The Age of Data-Driven Proteomics: How Machine Learning Enables Novel Workflows

Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning

Imputation techniques provide means to replace missing measurements with a value and are used in almost all downstream analysis of mass spectrometry (MS) based proteomics data using label-free quantification (LFQ). Here we demonstrate how collaborative filtering, denoising autoencoders, and variational autoencoders can impute missing values in the context of LFQ at different levels. We applied our method, proteomics imputation modeling mass spectrometry (PIMMS), to an alcohol-related liver disease (ALD) cohort with blood plasma proteomics data available for 358 individuals. Removing 20 percent of the intensities we were able to recover 15 out of 17 significant abundant protein groups using PIMMS-VAE imputations. When analyzing the full dataset we identified 30 additional proteins (+13.2%) that were significantly differentially abundant across disease stages compared to no imputation and found that some of these were predictive of ALD progression in machine learning models. We, therefore, suggest the use of deep learning approaches for imputing missing values in MS-based proteomics on larger datasets and provide workflows for these.

Microbiome modeling: a beginner's guide

Microbiomes, comprised of diverse microbial species and viruses, play pivotal roles in human health, environmental processes, and biotechnological applications and interact with each other, their environment, and hosts via ecological interactions. Our understanding of microbiomes is still limited and hampered by their complexity. A concept improving this understanding is systems biology, which focuses on the holistic description of biological systems utilizing experimental and computational methods. An important set of such experimental methods are metaomics methods which analyze microbiomes and output lists of molecular features. These lists of data are integrated, interpreted, and compiled into computational microbiome models, to predict, optimize, and control microbiome behavior. There exists a gap in understanding between microbiologists and modelers/bioinformaticians, stemming from a lack of interdisciplinary knowledge. This knowledge gap hinders the establishment of computational models in microbiome analysis. This review aims to bridge this gap and is tailored for microbiologists, researchers new to microbiome modeling, and bioinformaticians. To achieve this goal, it provides an interdisciplinary overview of microbiome modeling, starting with fundamental knowledge of microbiomes, metaomics methods, common modeling formalisms, and how models facilitate microbiome control. It concludes with guidelines and repositories for modeling. Each section provides entry-level information, example applications, and important references, serving as a valuable resource for comprehending and navigating the complex landscape of microbiome research and modeling.

Serum Proteomic Signatures in Cervical Cancer: Current Status and Future Directions

In 2020, the World Health Organization (WHO) reported 604,000 new diagnoses of cervical cancer (CC) worldwide, and over 300,000 CC-related fatalities. The vast majority of CC cases are caused by persistent human papillomavirus (HPV) infections. HPV-related CC incidence and mortality rates have declined worldwide because of increased HPV vaccination and CC screening with the Papanicolaou test (PAP test). Despite these significant improvements, developing countries face difficulty implementing these programs, while developed nations are challenged with identifying HPV-independent cases. Molecular and proteomic information obtained from blood or tumor samples have a strong potential to provide information on malignancy progression and response to therapy in CC. There is a large amount of published biomarker data related to CC available but the extensive validation required by the FDA approval for clinical use is lacking. The ability of researchers to use the big data obtained from clinical studies and to draw meaningful relationships from these data are two obstacles that must be overcome for implementation into clinical practice. We report on identified multimarker panels of serum proteomic studies in CC for the past 5 years, the potential for modern computational biology efforts, and the utilization of nationwide biobanks to bridge the gap between multivariate protein signature development and the prediction of clinically relevant CC patient outcomes.

Artificial Intelligence and Computational Biology in Gene Therapy: A Review

One of the trending fields in almost all areas of science and technology is artificial intelligence. Computational biology and artificial intelligence can help gene therapy in many steps including: gene identification, gene editing, vector design, development of new macromolecules and modeling of gene delivery. There are various tools used by computational biology and artificial intelligence in this field, such as genomics, transcriptomic and proteomics data analysis, machine learning algorithms and molecular interaction studies. These tools can introduce new gene targets, novel vectors, optimized experiment conditions, predict the outcomes and suggest the best solutions to avoid undesired immune responses following gene therapy treatment.

