Deep learning boosts sensitivity of mass spectrometry-based immunopeptidomics.
Ontology highlight
ABSTRACT:
SUBMITTER: Wilhelm M
PROVIDER: S-EPMC8184761 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: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 such non-tryptic peptides presents substantial computational challenges. To address these, we synthesized >300,000 peptides within the ProteomeTools project representing HLA class I & II ligands and products of the proteases AspN and LysN and analyzed these by multi-modal LC-MS/MS. The resulting data enabled training of a single model using the deep learning framework Prosit that shows outstanding prediction accuracy of fragment ion spectra for tryptic and non-tryptic peptides. Applying Prosit demonstrates that the identification of HLA peptides can be improved by 50-300% on average, that proteasomal HLA peptide splicing may not exist and that additional neo-epitopes that elicit an immune response can be identified from patient tumors. Together, the provided peptides, spectra and computational tools substantially expand the scope of immunopeptidomics workflows.
2021-04-26 | PXD021398 | Pride
Project description:The presentation of peptides on class I human leukocyte antigen (HLA-I) molecules plays a central role in immune recognition of infected or malignant cells. In cancer, non-self HLA-I ligands can arise from many different alterations, including non-synonymous mutations, gene fusion, cancer-specific alternative mRNA splicing or aberrant post-translational modifications. Identifying HLA-I ligands remains a challenging task that requires either heavy experimental work for in vivo identification or optimized bioinformatics tools for accurate predictions. To date, no HLA-I ligand predictor includes post-translational modifications. To fill this gap, we curated phosphorylated HLA-I ligands from several immunopeptidomics studies (including six newly measured samples) covering 72 HLA-I alleles and retrieved a total of 2,066 unique phosphorylated peptides. We then expanded our motif deconvolution tool to identify precise binding motifs of phosphorylated HLA-I ligands. Our results reveal a clear enrichment of phosphorylated peptides among HLA-C ligands and demonstrate a prevalent role of both HLA-I motifs and kinase motifs on the presentation of phosphorylated peptides. These data further enabled us to develop and validate the first predictor of interactions between HLA-I molecules and phosphorylated peptides.
| S-EPMC7000122 | biostudies-literature
Project description:Immunopeptidomes are the peptide repertoires bound by the molecules encoded by the major histocompatibility complex [human leukocyte antigen (HLA) in humans]. These HLA-peptide complexes are presented on the cell surface for immune T-cell recognition. Immunopeptidomics denotes the utilization of tandem mass spectrometry to identify and quantify peptides bound to HLA molecules. Data-independent acquisition (DIA) has emerged as a powerful strategy for quantitative proteomics and deep proteome-wide identification; however, DIA application to immunopeptidomics analyses has so far seen limited use. Further, of the many DIA data processing tools currently available, there is no consensus in the immunopeptidomics community on the most appropriate pipeline(s) for in-depth and accurate HLA peptide identification. Herein, we benchmarked four commonly used spectral library-based DIA pipelines developed for proteomics applications (Skyline, Spectronaut, DIA-NN, and PEAKS) for their ability to perform immunopeptidome quantification. We validated and assessed the capability of each tool to identify and quantify HLA-bound peptides. Generally, DIA-NN and PEAKS provided higher immunopeptidome coverage with more reproducible results. Skyline and Spectronaut conferred more accurate peptide identification with lower experimental false-positive rates. All tools demonstrated reasonable correlations in quantifying precursors of HLA-bound peptides. Our benchmarking study suggests a combined strategy of applying at least two complementary DIA software tools to achieve the greatest degree of confidence and in-depth coverage of immunopeptidome data.
| S-EPMC10060114 | biostudies-literature
Project description:The identification of major histocompatibility complex (MHC)-binding peptides in mass spectrometry (MS)-based immunopeptideomics relies largely on database search engines developed for proteomics data analysis. However, because immunopeptidomics experiments do not involve enzymatic digestion at specific residues, an inflated search space leads to a high false positive rate and low sensitivity in peptide identification. In order to improve the sensitivity and reliability of peptide identification, a post-processing tool named DeepRescore is developed. DeepRescore combines peptide features derived from deep learning predictions, namely accurate retention timeand MS/MS spectra predictions, with previously used features to rescore peptide-spectrum matches. Using two public immunopeptidomics datasets, it is shown that rescoring by DeepRescore increases both the sensitivity and reliability of MHC-binding peptide and neoantigen identifications compared to existing methods. It is also shown that the performance improvement is, to a large extent, driven by the deep learning-derived features. DeepRescore is developed using NextFlow and Docker and is available at https://github.com/bzhanglab/DeepRescore.
| S-EPMC7718998 | biostudies-literature
Project description: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.
