Biology subjects

Nielsen, M.

Publications and source records attributed to Nielsen, M..

At least 55 records · Page 3Linked to original sources

bioRxiv2021

APRANK: computational prioritization of antigenic proteins and peptides from complete pathogen proteomes

Availability of highly parallelized immunoassays has renewed interest in the discovery of serology biomarkers for infectious diseases. Protein and peptide microarrays now provide a rapid, high-throughput platform for immunological testing and validation of potential antigens and B-cell epitopes. However, there is still a need for tools to prioritize and select relevant probes when designing these arrays. In this work we describe a computational method called APRANK (Antigenic Protein and Peptide Ranker) which integrates multiple molecular features to prioritize antigenic targets in a given pathogen proteome. These features include subcellular localization, presence of repetitive motifs, natively disordered regions, secondary structure, transmembrane spans and predicted interaction with the immune system. We applied this method to prioritize potentially antigenic proteins and peptides in a number of bacteria and protozoa causing human diseases: Borrelia burgdorferi (Lyme disease), Brucella melitensis (Brucellosis), Coxiella burnetii (Q fever), Escherichia coli (Gastroenteritis), Francisella tularensis (Tularemia), Leishmania braziliensis (Leishmaniasis), Leptospira interrogans (Leptospirosis), Mycobacterium leprae (Leprae), Mycobacterium tuberculosis (Tuberculosis), Plasmodium falciparum (Malaria), Porphyromonas gingivalis (Periodontal disease), Staphylococcus aureus (Bacteremia), Streptococcus pyogenes (Group A Streptococcal infections), Toxoplasma gondii (Toxoplasmosis) and Trypanosoma cruzi (Chagas Disease). We have tested this integrative method using non-parametric ROC-curves and made an unbiased validation using an independent data set. We found that APRANK is successful in predicting antigenicity for all pathogen species tested, facilitating the production of antigen-enriched protein subsets. We make APRANK available to facilitate the identification of novel diagnostic antigens in infectious diseases.

immunology↗

bioRxiv2020

Integral use of immunopeptidomics and immunoinformatics for the characterization of antigen presentation and rational identification of BoLA-DR-presented peptides and epitopes

Major histocompatibility complex (MHC) peptide binding and presentation is the most selective event defining the landscape of T cell epitopes. Consequently, understanding the diversity of MHC alleles in a given population and the parameters that define the set of ligands that can be bound and presented by each of these alleles (the immunopeptidome) has an enormous impact on our capacity to predict and manipulate the potential of protein antigens to elicit functional T cell responses. Liquid chromatography-mass spectrometry (LC-MS) analysis of MHC eluted ligands (EL data) has proven to be a powerful technique for identifying such peptidomes, and methods integrating such data for prediction of antigen presentation have reached a high level of accuracy for both MHC class I and class II. Here, we demonstrate how these techniques and prediction methods can be readily extended to the bovine leukocyte antigen class II DR locus (BoLA-DR). BoLA-DR binding motifs were characterized by EL data derived from cell lines expressing a range of DRB3 alleles prevalent in Holstein-Friesian populations. The model generated (NetBoLAIIpan - available as a web-server at www.cbs.dtu.dk/services/NetBoLAIIpan) was shown to have unprecedented predictive power to identify known BoLA-DR restricted CD4 epitopes. In summary, the results demonstrate the power of an integrated approach combining advanced MS peptidomics with immunoinformatics for characterization of the BoLA-DR antigen presentation system and provide a novel tool that can be utilised to assist in rational evaluation and selection of bovine CD4 T cell epitopes.

bioinformatics↗

bioRxiv2020

TCRMatch: Predicting T-cell receptor specificity based on sequence similarity to previously characterized receptors

The adaptive immune system in vertebrates has evolved to recognize non-self-antigens, such as proteins expressed by infectious agents and mutated cancer cells. T cells play an important role in antigen recognition by expressing a diverse repertoire of antigen-specific receptors, which bind epitopes to mount targeted immune responses. Recent advances in high-throughput sequencing have enabled the routine generation of T-cell receptor (TCR) repertoire data. Identifying the specific epitopes targeted by different TCRs in these data would be valuable. To accomplish that, we took advantage of the ever-increasing number of TCRs with known epitope specificity curated in the Immune Epitope Database (IEDB) since 2004. We compared six metrics of sequence similarity to determine their power to predict if two TCRs have the same epitope specificity. We found that a comprehensive k-mer matching approach produced the best results, which we have implemented into TCRMatch, an openly accessible tool (http://tools.iedb.org/tcrmatch/) that takes TCR {beta}-chain CDR3 sequences as an input, identifies TCRs with a match in the IEDB, and reports the specificity of each match. We anticipate that this tool will provide new insights into T cell responses captured in receptor repertoire and single cell sequencing experiments and will facilitate the development of new strategies for monitoring and treatment of infectious, allergic, and autoimmune diseases, as well as cancer.

