volume   =  35,
  number   =  4,
  pages    = "316--319",
  month    =  apr,
  year     =  2017,
  language = "en"
}

@ARTICLE{Da_Veiga_Leprevost2017,
  title    = "{BioContainers}: an open-source and community-driven framework
              for software standardization",
  author   = "da Veiga Leprevost, Felipe and Gr{\"u}ning, Bj{\"o}rn A and Alves
              Aflitos, Saulo and R{\"o}st, Hannes L and Uszkoreit, Julian and
              Barsnes, Harald and Vaudel, Marc and Moreno, Pablo and Gatto,
              Laurent and Weber, Jonas and Bai, Mingze and Jimenez, Rafael C
              and Sachsenberg, Timo and Pfeuffer, Julianus and Vera Alvarez,
              Roberto and Griss, Johannes and Nesvizhskii, Alexey I and
              Perez-Riverol, Yasset",
  abstract = "MOTIVATION: BioContainers (biocontainers.pro) is an open-source
              and community-driven framework which provides platform
              independent executable environments for bioinformatics software.
              BioContainers allows labs of all sizes to easily install
              bioinformatics software, maintain multiple versions of the same
              software and combine tools into powerful analysis pipelines.
              BioContainers is based on popular open-source projects Docker and
              rkt frameworks, that allow software to be installed and executed
              under an isolated and controlled environment. Also, it provides
              infrastructure and basic guidelines to create, manage and
              distribute bioinformatics containers with a special focus on
              omics technologies. These containers can be integrated into more
              comprehensive bioinformatics pipelines and different
              architectures (local desktop, cloud environments or HPC
              clusters). AVAILABILITY AND IMPLEMENTATION: The software is
              freely available at github.com/BioContainers/. CONTACT:
              yperez@ebi.ac.uk.",
  journal  = "Bioinformatics",
  volume   =  33,
  number   =  16,
  pages    = "2580--2582",
  month    =  aug,
  year     =  2017,
  language = "en"
}

 @ARTICLE{Gabriels2022,
   title    = "psm\_utils: A high level Python {API} for parsing and handling
               peptide-spectrum-matches and proteomics search results",
   author   = "Gabriels, Ralf and Declercq, Arthur and Bouwmeester, Robbin and
               Degroeve, Sven and Martens, Lennart",
   abstract = "A plethora of proteomics search engine output file formats are in
               circulation. This lack of standardized output files greatly
               complicates generic downstream processing of peptide-spectrum
               matches (PSMs) and PSM files. While standards exist to solve this
               problem, these are far from universally supported by search
               engines. Moreover, software libraries are available to read a
               selection of PSM file formats, but a light-weight package to
               parse PSM files into a unified data structure has been missing.
               Here, we present psm\_utils, a Python package to read and write
               various PSM file formats and to handle peptidoforms, PSMs, and
               PSM lists in a unified and user-friendly Python-, command line-,
               and web-interface. psm\_utils was developed with pragmatism and
               maintainability in mind, adhering to community standards and
               relying on existing packages where possible. The Python API and
               command line interface greatly facilitate handling various PSM
               file formats. Moreover, a user-friendly web application was built
               using psm\_utils that allows anyone to interconvert PSM files and
               retrieve basic PSM statistics. psm\_utils is freely available
               under the permissive Apache2 license at
               https://github.com/compomics/psm\_utils.",
   journal  = "ChemRxiv",
   month    =  oct,
   year     =  2022,
   keywords = "Proteomics;Bioinformatics;Data analysis;Peptide
               identification;Peptide-spectrum matches",
   language = "en"
 }
 
 
 