| S-EPMC10831110 | biostudies-literature
Project description:Quantitative mass-spectrometry-based methods to perform relative and absolute quantification of peptides in the immunopeptidome are growing in popularity as researchers aim to measure the dynamic nature of the peptide major histocompatibility complex repertoire and make copies-per-cell estimations of target antigens of interest. Multiple methods to carry out these experiments have been reported, each with unique advantages and limitations. This article describes existing methods and recent applications, offering guidance for improving quantitative accuracy and selecting an appropriate experimental set-up to maximize data quality and quantity.
| S-EPMC9216433 | biostudies-literature
Project description: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.
| S-EPMC11208500 | biostudies-literature
Project description:Mass spectrometry imaging (MSI) is a high-throughput imaging technique capable of the qualitative and quantitative in situ detection of thousands of ions in biological samples. Ion image representation is a technique that produces a low-dimensional vector embedded with significant spectral and spatial information on an ion image, which further facilitates the distance-based similarity measurement for the identification of colocalized ions. However, given the low signal-to-noise ratios inherent in MSI data coupled with the scarcity of annotated data sets, achieving an effective ion image representation for each ion image remains a challenge. In this study, we propose DeepION, a novel deep learning-based method designed specifically for ion image representation, which is applied to the identification of colocalized ions and isotope ions. In DeepION, contrastive learning is introduced to ensure that the model can generate the ion image representation in a self-supervised manner without manual annotation. Since data augmentation is a crucial step in contrastive learning, a unique data augmentation strategy is designed by considering the characteristics of MSI data, such as the Poisson distribution of ion abundance and a random pattern of missing values, to generate plentiful ion image pairs for DeepION model training. Experimental results of rat brain tissue MSI show that DeepION outperforms other methods for both colocalized ion and isotope ion identification, demonstrating the effectiveness of ion image representation. The proposed model could serve as a crucial tool in the biomarker discovery and drug development of the MSI technique.
| S-EPMC10918617 | biostudies-literature
Project description:Understanding the properties of human leukocyte antigen (HLA) peptides (immunopeptides) is essential for precision cancer medicine, while the direct identification of immunopeptides from small biopsies of clinical tissues by mass spectrometry (MS) is still confronted with technical challenges. Here, to overcome these hindrances, high-field asymmetric waveform ion mobility spectrometry (FAIMS) is introduced to conduct differential ion mobility (DIM)-MS by seamless gas-phase fractionation optimal for scarce samples. By established DIM-MS for immunopeptidomics analysis, on average, 42.9 mg of normal and tumor colorectal tissues from identical patients (n = 17) were analyzed, and on average 4921 immunopeptides were identified. Among these 44,815 unique immunopeptides, two neoantigens, KRAS-G12V and CPPED1-R228Q, were identified. These neoantigens were confirmed by synthetic peptides through targeted MS in parallel reaction monitoring (PRM) mode. Comparison of the tissue-based personal immunopeptidome revealed tumor-specific processing of immunopeptides. Since the direct identification of neoantigens from tumor tissues suggested that more potential neoantigens have yet to be identified, we screened cell lines with known oncogenic KRAS mutations and identified 2 more neoantigens that carry KRAS-G12V. These results indicated that the established FAIMS-assisted DIM-MS is effective in the identification of immunopeptides and potential recurrent neoantigens directly from scarce samples such as clinical tissues.
| S-EPMC9388627 | biostudies-literature
Project description:SummaryIn recent years, SWATH-MS has become the proteomic method of choice for data-independent-acquisition, as it enables high proteome coverage, accuracy and reproducibility. However, data analysis is convoluted and requires prior information and expert curation. Furthermore, as quantification is limited to a small set of peptides, potentially important biological information may be discarded. Here we demonstrate that deep learning can be used to learn discriminative features directly from raw MS data, eliminating hence the need of elaborate data processing pipelines. Using transfer learning to overcome sample sparsity, we exploit a collection of publicly available deep learning models already trained for the task of natural image classification. These models are used to produce feature vectors from each mass spectrometry (MS) raw image, which are later used as input for a classifier trained to distinguish tumor from normal prostate biopsies. Although the deep learning models were originally trained for a completely different classification task and no additional fine-tuning is performed on them, we achieve a highly remarkable classification performance of 0.876 AUC. We investigate different types of image preprocessing and encoding. We also investigate whether the inclusion of the secondary MS2 spectra improves the classification performance. Throughout all tested models, we use standard protein expression vectors as gold standards. Even with our naïve implementation, our results suggest that the application of deep learning and transfer learning techniques might pave the way to the broader usage of raw mass spectrometry data in real-time diagnosis.Availability and implementationThe open source code used to generate the results from MS images is available on GitHub: https://ibm.biz/mstransc. The raw MS data underlying this article cannot be shared publicly for the privacy of individuals that participated in the study. Processed data including the MS images, their encodings, classification labels and results can be accessed at the following link: https://ibm.box.com/v/mstc-supplementary.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8275322 | biostudies-literature