Fragment Mass Spectrum Prediction Facilitates Site Localization of Phosphorylation

Prediction of glycopeptide fragment mass spectra by deep learning

Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact glycopeptide. Herein, we present DeepGlyco, a deep learning-based approach for the prediction of fragment spectra of intact glycopeptides. Our model adopts tree-structured long-short term memory networks to process the glycan moiety and a graph neural network architecture to incorporate potential fragmentation pathways of a specific glycan structure. This feature is beneficial to model explainability and differentiation ability of glycan structural isomers. We further demonstrate that predicted spectral libraries can be used for data-independent acquisition glycoproteomics as a supplement for library completeness. We expect that this work will provide a valuable deep learning resource for glycoproteomics.

Deep Learning Prediction Boosts Phosphoproteomics-Based Discoveries Through Improved Phosphopeptide Identification

Shotgun phosphoproteomics enables high-throughput analysis of phosphopeptides in biological samples. One of the primary challenges associated with this technology is the relatively low rate of phosphopeptide identification during data analysis. This limitation hampers the full realization of the potential offered by shotgun phosphoproteomics. Here we present DeepRescore2, a computational workflow that leverages deep learning-based retention time and fragment ion intensity predictions to improve phosphopeptide identification and phosphosite localization. Using a state-of-the-art computational workflow as a benchmark, DeepRescore2 increases the number of correctly identified peptide-spectrum matches by 17% in a synthetic dataset and identifies 19% to 46% more phosphopeptides in biological datasets. In a liver cancer dataset, 30% of the significantly altered phosphosites between tumor and normal tissues and 60% of the prognosis-associated phosphosites identified from DeepRescore2-processed data could not be identified based on the state-of-the-art workflow. Notably, DeepRescore2-processed data uniquely identifies EGFR hyperactivation as a new target in poor-prognosis liver cancer, which is validated experimentally. Integration of deep learning prediction in DeepRescore2 improves phosphopeptide identification and facilitates biological discoveries.

Acquisition and Analysis of DIA-Based Proteomic Data: A Comprehensive Survey in 2023

Data-independent acquisition (DIA) mass spectrometry (MS) has emerged as a powerful technology for high-throughput, accurate, and reproducible quantitative proteomics. This review provides a comprehensive overview of recent advances in both the experimental and computational methods for DIA proteomics, from data acquisition schemes to analysis strategies and software tools. DIA acquisition schemes are categorized based on the design of precursor isolation windows, highlighting wide-window, overlapping-window, narrow-window, scanning quadrupole-based, and parallel accumulation-serial fragmentation-enhanced DIA methods. For DIA data analysis, major strategies are classified into spectrum reconstruction, sequence-based search, library-based search, de novo sequencing, and sequencing-independent approaches. A wide array of software tools implementing these strategies are reviewed, with details on their overall workflows and scoring approaches at different steps. The generation and optimization of spectral libraries, which are critical resources for DIA analysis, are also discussed. Publicly available benchmark datasets covering global proteomics and phosphoproteomics are summarized to facilitate performance evaluation of various software tools and analysis workflows. Continued advances and synergistic developments of versatile components in DIA workflows are expected to further enhance the power of DIA-based proteomics.

Principles of phosphoproteomics and applications in cancer research

Phosphorylation constitutes the most common and best-studied regulatory post-translational modification in biological systems and archetypal signalling pathways driven by protein and lipid kinases are disrupted in essentially all cancer types. Thus, the study of the phosphoproteome stands to provide unique biological information on signalling pathway activity and on kinase network circuitry that is not captured by genetic or transcriptomic technologies. Here, we discuss the methods and tools used in phosphoproteomics and highlight how this technique has been used, and can be used in the future, for cancer research. Challenges still exist in mass spectrometry phosphoproteomics and in the software required to provide biological information from these datasets. Nevertheless, improvements in mass spectrometers with enhanced scan rates, separation capabilities and sensitivity, in biochemical methods for sample preparation and in computational pipelines are enabling an increasingly deep analysis of the phosphoproteome, where previous bottlenecks in data acquisition, processing and interpretation are being relieved. These powerful hardware and algorithmic innovations are not only providing exciting new mechanistic insights into tumour biology, from where new drug targets may be derived, but are also leading to the discovery of phosphoproteins as mediators of drug sensitivity and resistance and as classifiers of disease subtypes. These studies are, therefore, uncovering phosphoproteins as a new generation of disruptive biomarkers to improve personalised anti-cancer therapies.