immunology↗

bioRxiv2020

Combined assessment of MHC binding and antigen expression improves T cell epitope predictions

MHC class I antigen processing consists of multiple steps that result in the presentation of MHC bound peptides that can be recognized as T cell epitopes. Many of the pathway steps can be predicted using computational methods, but one is often neglected: mRNA expression of the epitope source proteins. In this study, we improve epitope prediction by taking into account both peptide-MHC binding affinities and expression levels of the peptides source protein. Specifically, we utilized biophysical principles and existing MHC binding prediction tools in concert with RNA expression to derive a function that estimates the likelihood of a peptide being presented on a given MHC class I molecule. Our combined model of Antigen eXpression based Epitope Likelihood-Function (AXEL-F) outperformed predictions based only on binding or based only on antigen expression for discriminating eluted ligands from random background peptides as well as in predicting neoantigens that are recognized by T cells. We also showed that in cases where cancer patient-specific RNA-Seq data is not available, cancer-type matched expression data from TCGA can be used to accurately estimate patient-specific gene expression. Using AXEL-F together with TGCA expression data we were able to more accurately predict neoantigens that are recognized by T cells. The method is available in the IEDB Analysis Resource and free to use for the academic community. Significance statementEpitope prediction tools have been used to call epitopes in viruses and other pathogens for almost 30 years, and more recently, to call cancer neoantigens. Several such tools have been developed, however most of them ignore the mRNA expression of the epitope source proteins. In the present study, we have, to our knowledge for the first time, developed a biophysically motivated model to combine peptide-MHC binding and abundance of the peptides source protein to improve epitope predictions. Our novel tool AXEL-F is freely available on the IEDB and presents a clear opportunity for predicting and selecting epitopes more efficiently.

bioinformatics↗

bioRxiv2020

SARS-CoV-2 genome-wide mapping of CD8 T cell recognition reveals strong immunodominance and substantial CD8 T cell activation in COVID-19 patients

To understand the CD8+ T cell immunity related to viral protection and disease severity in COVID-19, we evaluated the complete SARS-CoV-2 genome (3141 MHC-I binding peptides) to identify immunogenic T cell epitopes, and determine the level of CD8+ T cell involvement using DNA-barcoded peptide-major histocompatibility complex (pMHC) multimers. COVID-19 patients showed strong T cell responses, with up to 25% of all CD8+ lymphocytes specific to SARS-CoV-2-derived immunodominant epitopes, derived from ORF1 (open reading frame 1), ORF3, and Nucleocapsid (N) protein. A strong signature of T cell activation was observed in COVID-19 patients, while no T cell activation was seen in the non-exposed and high exposure risk healthy donors. Interestingly, patients with severe disease displayed the largest T cell populations with a strong activation profile. These results will have important implications for understanding the T cell immunity to SARS-CoV-2 infection, and how T cell immunity might influence disease development.

immunology↗

bioRxiv2020

Sampling SARS-CoV-2 proteomes for predicted CD8 T-cell epitopes as a tool for understanding immunogenic breadth and rationale vaccine design

Predictive models for vaccine design have become a powerful and necessary resource for the expeditiousness design of vaccines to combat the ongoing SARS-CoV-2 global pandemic. Here we use the power of these predicted models to assess the sequence diversity of circulating SARS-CoV-2 proteomes in the context of an individuals CD8 T-cell immune repertoire to identify potential. defined regions of immunogenicity. Using this approach of expedited and rational CD8 T-cell vaccine design, it may be possible to develop a therapeutic vaccine candidate with the potential for both global and local coverage.

immunology↗

bioRxiv2020

Utilizing Computational Machine Learning Tools to Understand Immunogenic Breadth in the Context of a CD8 T-Cell Mediated HIV Response