Bringing CAM photosynthesis to the table: Paving the way for resilient and productive agricultural systems in a changing climate

Modern agricultural systems are directly threatened by global climate change and the resulting freshwater crisis. A considerable challenge in the coming years will be to develop crops that can cope with the consequences of declining freshwater resources and changing temperatures. One approach to meeting this challenge may lie in our understanding of plant photosynthetic adaptations and water use efficiency. Plants from various taxa have evolved crassulacean acid metabolism (CAM), a water-conserving adaptation of photosynthetic carbon dioxide fixation that enables plants to thrive under semi-arid or seasonally drought-prone conditions. Although past research on CAM has led to a better understanding of the inner workings of plant resilience and adaptation to stress, successful introduction of this pathway into C3 or C4 plants has not been reported. The recent revolution in molecular, systems, and synthetic biology, as well as innovations in high-throughput data generation and mining, creates new opportunities to uncover the minimum genetic tool kit required to introduce CAM traits into drought-sensitive crops. Here, we propose four complementary research avenues to uncover this tool kit. First, genomes and computational methods should be used to improve understanding of the nature of variations that drive CAM evolution. Second, single-cell 'omics technologies offer the possibility for in-depth characterization of the mechanisms that trigger environmentally controlled CAM induction. Third, the rapid increase in new 'omics data enables a comprehensive, multimodal exploration of CAM. Finally, the expansion of functional genomics methods is paving the way for integration of CAM into farming systems.

Advances in data-independent acquisition mass spectrometry towards comprehensive digital proteome landscape

The data-independent acquisition mass spectrometry (DIA-MS) has rapidly evolved as a powerful alternative for highly reproducible proteome profiling with a unique strength of generating permanent digital maps for retrospective analysis of biological systems. Recent advancements in data analysis software tools for the complex DIA-MS/MS spectra coupled to fast MS scanning speed and high mass accuracy have greatly expanded the sensitivity and coverage of DIA-based proteomics profiling. Here, we review the evolution of the DIA-MS techniques, from earlier proof-of-principle of parallel fragmentation of all-ions or ions in selected m/z range, the sequential window acquisition of all theoretical mass spectra (SWATH-MS) to latest innovations, recent development in computation algorithms for data informatics, and auxiliary tools and advanced instrumentation to enhance the performance of DIA-MS. We further summarize recent applications of DIA-MS and experimentally-derived as well as in silico spectra library resources for large-scale profiling to facilitate biomarker discovery and drug development in human diseases with emphasis on the proteomic profiling coverage. Toward next-generation DIA-MS for clinical proteomics, we outline the challenges in processing multi-dimensional DIA data set and large-scale clinical proteomics, and continuing need in higher profiling coverage and sensitivity.

Updated MS²PIP web server supports cutting-edge proteomics applications

Interest in the use of machine learning for peptide fragmentation spectrum prediction has been strongly on the rise over the past years, especially for applications in challenging proteomics identification workflows such as immunopeptidomics and the full-proteome identification of data independent acquisition spectra. Since its inception, the MS²PIP peptide spectrum predictor has been widely used for various downstream applications, mostly thanks to its accuracy, ease-of-use, and broad applicability. We here present a thoroughly updated version of the MS²PIP web server, which includes new and more performant prediction models for both tryptic- and non-tryptic peptides, for immunopeptides, and for CID-fragmented TMT-labeled peptides. Additionally, we have also added new functionality to greatly facilitate the generation of proteome-wide predicted spectral libraries, requiring only a FASTA protein file as input. These libraries also include retention time predictions from DeepLC. Moreover, we now provide pre-built and ready-to-download spectral libraries for various model organisms in multiple DIA-compatible spectral library formats. Besides upgrading the back-end models, the user experience on the MS²PIP web server is thus also greatly enhanced, extending its applicability to new domains, including immunopeptidomics and MS3-based TMT quantification experiments. MS²PIP is freely available at https://iomics.ugent.be/ms2pip/.

