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: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: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: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
Project description:Retinoblastoma (RB) is an intraocular childhood tumor which, if left untreated, leads to blindness and mortality. Nucleolin (NCL) protein which is differentially expressed on the tumor cell surface, binds ligands and regulates carcinogenesis and angiogenesis. We found that NCL is over expressed in RB tumor tissues and cell lines compared to normal retina. We studied the effect of nucleolin-aptamer (NCL-APT) to reduce proliferation in RB tumor cells. Aptamer treatment on the RB cell lines (Y79 and WERI-Rb1) led to significant inhibition of cell proliferation. Locked nucleic acid (LNA) modified NCL-APT administered subcutaneously (s.c.) near tumor or intraperitoneally (i.p.) in Y79 xenografted nude mice resulted in 26 and 65% of tumor growth inhibition, respectively. Downregulation of inhibitor of apoptosis proteins, tumor miRNA-18a, altered serum cytokines, and serum miRNA-18a levels were observed upon NCL-APT treatment. Desorption electrospray ionization mass spectrometry (DESI MS)-based imaging of cell lines and tumor tissues revealed changes in phosphatidylcholines levels upon treatment. Thus, our study provides proof of concept illustrating NCL-APT-based targeted therapeutic strategy and use of DESI MS-based lipid imaging in monitoring therapeutic responses in RB.
2016-11-15 | GSE89818 | GEO
Project description:Computational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction. The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, is used to cluster ion images based on spatial expressions. We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters. Additionally, we introduce the relative isotope ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes. The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.
| S-EPMC8007517 | biostudies-literature
Project description:Methanococcus maripaludis is a methanogenic archaeon. Within its genome, there are two operons for membrane associated hydrogenases, eha and ehb. To investigate the regulation of ehb on the cell, an S40 mutant was constructed in such a way that a portion of the ehb operon was replaced by pac cassette in the wild type parental strain S2 (done by Whitman's group at the University of Georgia). The S40 and S2 strains were grown in 14N and 15N media with acetate separately. A biological replicate was made by switching the media. Mass spectrometry based quantitative proteomics were done on the mixtures to investigate the differences in expression patterns between S40 and S2. Keywords: isotope labeling mass spectrometry, quantitative proteomics
2005-09-20 | GSE2744 | GEO
Project description:Highly multiplexed imaging technology is a powerful tool to facilitate understanding the composition and interactions of cells in tumor microenvironments at subcellular resolution, which is crucial for both basic research and clinical applications. Imaging mass cytometry (IMC), a multiplex imaging method recently introduced, can measure up to 100 markers simultaneously in one tissue section by using a high-resolution laser with a mass cytometer. However, due to its high resolution and large number of channels, how to process and interpret the image data from IMC remains a key challenge to its further applications. Accurate and reliable single cell segmentation is the first and a critical step to process IMC image data. Unfortunately, existing segmentation pipelines either produce inaccurate cell segmentation results or require manual annotation, which is very time consuming. Here, we developed Dice-XMBD, a Deep learnIng-based Cell sEgmentation algorithm for tissue multiplexed imaging data. In comparison with other state-of-the-art cell segmentation methods currently used for IMC images, Dice-XMBD generates more accurate single cell masks efficiently on IMC images produced with different nuclear, membrane, and cytoplasm markers. All codes and datasets are available at https://github.com/xmuyulab/Dice-XMBD.
| S-EPMC8480472 | biostudies-literature
Project description:PurposeDeep-learning-based segmentation models implicitly learn to predict the presence of a structure based on its overall prominence in the training dataset. This phenomenon is observed and accounted for in deep-learning applications such as natural language processing but is often neglected in segmentation literature. The purpose of this work is to demonstrate the significance of class imbalance in deep-learning-based segmentation and recommend tuning of the neural network optimization objective.MethodsAn architecture and training procedure were chosen to represent common models in anatomical segmentation. A family of 5-block 2D U-Nets were independently trained to segment 10 structures from the Cancer Imaging Archive's Head-Neck-Radiomics-HN1 dataset. We identify the optimal threshold for our models according to their Dice score on the validation datasets and consider perturbations about the optimum. A measure of structure prominence in segmentation datasets is defined, and its impact on the optimal threshold is analyzed. Finally, we consider the use of a 2D Dice objective in addition to binary cross entropy.ResultsWe observe significant decreases in perceived model performance with conventional 0.5-thresholding. Perturbations of as little as ±0.05 about the optimum threshold induce a median reduction in Dice score of 11.8% for our models. There is statistical evidence to suggest a weak correlation between training dataset prominence and optimal threshold (Pearson r=0.92 and p≈10-4 ). We find that network optimization with respect to the 2D Dice score itself significantly reduces variability due to thresholding but does not unequivocally create the best segmentation models when assessed with distance-based segmentation metrics.ConclusionOur results suggest that those practicing deep-learning-based contouring should consider their postprocessing procedures as a potential avenue for improved performance. For intensity-based postprocessing, we recommend a mixed objective function consisting of the traditional binary cross entropy along with the 2D Dice score.
| S-EPMC8364283 | biostudies-literature