Predictive models are becoming more and more commonplace as tools for candidate antigen discovery to meet the challenges of enabling epitope mapping of cohorts with diverse HLA properties. Here we build on the concept of using two key parameters, diversity metric of the HLA profile of individuals within a population and consideration of sequence diversity in the context of an individuals CD8 T-cell immune repertoire to assess the HIV proteome for defined regions of immunogenicity. Using this approach, Analysis of HLA adaptation and functional immunogenicity data enabled the identification of regions within the proteome that offer significant conservation, HLA recognition within a population, low prevalence of HLA adaptation and demonstrated immunogenicity. We believe this unique and novel approach to vaccine design that, in combination with in vitro functional assays, offers a bespoke pipeline for expedited and rational CD8 T-cell vaccine design for HIV and potentially other pathogens with the potential for both global and local coverage.

immunology↗

bioRxiv2020

Robust T cell immunity in convalescent individuals with asymptomatic or mild COVID-19

ABSTRACTSARS-CoV-2-specific memory T cells will likely prove critical for long-term immune protection against COVID-19. We systematically mapped the functional and phenotypic landscape of SARS-CoV-2-specific T cell responses in a large cohort of unexposed individuals as well as exposed family members and individuals with acute or convalescent COVID-19. Acute phase SARS-CoV-2-specific T cells displayed a highly activated cytotoxic phenotype that correlated with various clinical markers of disease severity, whereas convalescent phase SARS-CoV-2-specific T cells were polyfunctional and displayed a stem-like memory phenotype. Importantly, SARS-CoV-2-specific T cells were detectable in antibody-seronegative family members and individuals with a history of asymptomatic or mild COVID-19. Our collective dataset shows that SARS-CoV-2 elicits robust memory T cell responses akin to those observed in the context of successful vaccines, suggesting that natural exposure or infection may prevent recurrent episodes of severe COVID-19 also in seronegative individuals.Competing Interest StatementThe authors have declared no competing interest.View Full Text

immunology↗

bioRxiv2020

A systematic, unbiased mapping of CD8+ and CD4+ T cell epitopes in Yellow Fever vaccinees

1.Examining CD8+ and CD4+ T cell responses after primary Yellow Fever vaccination in a cohort of 210 volunteers, we have identified and tetramer-validated 92 CD8+ and 50 CD4+ T cell epitopes, many inducing strong and prevalent (i.e. immunodominant) T cell responses. Restricted by 40 and 14 HLA-class I and II allotypes, respectively, these responses have wide population coverage and might be of considerable academic, diagnostic and therapeutic interest. The broad coverage of epitopes and HLA overcame the otherwise confounding effects of HLA diversity and non-HLA background providing the first evidence of T cell immunodomination in humans. Also, double-staining of CD4+ T cells with tetramers representing the same HLA-binding core, albeit with different flanking regions, demonstrated an extensive diversification of the specificities of many CD4+ T cell responses. We suggest that this could reduce the risk of pathogen escape, and that multi-tetramer staining is required to reveal the true magnitude and diversity of CD4+ T cell responses. Our T cell epitope discovery approach uses a combination of 1) overlapping peptides representing the entire Yellow Fever virus proteome to search for peptides containing CD4+ and/or CD8+ T cell epitopes, 2) predictors of peptide-HLA binding to suggest epitopes and their restricting HLA allotypes, 3) generation of peptide-HLA tetramers to identify T cell epitopes, and 4) analysis of ex vivo T cell responses to validate the same. This approach is systematic, exhaustive, and can be done in any individual of any HLA haplotype. It is all-inclusive in the sense that it includes all protein antigens and peptide epitopes, and encompasses both CD4+ and CD8+ T cell epitopes. It is efficient and, importantly, reduces the false discovery rate. The unbiased nature of the T cell epitope discovery approach presented here should support the refinement of future peptide-HLA class I and II predictors and tetramer technologies, which eventually should cover all HLA class I and II isotypes. We believe that future investigations of emerging pathogens (e.g. SARS-CoV-2) should include population-wide T cell epitope discovery using blood samples from patients, convalescents and/or long-term survivors, who might all hold important information on T cell epitopes and responses.

immunology↗

bioRxiv2020

HLA-class II specificity assessed by high-density peptide microarray interactions