Machine Learning on Large-Scale Proteomics Data Identifies Tissue and Cell-Type Specific Proteins

Using data from 183 public human data sets from PRIDE, a machine learning model was trained to identify tissue and cell-type specific protein patterns. PRIDE projects were searched with ionbot and tissue/cell type annotation was manually added. Data from physiological samples were used to train a Random Forest model on protein abundances to classify samples into tissues and cell types. Subsequently, a one-vs-all classification and feature importance were used to analyze the most discriminating protein abundances per class. Based on protein abundance alone, the model was able to predict tissues with 98% accuracy, and cell types with 99% accuracy. The F-scores describe a clear view on tissue-specific proteins and tissue-specific protein expression patterns. In-depth feature analysis shows slight confusion between physiologically similar tissues, demonstrating the capacity of the algorithm to detect biologically relevant patterns. These results can in turn inform downstream uses, from identification of the tissue of origin of proteins in complex samples such as liquid biopsies, to studying the proteome of tissue-like samples such as organoids and cell lines.

Proteomic Applications and Considerations: From Research to Patient Care

Despite technological advancements in the field of proteomics, the rate at which serum and plasma biomarkers identified using proteomic approaches are translated into clinical use remains extremely low. In this chapter, we describe recent technological advancements and analytical strategies in proteomic methods. We also describe the progress of proteomic blood-based biomarkers to date and discuss what the future of proteomics might entail with the use of multi-omic approaches and implementing machine learning on large proteomic datasets. Lastly, we provide several key considerations for biomarker studies, ranging from sample type to the use of reference samples, in order to achieve progress from bench to bedside, ultimately improving patient diagnosis, disease, and/or therapeutic monitoring and care.

ProteomicsML: An Online Platform for Community-Curated Data sets and Tutorials for Machine Learning in Proteomics

Data set acquisition and curation are often the most difficult and time-consuming parts of a machine learning endeavor. This is especially true for proteomics-based liquid chromatography (LC) coupled to mass spectrometry (MS) data sets, due to the high levels of data reduction that occur between raw data and machine learning-ready data. Since predictive proteomics is an emerging field, when predicting peptide behavior in LC-MS setups, each lab often uses unique and complex data processing pipelines in order to maximize performance, at the cost of accessibility and reproducibility. For this reason we introduce ProteomicsML, an online resource for proteomics-based data sets and tutorials across most of the currently explored physicochemical peptide properties. This community-driven resource makes it simple to access data in easy-to-process formats, and contains easy-to-follow tutorials that allow new users to interact with even the most advanced algorithms in the field. ProteomicsML provides data sets that are useful for comparing state-of-the-art machine learning algorithms, as well as providing introductory material for teachers and newcomers to the field alike. The platform is freely available at https://www.proteomicsml.org/, and we welcome the entire proteomics community to contribute to the project at https://github.com/ProteomicsML/ProteomicsML.

New insights and approaches for analyses of immunopeptidomes

Human leucocyte antigen (HLA) molecules play a key role in health and disease by presenting antigen to T-lymphocytes for immunosurveillance. Immunopeptidomics involves the study of the collection of peptides presented within the antigen-binding groove of HLA molecules. Identifying their nature and diversity is crucial to understanding immunosurveillance especially during infection or for the recognition and potential eradication of tumours. This review discusses recent advances in the isolation, identification, and quantitation of these peptide antigens. New informatics approaches and databases have shed light on the extent of peptide antigens derived from unconventional sources including peptides derived from transcripts associated with frame shifts, long noncoding RNA, incorrectly annotated untranslated regions, post-translational modifications, and proteasomal splicing. Several challenges remain in successful analysis of immunopeptides, yet recent developments point to unexplored biology waiting to be unravelled.