Deep learning prediction boosts phosphoproteomics-based discoveries through improved phosphopeptide identification

Shotgun phosphoproteomics enables high-throughput analysis of phosphopeptides in biological samples, but low phosphopeptide identification rate in data analysis limits the potential of this technology. Here we present DeepRescore2, a computational workflow that leverages deep learning-based retention time and fragment ion intensity predictions to improve phosphopeptide identification and phosphosite localization. Using a state-of-the-art computational workflow as a benchmark, DeepRescore2 increases the number of correctly identified peptide-spectrum matches by 17% in a synthetic dataset and identifies 19%-46% more phosphopeptides in biological datasets. In a liver cancer dataset, 30% of the significantly altered phosphosites between tumor and normal tissues and 60% of the prognosis-associated phosphosites identified from DeepRescore2-processed data could not be identified based on the state-of-the-art workflow. Notably, DeepRescore2-processed data uniquely identifies EGFR hyperactivation as a new target in poor-prognosis liver cancer, which is validated experimentally. Integration of deep learning prediction in DeepRescore2 improves phosphopeptide identification and facilitates biological discoveries.

Prediction of peptide mass spectral libraries with machine learning

The recent development of machine learning methods to identify peptides in complex mass spectrometric data constitutes a major breakthrough in proteomics. Longstanding methods for peptide identification, such as search engines and experimental spectral libraries, are being superseded by deep learning models that allow the fragmentation spectra of peptides to be predicted from their amino acid sequence. These new approaches, including recurrent neural networks and convolutional neural networks, use predicted in silico spectral libraries rather than experimental libraries to achieve higher sensitivity and/or specificity in the analysis of proteomics data. Machine learning is galvanizing applications that involve large search spaces, such as immunopeptidomics and proteogenomics. Current challenges in the field include the prediction of spectra for peptides with post-translational modifications and for cross-linked pairs of peptides. Permeation of machine-learning-based spectral prediction into search engines and spectrum-centric data-independent acquisition workflows for diverse peptide classes and measurement conditions will continue to push sensitivity and dynamic range in proteomics applications in the coming years.

Comparative Assessment of Quantification Methods for Tumor Tissue Phosphoproteomics

With increasing sensitivity and accuracy in mass spectrometry, the tumor phosphoproteome is getting into reach. However, the selection of quantitation techniques best-suited to the biomedical question and diagnostic requirements remains a trial and error decision as no study has directly compared their performance for tumor tissue phosphoproteomics. We compared label-free quantification (LFQ), spike-in-SILAC (stable isotope labeling by amino acids in cell culture), and tandem mass tag (TMT) isobaric tandem mass tags technology for quantitative phosphosite profiling in tumor tissue. Compared to the classic SILAC method, spike-in-SILAC is not limited to cell culture analysis, making it suitable for quantitative analysis of tumor tissue samples. TMT offered the lowest accuracy and the highest precision and robustness toward different phosphosite abundances and matrices. Spike-in-SILAC offered the best compromise between these features but suffered from a low phosphosite coverage. LFQ offered the lowest precision but the highest number of identifications. Both spike-in-SILAC and LFQ presented susceptibility to matrix effects. Match between run (MBR)-based analysis enhanced the phosphosite coverage across technical replicates in LFQ and spike-in-SILAC but further reduced the precision and robustness of quantification. The choice of quantitative methodology is critical for both study design such as sample size in sample groups and quantified phosphosites and comparison of published cancer phosphoproteomes. Using ovarian cancer tissue as an example, our study builds a resource for the design and analysis of quantitative phosphoproteomic studies in cancer research and diagnostics.

Separation of Serum and Plasma Proteins for In-Depth Proteomic Analysis

There are probably no biological samples that did more to spur interest in proteomics than serum and plasma. The belief was that comparing the proteomes of these samples obtained from healthy and disease-affected individuals would lead to biomarkers that could be used to diagnose conditions such as cancer. While the continuing development of mass spectrometers with greater sensitivity and resolution has been invaluable, the invention of strategic strategies to separate circulatory proteins has been just as critical. Novel and creative separation techniques were required because serum and plasma probably have the greatest dynamic range of protein concentration of any biological sample. The concentrations of circulating proteins can range over twelve orders of magnitude, making it a challenge to identify low-abundance proteins where the bulk of the useful biomarkers are believed to exist. The major goals of this article are to (i) provide an historical perspective on the rapid development of serum and plasma proteomics; (ii) describe various separation techniques that have made obtaining an in-depth view of the proteome of these biological samples possible; and (iii) describe applications where serum and plasma proteomics have been employed to discover potential biomarkers for pathological conditions.

Deep learning approaches for data-independent acquisition proteomics

INTRODUCTION

Data-independent acquisition (DIA) is an emerging technology for large-scale proteomic studies. DIA data analysis methods are evolving rapidly, and deep learning has cut a conspicuous figure in this field.

AREAS COVERED

This review discusses and provides an overview of the deep learning methods that are used for DIA data analysis, including spectral library prediction, feature scoring, and statistical control in peptide-centric analysis, as well as de novo peptide sequencing. Literature searches were performed for articles, including preprints, up to December 2021 from PubMed, Scopus, and Web of Science databases.

