Immunoinformatics (Amsterdam, Netherlands)最新文献

Proteins have an arsenal of medical applications that include disrupting protein interactions, acting as potent vaccines, and replacing genetically deficient proteins. While therapeutics must avoid triggering unwanted immune-responses, vaccines should support a robust immune-reaction targeting a broad range of pathogen variants. Therefore, computational methods modifying proteins’ immunogenicity without disrupting function are needed. While many components of the immune-system can be involved in a reaction, we focus on Cytotoxic T-lymphocytes (CTLs). These target short peptides presented via the MHC Class I (MHC-I) pathway. To explore the limits of modifying the visibility of those peptides to CTLs within the distribution of naturally occurring sequences, we developed a novel machine learning technique, CAPE-XVAE. It combines a language model with reinforcement learning to modify a protein’s immune-visibility. Our results show that CAPE-XVAE effectively modifies the visibility of the HIV Nef protein to CTLs. We contrast CAPE-XVAE to CAPE-Packer, a physics-based method we also developed. Compared to CAPE-Packer, the machine learning approach suggests sequences that draw upon local sequence similarities in the training set. This is beneficial for vaccine development, where the sequence should be representative of the real viral population. Additionally, the language model approach holds promise for preserving both known and unknown functional constraints, which is essential for the immune-modulation of therapeutic proteins. In contrast, CAPE-Packer, emphasizes preserving the protein’s overall fold and can reach greater extremes of immune-visibility, but falls short of capturing the sequence diversity of viral variants available to learn from. Source code: https://github.com/hcgasser/CAPE (Tag: v1.1)

Coronaviruses are known to infect a wide range of mammals. In humans, coronaviruses have been responsible for causing the common cold. The immune response against common cold coronaviruses appears to elicit a cross-protective response to SARS-CoV-2. This study identified protein regions in the mammalian coronaviruses' proteome that are identical to those of SARS-CoV-2. Using bioinformatics analysis, the study predicted the involvement of SARS-CoV-2-identical protein regions, identified in mammalian coronaviruses, in antigen-presenting processes and their ability to elicit immune responses. The SARS-CoV-2-identical protein regions were predominantly found in the proteomes of betacoronaviruses, with less prevalence in alphacoronaviruses. Alphacoronaviruses, such as FCoV in domestic felines and MCoV in minks, are known to infect species highly susceptible to SARS-CoV-2. In contrast, betacoronaviruses infect mammals with lower susceptibility to SARS-CoV-2, including dogs, mice, and farmed animals. Furthermore, betacoronaviruses exhibited a higher number of peptides with an increased potential for efficient presentation during the antigen-presenting process, indicating their greater immunogenicity. Conversely, the SW1 gammacoronavirus showed a lower count of SARS-CoV-2 protein regions and a reduced potential for efficient antigen presentation. The results suggested that the elevated number of SARS-CoV-2 identical stretches found in betacoronaviruses may provide potential cross-protection between SARS-CoV-2 and mammalian betacoronaviruses. This cross-protection could be similar to that observed between human coronaviruses causing the common cold and SARS-CoV-2. The limited numbers observed in the proteomes of FCoV, MCoV, and SW1-CoV may offer an explanation for the susceptibility of cats and minks to SARS-CoV-2, as well as a potential vulnerability in cetaceans.

The vast potential sequence diversity of TCRs and their ligands has presented an historic barrier to computational prediction of TCR epitope specificity, a holy grail of quantitative immunology. One common approach is to cluster sequences together, on the assumption that similar receptors bind similar epitopes. Here, we provide the first independent evaluation of widely used clustering algorithms for TCR specificity inference, observing some variability in predictive performance between models, and marked differences in scalability. Despite these differences, we find that different algorithms produce clusters with high degrees of similarity for receptors recognising the same epitope. Our analysis strengthens the case for use of clustering models to identify signals of common specificity from large repertoires, whilst highlighting scope for improvement of complex models over simple comparators.

Modeling and experimental data were used to evaluate how monocytes would respond to dual TLR4/TLR5 and dual TLR4/TLR7 signaling analogous to how the cells would respond to simultaneously encountering different types of pathogens. Both TLR4/TLR5 and TLR4/TLR7 signaling resulted in a decreased NFkB response relative to signaling through a single TLR. The NFkB response also decreased when all three signaling cascades were triggered. The model suggested that competition between the signaling pathways led to the impaired response when the cells were exposed to multiple TLR agonists, however adjusting the level of IRAKs and TABs in the model was insufficient to overcome competition between the signaling pathways. To experimentally examine how modifying TLR signaling proteins would impact the NFkB response to multiple TLR agonists, cells were pre-conditioned with lipopolysaccharide and the response to single, dual, and triple TLR signaling was followed. Pre-conditioning led to a reduction in the NFkB response to all three agonists, likely a consequence of decreased tlr4, tlr5, tlr7, nfkb, tab1, tab2, and tab3 expression. Collectively, the model supported exploration of the effects of multiple agonists on the signaling pathways and the effectiveness of adjusting the level of TLR signaling proteins in improving the NFkB response. These experiments and data show the importance of having a model capable of integrating multiple TLR signaling cascades since data generated by the model of a single TLR signaling cascade could not predict how the cells would respond when multiple TLR signaling cascades were activated.