Implementing the reuse of public DIA proteomics datasets: from the PRIDE database to Expression Atlas

The number of mass spectrometry (MS)-based proteomics datasets in the public domain keeps increasing, particularly those generated by Data Independent Acquisition (DIA) approaches such as SWATH-MS. Unlike Data Dependent Acquisition datasets, the re-use of DIA datasets has been rather limited to date, despite its high potential, due to the technical challenges involved. We introduce a (re-)analysis pipeline for public SWATH-MS datasets which includes a combination of metadata annotation protocols, automated workflows for MS data analysis, statistical analysis, and the integration of the results into the Expression Atlas resource. Automation is orchestrated with Nextflow, using containerised open analysis software tools, rendering the pipeline readily available and reproducible. To demonstrate its utility, we reanalysed 10 public DIA datasets from the PRIDE database, comprising 1,278 SWATH-MS runs. The robustness of the analysis was evaluated, and the results compared to those obtained in the original publications. The final expression values were integrated into Expression Atlas, making SWATH-MS experiments more widely available and combining them with expression data originating from other proteomics and transcriptomics datasets.

A comprehensive LFQ benchmark dataset on modern day acquisition strategies in proteomics

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).

Measurement(s)	Digital Data Repository
Technology Type(s)	Digital Data Repository

Pout2Prot: An Efficient Tool to Create Protein (Sub)groups from Percolator Output Files

In metaproteomics, the study of the collective proteome of microbial communities, the protein inference problem is more challenging than in single-species proteomics. Indeed, a peptide sequence can be present not only in multiple proteins or protein isoforms of the same species, but also in homologous proteins from closely related species. To assign the taxonomy and functions of the microbial species, specialized tools have been developed, such as Prophane. This tool, however, is not directly compatible with post-processing tools such as Percolator. In this manuscript we therefore present Pout2Prot, which takes Percolator Output (.pout) files from multiple experiments and creates protein group and protein subgroup output files (.tsv) that can be used directly with Prophane. We investigated different grouping strategies and compared existing protein grouping tools to develop an advanced protein grouping algorithm that offers a variety of different approaches, allows grouping for multiple files, and uses a weighted spectral count for protein (sub)groups to reflect abundance. Pout2Prot is available as a web application at https://pout2prot.ugent.be and is installable via pip as a standalone command line tool and reusable software library. All code is open source under the Apache License 2.0 and is available at https://github.com/compomics/pout2prot.

Critical Assessment of MetaProteome Investigation (CAMPI): a multi-laboratory comparison of established workflows

Metaproteomics has matured into a powerful tool to assess functional interactions in microbial communities. While many metaproteomic workflows are available, the impact of method choice on results remains unclear. Here, we carry out a community-driven, multi-laboratory comparison in metaproteomics: the critical assessment of metaproteome investigation study (CAMPI). Based on well-established workflows, we evaluate the effect of sample preparation, mass spectrometry, and bioinformatic analysis using two samples: a simplified, laboratory-assembled human intestinal model and a human fecal sample. We observe that variability at the peptide level is predominantly due to sample processing workflows, with a smaller contribution of bioinformatic pipelines. These peptide-level differences largely disappear at the protein group level. While differences are observed for predicted community composition, similar functional profiles are obtained across workflows. CAMPI demonstrates the robustness of present-day metaproteomics research, serves as a template for multi-laboratory studies in metaproteomics, and provides publicly available data sets for benchmarking future developments.

Critical Assessment of MetaProteome Investigation (CAMPI): a multi-laboratory comparison of established workflows

Metaproteomics has matured into a powerful tool to assess functional interactions in microbial communities. While many metaproteomic workflows are available, the impact of method choice on results remains unclear. Here, we carry out a community-driven, multi-laboratory comparison in metaproteomics: the critical assessment of metaproteome investigation study (CAMPI). Based on well-established workflows, we evaluate the effect of sample preparation, mass spectrometry, and bioinformatic analysis using two samples: a simplified, laboratory-assembled human intestinal model and a human fecal sample. We observe that variability at the peptide level is predominantly due to sample processing workflows, with a smaller contribution of bioinformatic pipelines. These peptide-level differences largely disappear at the protein group level. While differences are observed for predicted community composition, similar functional profiles are obtained across workflows. CAMPI demonstrates the robustness of present-day metaproteomics research, serves as a template for multi-laboratory studies in metaproteomics, and provides publicly available data sets for benchmarking future developments.