The ability to predict and/or identify MHC binding peptides is an essential component of T cell epitope discovery; something that ultimately should benefit the development of vaccines and immunotherapies. In particular, MHC class I (MHC-I) prediction tools have matured to a point where accurate selection of optimal peptide epitopes is possible for virtually all MHC-I allotypes; in comparison, current MHC class II (MHC-II) predictors are less mature. Since MHC-II restricted CD4+ T cells control and orchestrate most immune responses, this shortcoming severely hampers the development of effective immunotherapies. The ability to generate large panels of peptides and subsequently large bodies of peptide-MHC-II interaction data is key to the solution of this problem; a solution that also will support the improvement of bioinformatics predictors, which critically relies on the availability of large amounts of accurate, diverse and representative data. Here, we have used recombinant HLA-DRB1*01:01 and HLA-DRB1*03:01 molecules to interrogate high-density peptide arrays, in casu containing 70,000 random peptides in triplicates. We demonstrate that the binding data acquired contains systematic and interpretable information reflecting the specificity of the HLA-DR molecules investigated. Collectively, with a cost per peptide reduced to a few cents combined with the flexibility of recombinant HLA technology, this poses an attractive strategy to generate vast bodies of MHC-II binding data at an unprecedented speed and for the benefit of generating peptide-MHC-II binding data as well as improving MHC-II prediction tools.

immunology↗

bioRxiv2019

Improved prediction of MHC II antigen presentation throughintegration and motif deconvolution of mass spectrometryMHC eluted ligand data

Major Histocompatibility Complex II (MHC II) molecules play a vital role in the onset and control of cellular immunity. In a highly selective process, MHC II presents peptides derived from exogenous antigens on the surface of antigen-presenting cells for T cell scrutiny. Understanding the rules defining this presentation holds critical insights into the regulation and potential manipulation of the cellular immune system. Here, we apply the NNAlign_MA machine learning framework to analyse and integrate large-scale eluted MHC II ligand mass spectrometry (MS) data sets to advance prediction of CD4+ epitopes. NNAlign_MA allows integration of mixed data types, handling ligands with multiple potential allele annotations, encoding of ligand context, leveraging information between data sets, and has pan-specific power allowing accurate predictions outside the set of molecules included in the training data. Applying this framework, we identified accurate binding motifs of more than 50 MHC class II molecules described by MS data, particularly expanding coverage for DP and DQ beyond that obtained using current MS motif deconvolution techniques. Further, in large-scale benchmarking, the final model termed NetMHCIIpan-4.0, demonstrated improved performance beyond current state-of-the-art predictors for ligand and CD4+ T cell epitope prediction. These results suggest NNAlign_MA and NetMHCIIpan-4.0 are powerful tools for analysis of immunopeptidome MS data, prediction of T cell epitopes and development of personalized immunotherapies.

bioinformatics↗

bioRxiv2019

The shared neoantigen landscape of MSI cancers reflects immunoediting during tumor evolution

The immune system can recognize and attack cancer cells, especially those with a high load of mutation-induced neoantigens. Such neoantigens are particularly abundant in DNA mismatch repair (MMR)-deficient, microsatellite-unstable (MSI) cancers. MMR deficiency leads to insertion/deletion (indel) mutations at coding microsatellites (cMS) and to neoantigen-inducing translational frameshifts. The abundance of mutational neoantigens renders MSI cancers sensitive to immune checkpoint blockade. However, the neoantigen landscape of MMR-deficient cancers has not yet been systematically mapped. In the present study, we used a novel tool to monitor neoantigen-inducing indel mutations in MSI colorectal and endometrial cancer. Our results show that MSI cancers share several highly immunogenic neoantigens that result from specific, recurrent indel mutation events. Notably, the frequency of such indel mutations was negatively correlated to the predicted immunogenicity of the resulting neoantigens. These observations suggest continuous immunoediting of emerging MMR-deficient cells during tumor evolution.\n\nOne sentence summaryQuantitative indel mutation analysis reveals evidence of immune selection in mismatch repair-deficient cancers