@ARTICLE{Verheggen2020,
  title    = "Anatomy and evolution of database search engines-a central
              component of mass spectrometry based proteomic workflows",
  author   = "Verheggen, Kenneth and Raeder, Helge and Berven, Frode S and
              Martens, Lennart and Barsnes, Harald and Vaudel, Marc",
  abstract = "Sequence database search engines are bioinformatics algorithms
              that identify peptides from tandem mass spectra using a reference
              protein sequence database. Two decades of development, notably
              driven by advances in mass spectrometry, have provided scientists
              with more than 30 published search engines, each with its own
              properties. In this review, we present the common paradigm behind
              the different implementations, and its limitations for modern
              mass spectrometry datasets. We also detail how the search engines
              attempt to alleviate these limitations, and provide an overview
              of the different software frameworks available to the researcher.
              Finally, we highlight alternative approaches for the
              identification of proteomic mass spectrometry datasets, either as
              a replacement for, or as a complement to, sequence database
              search engines.",
  journal  = "Mass Spectrometry Reviews",
  volume   =  39,
  number   =  3,
  pages    = "292--306",
  month    =  may,
  year     =  2020,
  keywords = "bioinformatics; proteomics; search engine",
  language = "en"
}



@ARTICLE{Elias2010,
  title    = "Target-decoy search strategy for mass spectrometry-based
              proteomics",
  author   = "Elias, Joshua E and Gygi, Steven P",
  abstract = "Accurate and precise methods for estimating incorrect peptide and
              protein identifications are crucial for effective large-scale
              proteome analyses by tandem mass spectrometry. The target-decoy
              search strategy has emerged as a simple, effective tool for
              generating such estimations. This strategy is based on the
              premise that obvious, necessarily incorrect ``decoy'' sequences
              added to the search space will correspond with incorrect search
              results that might otherwise be deemed to be correct. With this
              knowledge, it is possible not only to estimate how many incorrect
              results are in a final data set but also to use decoy hits to
              guide the design of filtering criteria that sensitively partition
              a data set into correct and incorrect identifications.",
  journal  = " Methods in Molecular Biology",
  volume   =  604,
  pages    = "55--71",
  year     =  2010,
  language = "en"
}



@ARTICLE{Gupta2011,
  title    = "Target-decoy approach and false discovery rate: when things may
              go wrong",
  author   = "Gupta, Nitin and Bandeira, Nuno and Keich, Uri and Pevzner, Pavel
              A",
  abstract = "The target-decoy approach (TDA) has done the field of proteomics
              a great service by filling in the need to estimate the false
              discovery rates (FDR) of peptide identifications. While TDA is
              often viewed as a universal solution to the problem of FDR
              evaluation, we argue that the time has come to critically
              re-examine TDA and to acknowledge not only its merits but also
              its demerits. We demonstrate that some popular MS/MS search tools
              are not TDA-compliant and that it is easy to develop a non-TDA
              compliant tool that outperforms all TDA-compliant tools. Since
              the distinction between TDA-compliant and non-TDA compliant tools
              remains elusive, we are concerned about a possible proliferation
              of non-TDA-compliant tools in the future (developed with the best
              intentions). We are also concerned that estimation of the FDR by
              TDA awkwardly depends on a virtual coin toss and argue that it is
              important to take the coin toss factor out of our estimation of
              the FDR. Since computing FDR via TDA suffers from various
              restrictions, we argue that TDA is not needed when accurate
              p-values of individual Peptide-Spectrum Matches are available.",
  journal  = "Journal of the American Society for Mass Spectrometry",
  volume   =  22,
  number   =  7,
  pages    = "1111--1120",
  month    =  jul,
  year     =  2011,
  language = "en"
}


@ARTICLE{Gatto2012,
  title    = "{MSnbase-an} {R/Bioconductor} package for isobaric tagged mass
              spectrometry data visualization, processing and quantitation",
  author   = "Gatto, Laurent and Lilley, Kathryn S",
  abstract = "UNLABELLED: MSnbase is an R/Bioconductor package for the analysis
              of quantitative proteomics experiments that use isobaric tagging.
              It provides an exploratory data analysis framework for
              reproducible research, allowing raw data import, quality control,
              visualization, data processing and quantitation. MSnbase allows
              direct integration of quantitative proteomics data with
              additional facilities for statistical analysis provided by the
              Bioconductor project. AVAILABILITY: MSnbase is implemented in R
              (version $\geq$ 2.13.0) and available at the Bioconductor web
              site (http://www.bioconductor.org/). Vignettes outlining typical
              workflows, input/output capabilities and detailing underlying
              infrastructure are included in the package.",
  journal  = "Bioinformatics",
  volume   =  28,
  number   =  2,
  pages    = "288--289",
  month    =  jan,
  year     =  2012,
  language = "en"
}