Vitamin C Differentially Impacts the Serum Proteome Profile in Female and Male Mice

A suboptimal blood vitamin C (ascorbate) level increases the risk of several chronic diseases. However, the detection of hypovitaminosis C is not a simple task, as ascorbate is unstable in blood samples. In this study, we examined the serum proteome of mice lacking the gulonolactone oxidase (Gulo) required for the ascorbate biosynthesis. Gulo^-/- mice were supplemented with different concentrations of ascorbate in drinking water, and serum was collected to identify proteins correlating with serum ascorbate levels using an unbiased label-free liquid chromatography-tandem mass spectrometry global quantitative proteomic approach. Parallel reaction monitoring was performed to validate the correlations. We uncovered that the serum proteome profiles differ significantly between male and female mice. Also, unlike Gulo^-/- males, a four-week ascorbate treatment did not entirely re-establish the serum proteome profile of ascorbate-deficient Gulo^-/- females to the optimal profile exhibited by Gulo^-/- females that never experienced an ascorbate deficiency. Finally, the serum proteins involved in retinoid metabolism, cholesterol, and lipid transport were similarly affected by ascorbate levels in males and females. In contrast, the proteins regulating serum peptidases and the protein of the acute phase response were different between males and females. These proteins are potential biomarkers correlating with blood ascorbate levels and require further study in standard clinical settings. The complete proteomics data set generated in this study has been deposited to the public repository ProteomeXchange with the data set identifier: PXD027019.

DeepLC can predict retention times for peptides that carry as-yet unseen modifications

The inclusion of peptide retention time prediction promises to remove peptide identification ambiguity in complex liquid chromatography-mass spectrometry identification workflows. However, due to the way peptides are encoded in current prediction models, accurate retention times cannot be predicted for modified peptides. This is especially problematic for fledgling open searches, which will benefit from accurate retention time prediction for modified peptides to reduce identification ambiguity. We present DeepLC, a deep learning peptide retention time predictor using peptide encoding based on atomic composition that allows the retention time of (previously unseen) modified peptides to be predicted accurately. We show that DeepLC performs similarly to current state-of-the-art approaches for unmodified peptides and, more importantly, accurately predicts retention times for modifications not seen during training. Moreover, we show that DeepLC's ability to predict retention times for any modification enables potentially incorrect identifications to be flagged in an open search of a wide variety of proteome data.

Identification of Non-Canonical Translation Products in C. elegans Using Tandem Mass Spectrometry

Transcriptome and ribosome sequencing have revealed the existence of many non-canonical transcripts, mainly containing splice variants, ncRNA, sORFs and altORFs. However, identification and characterization of products that may be translated out of these remains a challenge. Addressing this, we here report on 552 non-canonical proteins and splice variants in the model organism C. elegans using tandem mass spectrometry. Aided by sequencing-based prediction, we generated a custom proteome database tailored to search for non-canonical translation products of C. elegans. Using this database, we mined available mass spectrometric resources of C. elegans, from which 51 novel, non-canonical proteins could be identified. Furthermore, we utilized diverse proteomic and peptidomic strategies to detect 40 novel non-canonical proteins in C. elegans by LC-TIMS-MS/MS, of which 6 were common with our meta-analysis of existing resources. Together, this permits us to provide a resource with detailed annotation of 467 splice variants and 85 novel proteins mapped onto UTRs, non-coding regions and alternative open reading frames of the C. elegans genome.