cancer biology↗

bioRxiv2019

Benchmarking predictions of MHC class I restricted T cell epitopes

T cell epitope candidates are commonly identified using computational prediction tools in order to enable applications such as vaccine design, cancer neoantigen identification, development of diagnostics and removal of unwanted immune responses against protein therapeutics. Most T cell epitope prediction tools are based on machine learning algorithms trained on MHC binding or naturally processed MHC ligand elution data. The ability of currently available tools to predict T cell epitopes has not been comprehensively evaluated. In this study, we used a recently published dataset that systematically defined T cell epitopes recognized in vaccinia virus (VACV) infected mice, considering both peptides predicted to bind MHC or experimentally eluted from infected cells, making this the most comprehensive dataset of T cell epitopes mapped in a complex pathogen. We evaluated the performance of all currently publicly available computational T cell epitope prediction tools to identify these major epitopes from all peptides encoded in the VACV proteome. We found that all methods were able to improve epitope identification above random, with the best performance achieved by neural network-based predictions trained on both MHC binding and MHC ligand elution data (NetMHCPan-4.0 and MHCFlurry). Impressively, these methods were able to capture more than half of the major epitopes in the top 0.04% (N = 277) of peptides in the VACV proteome (N = 767,788). These performance metrics provide guidance for immunologists as to which prediction methods to use. In addition, this benchmark was implemented in an open and easy to reproduce format, providing developers with a framework for future comparisons against new tools.\n\nAuthor summaryComputational prediction tools are used to screen peptides to identify potential T cell epitope candidates. These tools, developed using machine learning methods, save time and resources in many immunological studies including vaccine discovery and cancer neoantigen identification. In addition to the already existing methods several epitope prediction tools are being developed these days but they lack a comprehensive and uniform evaluation to see which method performs best. In this study we did a comprehensive evaluation of publicly accessible MHC I restricted T cell epitope prediction tools using a recently published dataset of Vaccinia virus epitopes. We found that methods based on artificial neural network architecture and trained on both MHC binding and ligand elution data showed very high performance (NetMHCPan-4.0 and MHCFlurry). This benchmark analysis will help immunologists to choose the right prediction method for their desired work and will also serve as a framework for tool developers to evaluate new prediction methods.

immunology↗

bioRxiv2019

The Life History of Human Foraging: Cross-Cultural and Individual Variation

Human adaptation depends upon the integration of slow life history, complex production skills, and extensive sociality. Refining and testing models of the evolution of human life history and cultural learning will benefit from increasingly accurate measurement of knowledge, skills, and rates of production with age. We pursue this goal by inferring individual hunters of hunting skill gain and loss from approximately 23,000 hunting records generated by more than 1,800 individuals at 40 locations. The model provides an improved picture of ages of peak productivity as well as variation within and among ages. The data reveal an average age of peak productivity between 30 and 35 years of age, though high skill is maintained throughout much of adulthood. In addition, there is substantial variation both among individuals and sites. Within study sites, variation among individuals depends more upon heterogeneity in rates of decline than in rates of increase. This analysis sharpens questions about the co-evolution of human life history and cultural adaptation. It also demonstrates new statistical algorithms and models that expand the potential inferences drawn from detailed quantitative data collected in the field.

animal behavior and cognition↗

bioRxiv2019

NNAlign_MA; semi-supervised MHC peptidome deconvolution for accurate characterization of MHC binding motifs and improved T cell epitope prediction

Antigen presentation by Major Histocompatibility Complex (MHC) is a cornerstone of the cellular immune system, and characterization of the rules defining which peptides are suitable for MHC presentation is of key interest for understanding T cell immunogenicity and the development of T cell driven therapeutics. The collective set of peptides presented on a cell surface by MHC molecules is known as the immunopeptidome. Due to the vast MHC polymorphism, this peptidome is unique between individuals. Current state-of-the-art liquid chromatography mass spectrometry (LC-MS) technologies allow the identification of large peptidomes specific for a given host or cell line, and numerous studies have proven this data to be a rich source of information for learning the rules of MHC-mediated antigen presentation. The data obtained with MS techniques is usually poly-specific - i.e. it contains multiple sequence motifs matching the different MHC molecules expressed in the system under investigation. Deconvolution of this poly-specificity has proven a challenge, and imposes a substantial limitation for learning MHC specific rules for antigen presentation from immunopeptidome data. This since each ligand first must be unambiguously associated to its presenting MHC molecule(s) within the haplotype of the cell line. Here, we describe NNAlign_MA, a method that is able to address this challenge. NNAlign_MA is capable of taking a mixed training set composed of single-allele (SA) data (peptides assigned to single MHCs) and multi-allele (MA) data (peptides with multiple options for MHCs assignments) as input, and in a fully automated manner deconvolute the individual MHC restriction of all MA sequences while learning the binding specificities of all the MHCs present in the training set. The NNAlign_MA method was benchmarked on a large and diverse dataset, covering human MHC class I and class II, and bovine class I (BoLA) data. For all cases, the method was demonstrated to have unprecedented performance compared to state-of-the-art methods, achieving a complete deconvolution of binding motifs contained within poly-specificity MS eluted ligand data and an improved predictive performance for identification of both eluted ligands and T cell epitopes. Given its very high flexibility and ease of use, we expect NNAlign_MA to serve as an effective tool to increase our understanding of the rules for MHC antigen presentation and guide the development of novel T cell-based therapeutics.