The cellular immune response comprises several processes, with the most notable ones being the binding of the peptide to the Major Histocompability Complex (MHC), the peptide-MHC (pMHC) presentation to the surface of the cell, and the recognition of the pMHC by the T-Cell Receptor. Identifying the most potent peptide targets for MHC binding, presentation and T-cell recognition is vital for developing peptide-based vaccines and T-cell-based immunotherapies. Data-driven tools that predict each of these steps have been developed, and the availability of mass spectrometry (MS) datasets has facilitated the development of accurate Machine Learning (ML) methods for class-I pMHC binding prediction. However, the accuracy of ML-based tools for pMHC kinetic stability prediction and peptide immunogenicity prediction is uncertain, as stability and immunogenicity datasets are not abundant. Here, we use transfer learning techniques to improve stability and immunogenicity predictions, by taking advantage of a large number of binding affinity and MS datasets. The resulting models, TLStab and TLImm, exhibit comparable or better performance than state-of-the-art approaches on different stability and immunogenicity test sets respectively. Our approach demonstrates the promise of learning from the task of peptide binding to improve predictions on downstream tasks. The source code of TLStab and TLImm is publicly available at https://github.com/KavrakiLab/TL-MHC.

The immune system is highly complex, and its malfunctioning can result in many complex disorders. Understanding its inner workings is crucial to designing optimal immunotherapies, developing new vaccines, or understanding autoimmune diseases, just to name a few. Immune-related diseases present unique challenges due to our limited understanding of the complex molecular and cellular interactions involved, as well as the scarcity of available therapeutic options. Recent years have witnessed the progressive development of high-throughput experimental technologies to probe the immune system. This large amount of data has facilitated the emergence of statistical and machine-learning models focused on unravelling the intricate complexities of the immune system. With this vision in mind, a workshop titled "Computational modelling of immunological mechanisms: From statistical approaches to interpretable machine learning" was organized on Sunday, September 18th, 2022 at the 21st European Conference on Computational Biology (ECCB) in Sitges, Spain. The workshop, led by María Rodríguez Martínez, Anna Niarakis, and Matteo Barberis, explored recent statistical models, high-throughput data analyses, and machine learning models to understand immunological mechanisms. More than 60 participants attended the workshop, comprising students, early-career and senior researchers, as well as professionals from diverse domains including Immunology, Systems Biology, Computational Biology, Computer Science, and Bioinformatics. To conclude the workshop, a round table was organized to foster discussions on the existing challenges and chart a roadmap for the development of the next generation of computational models dedicated to investigating the cellular and molecular functions that underlie the immune system.

Protein folding problem obtained a practical solution recently, owing to advances in deep learning. There are classes of proteins though, such as antibodies, that are structurally unique, where the general solution still lacks. In particular, the prediction of the CDR-H3 loop, which is an instrumental part of an antibody in its antigen recognition abilities, remains a challenge. Antibody-specific deep learning frameworks were proposed to tackle this problem noting great progress, both on accuracy and speed fronts. Oftentimes though, the original networks produce physically implausible bond geometries that then need to undergo a time-consuming energy minimization process. Here we hypothesized that pre-training the network on a large, augmented set of models with correct physical geometries, rather than a small set of real antibody X-ray structures, would allow the network to learn better bond geometries. We show that fine-tuning such a pre-trained network on a task of shape prediction on real X-ray structures improves the number of correct peptide bond distances, abstracted as the Cα distances. We further demonstrate that pre-training allows the network to produce physically plausible shapes on an artificial set of CDR-H3s, showing the ability to generalize to the vast antibody sequence space. We hope that our strategy will benefit the development of deep learning antibody models that rapidly generate physically plausible geometries, without the burden of time-consuming energy minimization.

The recognition of an epitope by a T-cell receptor (TCR) is crucial for eliminating pathogens and establishing immunological memory. Prediction of the binding of any TCR–epitope pair is still a challenging task, especially for novel epitopes, because the underlying patterns are largely unknown to domain experts and machine learning models. To achieve a deeper understanding of TCR–epitope interactions, we have used interpretable deep learning techniques to gain insights into the performance of TCR–epitope binding machine learning models. We demonstrate how interpretable AI techniques can be linked to the three-dimensional structure of molecules to offer novel insights into the factors that determine TCR affinity on a molecular level. Additionally, our results show the importance of using interpretability techniques to verify the predictions of machine learning models for challenging molecular biology problems where small hard-to-detect problems can accumulate to inaccurate results.

Analysis of an individual's immunoglobulin or T cell receptor gene repertoire can provide important insights into immune function. High-quality analysis of adaptive immune receptor repertoire sequencing data depends upon accurate and relatively complete germline sets, but current sets are known to be incomplete. Established processes for the review and systematic naming of receptor germline genes and alleles require specific evidence and data types, but the discovery landscape is rapidly changing. To exploit the potential of emerging data, and to provide the field with improved state-of-the-art germline sets, an intermediate approach is needed that will allow the rapid publication of consolidated sets derived from these emerging sources. These sets must use a consistent naming scheme and allow refinement and consolidation into genes as new information emerges. Name changes should be minimised, but, where changes occur, the naming history of a sequence must be traceable. Here we outline the current issues and opportunities for the curation of germline IG/TR genes and present a forward-looking data model for building out more robust germline sets that can dovetail with current established processes. We describe interoperability standards for germline sets, and an approach to transparency based on principles of findability, accessibility, interoperability, and reusability.