Ion Mobility Coupled to a Time-of-Flight Mass Analyzer Combined With Fragment Intensity Predictions Improves Identification of Classical Bioactive Peptides and Small Open Reading Frame-Encoded Peptides

Bioactive peptides exhibit key roles in a wide variety of complex processes, such as regulation of body weight, learning, aging, and innate immune response. Next to the classical bioactive peptides, emerging from larger precursor proteins by specific proteolytic processing, a new class of peptides originating from small open reading frames (sORFs) have been recognized as important biological regulators. But their intrinsic properties, specific expression pattern and location on presumed non-coding regions have hindered the full characterization of the repertoire of bioactive peptides, despite their predominant role in various pathways. Although the development of peptidomics has offered the opportunity to study these peptides in vivo, it remains challenging to identify the full peptidome as the lack of cleavage enzyme specification and large search space complicates conventional database search approaches. In this study, we introduce a proteogenomics methodology using a new type of mass spectrometry instrument and the implementation of machine learning tools toward improved identification of potential bioactive peptides in the mouse brain. The application of trapped ion mobility spectrometry (tims) coupled to a time-of-flight mass analyzer (TOF) offers improved sensitivity, an enhanced peptide coverage, reduction in chemical noise and the reduced occurrence of chimeric spectra. Subsequent machine learning tools MS2PIP, predicting fragment ion intensities and DeepLC, predicting retention times, improve the database searching based on a large and comprehensive custom database containing both sORFs and alternative ORFs. Finally, the identification of peptides is further enhanced by applying the post-processing semi-supervised learning tool Percolator. Applying this workflow, the first peptidomics workflow combined with spectral intensity and retention time predictions, we identified a total of 167 predicted sORF-encoded peptides, of which 48 originating from presumed non-coding locations, next to 401 peptides from known neuropeptide precursors, linked to 66 annotated bioactive neuropeptides from within 22 different families. Additional PEAKS analysis expanded the pool of SEPs on presumed non-coding locations to 84, while an additional 204 peptides completed the list of peptides from neuropeptide precursors. Altogether, this study provides insights into a new robust pipeline that fuses technological advancements from different fields ensuring an improved coverage of the neuropeptidome in the mouse brain.

Cov-MS: A Community-Based Template Assay for Mass-Spectrometry-Based Protein Detection in SARS-CoV-2 Patients

Rising population density and global mobility are among the reasons why pathogens such as SARS-CoV-2, the virus that causes COVID-19, spread so rapidly across the globe. The policy response to such pandemics will always have to include accurate monitoring of the spread, as this provides one of the few alternatives to total lockdown. However, COVID-19 diagnosis is currently performed almost exclusively by reverse transcription polymerase chain reaction (RT-PCR). Although this is efficient, automatable, and acceptably cheap, reliance on one type of technology comes with serious caveats, as illustrated by recurring reagent and test shortages. We therefore developed an alternative diagnostic test that detects proteolytically digested SARS-CoV-2 proteins using mass spectrometry (MS). We established the Cov-MS consortium, consisting of 15 academic laboratories and several industrial partners to increase applicability, accessibility, sensitivity, and robustness of this kind of SARS-CoV-2 detection. This, in turn, gave rise to the Cov-MS Digital Incubator that allows other laboratories to join the effort, navigate, and share their optimizations and translate the assay into their clinic. As this test relies on viral proteins instead of RNA, it provides an orthogonal and complementary approach to RT-PCR using other reagents that are relatively inexpensive and widely available, as well as orthogonally skilled personnel and different instruments. Data are available via ProteomeXchange with identifier PXD022550.

Cov-MS: A Community-Based Template Assay for Mass-Spectrometry-Based Protein Detection in SARS-CoV-2 Patients

Rising population density and global mobility are among the reasons why pathogens such as SARS-CoV-2, the virus that causes COVID-19, spread so rapidly across the globe. The policy response to such pandemics will always have to include accurate monitoring of the spread, as this provides one of the few alternatives to total lockdown. However, COVID-19 diagnosis is currently performed almost exclusively by reverse transcription polymerase chain reaction (RT-PCR). Although this is efficient, automatable, and acceptably cheap, reliance on one type of technology comes with serious caveats, as illustrated by recurring reagent and test shortages. We therefore developed an alternative diagnostic test that detects proteolytically digested SARS-CoV-2 proteins using mass spectrometry (MS). We established the Cov-MS consortium, consisting of 15 academic laboratories and several industrial partners to increase applicability, accessibility, sensitivity, and robustness of this kind of SARS-CoV-2 detection. This, in turn, gave rise to the Cov-MS Digital Incubator that allows other laboratories to join the effort, navigate, and share their optimizations and translate the assay into their clinic. As this test relies on viral proteins instead of RNA, it provides an orthogonal and complementary approach to RT-PCR using other reagents that are relatively inexpensive and widely available, as well as orthogonally skilled personnel and different instruments. Data are available via ProteomeXchange with identifier PXD022550.