bioinformatics↗

bioRxiv2018

Characterisation of antigenic MHC Class I-restricted T cell epitopes in the glycoprotein of Ebolavirus

Ebolavirus is a pathogen capable of causing highly lethal haemorrhagic fever in humans. The envelope-displayed viral glycoprotein is the primary target of humoral immunity induced by both natural exposure and vaccination. The epitopes targeted by B cells have been thoroughly characterised by functional and structural analyses of the glycoprotein, GP, yet there is a paucity of information regarding the cellular immune response to Ebolavirus. To date, no T cell epitopes in the glycoprotein have been characterised in detail in humans.\n\nA recent Phase I clinical trial of a heterologous prime-boost vaccination regime with viral vectors encoding filovirus antigens elicited strong humoral and T cell responses in vaccinees. Using samples from this trial, the most frequently recognised peptide pools were studied in more detail to identify the minimal epitopes recognised by antigen-specific T cells and associated HLA-restrictions.\n\nUsing IFN{gamma} ELISPOT and flow cytometry, we characterised nine highly immunogenic T cell epitopes located on both the GP1 and GP2 subunits of the Ebolavirus GP. Epitope mapping revealed the location of these epitopes as presented on the mature virion. HLA-typing on all participants, combined with in silico epitope analysis, determined the likely MHC class I restriction elements. Thirteen HLA-A and -B alleles were predicted to present the identified epitopes, suggesting promiscuous recognition and induction of a broad immune response.\n\nThe glycoprotein of Ebolavirus is highly immunogenic, inducing both CD4+ and CD8+ T cell responses and we have shown here for the first time that these responses are associated with multiple HLA types. Delivery of this antigen using a heterologous prime-boost approach with ChAd3 and MVA is likely to be highly immunogenic in genetically diverse human populations, due to the induction of responses against multiple immunodominant epitopes.\n\nAuthor SummaryThe West African Ebolavirus epidemic in 2013-2016 claimed more than 11,000 lives, eclipsing all previously recorded outbreaks combined. Understanding the mechanisms of host-pathogen interactions informs rational vaccine design. B cell epitopes have been described extensively through the characterisation of monoclonal antibodies from survivors of Ebolavirus disease. Despite a clear role for cellular immunity in survival of Ebolavirus disease, data relating to minimal T cell epitopes in the glycoprotein has so far only been obtained in murine. This study describes the first identification of human T cell epitopes in the surface glycoprotein of the Ebolavirus. These epitopes have been identified using samples from a clinical trial of viral vectored vaccines against the Zaire Ebolavirus undertaken during the 2013-2016 West African outbreak. We also describe the recognition of these epitopes through multiple HLA alleles. As efforts to progress a vaccine against Ebola towards licensure proceed, detailed characterisation of immunity to the virus contribute to our understanding of the potential application of vaccines in diverse populations.

immunology↗

bioRxiv2018

NetTCR: sequence-based prediction of TCR binding to peptide-MHC complexes using convolutional neural networks

Predicting epitopes recognized by cytotoxic T cells has been a long standing challenge within the field of immuno- and bioinformatics. While reliable predictions of peptide binding are available for most Major Histocompatibility Complex class I (MHCI) alleles, prediction models of T cell receptor (TCR) interactions with MHC class I-peptide complexes remain poor due to the limited amount of available training data. Recent next generation sequencing projects have however generated a considerable amount of data relating TCR sequences with their cognate HLA-peptide complex target. Here, we utilize such data to train a sequence-based predictor of the interaction between TCRs and peptides presented by the most common human MHCI allele, HLA-A*02:01. Our model is based on convolutional neural networks, which are especially designed to meet the challenges posed by the large length variations of TCRs. We show that such a sequence-based model allows for the identification of TCRs binding a given cognate peptide-MHC target out of a large pool of non-binding TCRs.

bioinformatics↗

bioRxiv2018

NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unravelling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed.\n\nHere, we present an updated and extended version of the NetSurfP tool (http://www.cbs.dtu.dk/services/NetSurfP-2.0/), that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences.\n\nWe assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1,000 proteins in less than 2 hours, and complete proteomes in less than 1 day.

bioinformatics↗