EXPERT OPINION

While spectral library prediction has broken through the limitation on proteome coverage of experimental libraries, the statistical burden due to the large query space is the remaining challenge of utilizing proteome-wide predicted libraries. Analysis of post-translational modifications is another promising direction of deep learning-based DIA methods.

DeepPhospho accelerates DIA phosphoproteome profiling through in silico library generation

Phosphoproteomics integrating data-independent acquisition (DIA) enables deep phosphoproteome profiling with improved quantification reproducibility and accuracy compared to data-dependent acquisition (DDA)-based phosphoproteomics. DIA data mining heavily relies on a spectral library that in most cases is built on DDA analysis of the same sample. Construction of this project-specific DDA library impairs the analytical throughput, limits the proteome coverage, and increases the sample size for DIA phosphoproteomics. Herein we introduce a deep neural network, DeepPhospho, which conceptually differs from previous deep learning models to achieve accurate predictions of LC-MS/MS data for phosphopeptides. By leveraging in silico libraries generated by DeepPhospho, we establish a DIA workflow for phosphoproteome profiling which involves DIA data acquisition and data mining with DeepPhospho predicted libraries, thus circumventing the need of DDA library construction. Our DeepPhospho-empowered workflow substantially expands the phosphoproteome coverage while maintaining high quantification performance, which leads to the discovery of more signaling pathways and regulated kinases in an EGF signaling study than the DDA library-based approach. DeepPhospho is provided as a web server as well as an offline app to facilitate user access to model training, predictions and library generation.

Artificial intelligence for proteomics and biomarker discovery

There is an avalanche of biomedical data generation and a parallel expansion in computational capabilities to analyze and make sense of these data. Starting with genome sequencing and widely employed deep sequencing technologies, these trends have now taken hold in all omics disciplines and increasingly call for multi-omics integration as well as data interpretation by artificial intelligence technologies. Here, we focus on mass spectrometry (MS)-based proteomics and describe how machine learning and, in particular, deep learning now predicts experimental peptide measurements from amino acid sequences alone. This will dramatically improve the quality and reliability of analytical workflows because experimental results should agree with predictions in a multi-dimensional data landscape. Machine learning has also become central to biomarker discovery from proteomics data, which now starts to outperform existing best-in-class assays. Finally, we discuss model transparency and explainability and data privacy that are required to deploy MS-based biomarkers in clinical settings.

pDeepXL: MS/MS Spectrum Prediction for Cross-Linked Peptide Pairs by Deep Learning

In cross-linking mass spectrometry, the identification of cross-linked peptide pairs heavily relies on the ability of a database search engine to measure the similarities between experimental and theoretical MS/MS spectra. However, the lack of accurate ion intensities in theoretical spectra impairs the performance of search engines, in particular, on proteome scales. Here we introduce pDeepXL, a deep neural network to predict MS/MS spectra of cross-linked peptide pairs. To train pDeepXL, we used the transfer-learning technique because it facilitated the training with limited benchmark data of cross-linked peptide pairs. Test results on more than ten data sets showed that pDeepXL accurately predicted the spectra of both noncleavable DSS/BS3/Leiker cross-linked peptide pairs (>80% of predicted spectra have Pearson's r values higher than 0.9) and cleavable DSSO/DSBU cross-linked peptide pairs (>75% of predicted spectra have Pearson's r values higher than 0.9). pDeepXL also achieved the accurate prediction on unseen data sets using an online fine-tuning technique. Lastly, integrating pDeepXL into a database search engine increased the number of identified cross-link spectra by 18% on average.

Data-independent acquisition method for ubiquitinome analysis reveals regulation of circadian biology

Protein ubiquitination is involved in virtually all cellular processes. Enrichment strategies employing antibodies targeting ubiquitin-derived diGly remnants combined with mass spectrometry (MS) have enabled investigations of ubiquitin signaling at a large scale. However, so far the power of data independent acquisition (DIA) with regards to sensitivity in single run analysis and data completeness have not yet been explored. Here, we develop a sensitive workflow combining diGly antibody-based enrichment and optimized Orbitrap-based DIA with comprehensive spectral libraries together containing more than 90,000 diGly peptides. This approach identifies 35,000 diGly peptides in single measurements of proteasome inhibitor-treated cells - double the number and quantitative accuracy of data dependent acquisition. Applied to TNF signaling, the workflow comprehensively captures known sites while adding many novel ones. An in-depth, systems-wide investigation of ubiquitination across the circadian cycle uncovers hundreds of cycling ubiquitination sites and dozens of cycling ubiquitin clusters within individual membrane protein receptors and transporters, highlighting new connections between metabolism and circadian regulation.