Deep learning neural network tools for proteomics

Mass-spectrometry-based proteomics enables quantitative analysis of thousands of human proteins. However, experimental and computational challenges restrict progress in the field. This review summarizes the recent flurry of machine-learning strategies using artificial deep neural networks (or "deep learning") that have started to break barriers and accelerate progress in the field of shotgun proteomics. Deep learning now accurately predicts physicochemical properties of peptides from their sequence, including tandem mass spectra and retention time. Furthermore, deep learning methods exist for nearly every aspect of the modern proteomics workflow, enabling improved feature selection, peptide identification, and protein inference.

Personalized Proteome: Comparing Proteogenomics and Open Variant Search Approaches for Single Amino Acid Variant Detection

Discovery of variant peptides such as a single amino acid variant (SAAV) in shotgun proteomics data is essential for personalized proteomics. Both the resolution of shotgun proteomics methods and the search engines have improved dramatically, allowing for confident identification of SAAV peptides. However, it is not yet known if these methods are truly successful in accurately identifying SAAV peptides without prior genomic information in the search database. We studied this in unprecedented detail by exploiting publicly available long-read RNA sequences and shotgun proteomics data from the gold standard reference cell line NA12878. Searching spectra from this cell line with the state-of-the-art open modification search engine ionbot against carefully curated search databases resulted in 96.7% false-positive SAAVs and an 85% lower true positive rate than searching with peptide search databases that incorporate prior genetic information. While adding genetic variants to the search database remains indispensable for correct peptide identification, inclusion of long-read RNA sequences in the search database contributes only 0.3% new peptide identifications. These findings reveal the differences in SAAV detection that result from various approaches, providing guidance to researchers studying SAAV peptides and developers of peptide spectrum identification tools.

Data Management of Sensitive Human Proteomics Data: Current Practices, Recommendations, and Perspectives for the Future

Today it is the norm that all relevant proteomics data that support the conclusions in scientific publications are made available in public proteomics data repositories. However, given the increase in the number of clinical proteomics studies, an important emerging topic is the management and dissemination of clinical, and thus potentially sensitive, human proteomics data. Both in the United States and in the European Union, there are legal frameworks protecting the privacy of individuals. Implementing privacy standards for publicly released research data in genomics and transcriptomics has led to processes to control who may access the data, so-called "controlled access" data. In parallel with the technological developments in the field, it is clear that the privacy risks of sharing proteomics data need to be properly assessed and managed. In our view, the proteomics community must be proactive in addressing these issues. Yet a careful balance must be kept. On the one hand, neglecting to address the potential of identifiability in human proteomics data could lead to reputational damage of the field, while on the other hand, erecting barriers to open access to clinical proteomics data will inevitably reduce reuse of proteomics data and could substantially delay critical discoveries in biomedical research. In order to balance these apparently conflicting requirements for data privacy and efficient use and reuse of research efforts through the sharing of clinical proteomics data, development efforts will be needed at different levels including bioinformatics infrastructure, policymaking, and mechanisms of oversight.

Deep Learning in Proteomics

Proteomics, the study of all the proteins in biological systems, is becoming a data-rich science. Protein sequences and structures are comprehensively catalogued in online databases. With recent advancements in tandem mass spectrometry (MS) technology, protein expression and post-translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of abstraction from data, and it thrives in data-rich scientific research domains. Here, a comprehensive overview of deep learning applications in proteomics, including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex-peptide binding prediction, and protein structure prediction, is provided. Limitations and the future directions of deep learning in proteomics are also discussed. This review will provide readers an overview of deep learning and how it can be used to analyze proteomics data.