@Manual{shiny2021,
    title = {shiny: Web Application Framework for R},
    author = {Winston Chang and Joe Cheng and JJ Allaire and Carson Sievert and Barret Schloerke and Yihui Xie and Jeff Allen and Jonathan McPherson and Alan Dipert and Barbara Borges},
    year = {2021},
    note = {R package version 1.7.1},
    url = {https://CRAN.R-project.org/package=shiny},
  }


@ARTICLE{Gonnelli2015,
  title    = "A decoy-free approach to the identification of peptides",
  author   = "Gonnelli, Giulia and Stock, Michiel and Verwaeren, Jan and
              Maddelein, Davy and De Baets, Bernard and Martens, Lennart and
              Degroeve, Sven",
  abstract = "A growing number of proteogenomics and metaproteomics studies
              indicate potential limitations of the application of the
              ``decoy'' database paradigm used to separate correct peptide
              identifications from incorrect ones in traditional shotgun
              proteomics. We therefore propose a binary classifier called Nokoi
              that allows fast yet reliable decoy-free separation of correct
              from incorrect peptide-to-spectrum matches (PSMs). Nokoi was
              trained on a very large collection of heterogeneous data using
              ranks supplied by the Mascot search engine to label correct and
              incorrect PSMs. We show that Nokoi outperforms Mascot and
              achieves a performance very close to that of Percolator at
              substantially higher processing speeds.",
  journal  = "Journal of Proteome Research",
  volume   =  14,
  number   =  4,
  pages    = "1792--1798",
  month    =  apr,
  year     =  2015,
  keywords = "decoy databases; machine learning; peptide identification",
  language = "en"
}


@article{Efron2008,
author = {Bradley Efron},
title = {{Microarrays, Empirical Bayes and the Two-Groups Model}},
volume = {23},
journal = {Statistical Science},
number = {1},
publisher = {Institute of Mathematical Statistics},
pages = {1 -- 22},
keywords = {empirical null, False discovery rates, simultaneous tests},
year = {2008},
doi = {10.1214/07-STS236},
URL = {https://doi.org/10.1214/07-STS236}
}

@ARTICLE{Spivak2009,
  title    = "Improvements to the percolator algorithm for Peptide
              identification from shotgun proteomics data sets",
  author   = "Spivak, Marina and Weston, Jason and Bottou, L{\'e}on and
              K{\"a}ll, Lukas and Noble, William Stafford",
  abstract = "Shotgun proteomics coupled with database search software allows
              the identification of a large number of peptides in a single
              experiment. However, some existing search algorithms, such as
              SEQUEST, use score functions that are designed primarily to
              identify the best peptide for a given spectrum. Consequently,
              when comparing identifications across spectra, the SEQUEST score
              function Xcorr fails to discriminate accurately between correct
              and incorrect peptide identifications. Several machine learning
              methods have been proposed to address the resulting
              classification task of distinguishing between correct and
              incorrect peptide-spectrum matches (PSMs). A recent example is
              Percolator, which uses semisupervised learning and a decoy
              database search strategy to learn to distinguish between correct
              and incorrect PSMs identified by a database search algorithm. The
              current work describes three improvements to Percolator. (1)
              Percolator's heuristic optimization is replaced with a clear
              objective function, with intuitive reasons behind its choice. (2)
              Tractable nonlinear models are used instead of linear models,
              leading to improved accuracy over the original Percolator. (3) A
              method, Q-ranker, for directly optimizing the number of
              identified spectra at a specified q value is proposed, which
              achieves further gains.",
  journal  = "Journal of Proteome Research",
  volume   =  8,
  number   =  7,
  pages    = "3737--3745",
  month    =  jul,
  year     =  2009,
  language = "en"
}