Biology subjects

Meysman, P.

Publications and source records attributed to Meysman, P..

At least 37 records · Page 2Linked to original sources

bioRxiv2023

The pitfalls of negative data bias for the T-cell epitope specificity challenge

Summary / AbstractEven high-performing machine learning models can have problems when deployed in a real-world setting if the data used to train and test the model contains biases. TCR-epitope binding prediction for novel epitopes is a very important but yet unsolved problem in immunology. In this article, we describe how the technique used to create negative data for the TCR-epitope interaction prediction task can lead to a strong bias and makes that the performance drops to random when tested in a more realistic scenario.

bioinformatics↗

bioRxiv2023

Multi-view learning to unravel the different levels underlying hepatitis B vaccine response

The immune system acts as the intricate apparatus dedicated to mounting a defence that ensures host survival from microbial threats. To engage this faceted immune response and provide protection against infectious diseases, vaccinations are the critical tool developed. However, vaccine responses are governed by levels that when interrogated separately only explain a fraction of the immune reaction. To address this knowledge gap, we conducted a feasibility study to determine if multi-view modelling can aid in gaining actionable insights on response markers shared across populations, capture the immune system diversity, and disentangle confounders. We thus sought to assess this multi-view modelling capacity on the responsiveness to Hepatitis B virus (HBV) vaccination. Seroconversion to vaccine induced antibodies against HBV surface antigen (anti-HBs) in early-converters (n=21; <2 month) and late-converters (n=9; <6 months), was defined based on the anti-HBs titres (>10IU/L). The multi-view data encompassed bulk RNA-seq, CD4+ T cell parameters (including T-cell receptor data), flow cytometry data, and clinical metadata (including age and gender). The modelling included testing single-view and multi-view joint dimensionality reductions. Multi-view joint dimensionality reduction out-performed single-view methods in terms of area under curve and balanced accuracy, confirming an increase in predictive power to be gained. The interpretation of the findings showed that age, gender, inflammation-related gene sets and pre-existing vaccine specific T-cells were associated with vaccination responsiveness. This multi-view dimensionality reduction approach complements the clinical seroconversion and all single modalities. Importantly, this modelling could identify what features predict HBV vaccine response. This methodology could be extended to other vaccination trials to identify key features regulating responsiveness.

systems biology↗

bioRxiv2022

Predicting MmpR-based bedaquiline resistance using sequence- and structure-based features

Accurate molecular detection of resistance to bedaquiline, a core drug for the treatment of drug resistant tuberculosis, remains challenging. In this study, we investigated whether three sequence- and nine structure-based features describing the impact of Rv0678 variants on the MmpR transcriptional repressor could predict the bedaquiline phenotype of isolates containing Rv0678 variants. Paired genotypic and phenotypic data was used to train a binary random forest classifier. The mean value of the individual features was similar for resistant and susceptible variants (p[≥]0.05). Leave one out cross validation showed predictability of bedaquiline resistance from Rv0678 variants when using a binary classifier with a combination of sequence and structural features (ROC AUC = 0.766; f1 score = 0.746), but the performance was too low for clinically use. Evolutionary conservation of the affected residue was the most important individual feature (mean decrease in impurity = 0.226 {+/-} 0.003) to discriminate bedaquiline resistance from susceptibility. Prediction of bedaquiline resistance was only possible when restricting the data to missense variants, as the selected features could not be applied to Rv0678 insertions and deletions. Additionally, prediction of bedaquiline resistance was only possible when restricting the data to isolates for which the phenotype was determined using Mycobacterial Growth Indicator Tubes, suggesting possible misclassification of the bedaquiline phenotype by other methods. The results of this study suggest that structural features describing Rv0678 missense variants could be used to predict bedaquiline resistance, albeit not yet at the performance level required for clinical practice. Author summaryGuidelines by the World Health Organization indicate that antibiotic resistant tuberculosis should be treated with bedaquiline, a newly discovered antibiotic. However, resistance to bedaquiline has already emerged and is spreading rapidly. More than 500 different variants have been discovered in the bedaquiline resistance genes in Mycobacterium tuberculosis. It is not known which DNA variants specifically drive bedaquiline resistance due to insufficiency of data. Here, we used a machine learning technique to predict whether a variant in the Rv0678 gene confers bedaquiline resistance. To this end, for each variant we defined features that describe the impact of the variant on the MmpR (encoded by the Rv0678 gene) protein structure. These features were then fed into a classification algorithm to predict bedaquiline resistance. We successfully developed a bedaquiline resistance prediction model, although performance was limited. We also found that accurate predictions were only possible when restricting the data to samples that were tested on the MGIT platform, a World Health Organization endorsed method to test for bedaquiline resistance. Our study shows that predicting bedaquiline resistance from protein structural features is feasible. Furthermore, our study provides new insights into phenotypic testing platforms to assess bedaquiline resistance.

microbiology↗

bioRxiv2022

Benchmarking solutions to the T-cell receptor epitope prediction problem: IMMREP22 workshop report

Many different solutions to predicting the cognate epitope target of a T-cell receptor (TCR) have been proposed. However several questions on the advantages and disadvantages of these different approaches remain unresolved, as most methods have only been evaluated within the context of their initial publications and data sets. Here, we report the findings of the first public TCR-epitope prediction benchmark performed on 23 prediction models in the context of the ImmRep 2022 TCR-epitope specificity workshop. This benchmark revealed that the use of paired-chain alpha-beta, as well as CDR1/2 or V/J information, when available, improves classification obtained with CDR3 data, independent of the underlying approach. In addition, we found that straight-forward distance-based approaches can achieve a respectable performance when compared to more complex machine-learning models. Finally, we highlight the need for a truly independent follow-up benchmark and provide recommendations for the design of such a next benchmark.

bioinformatics↗

bioRxiv2022

Interpretable deep learning to uncover the molecular binding patterns determining TCR-epitope interactions

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.

bioinformatics↗

bioRxiv2021

Predicting compound-protein interaction using hierarchical graph convolutional networks

MotivationConvolutional neural networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. They have also drawn much attention from other domains, including drug discovery and drug development. In this study, we develop a computational method based on convolutional neural networks to tackle a fundamental question in drug discovery and development, i.e. the prediction of compound-protein interactions based on compound structure and protein sequence. We propose a hierarchical graph convolutional network (HGCN) to encode small molecules. The HGCN aggregates a molecule embedding from substructure embeddings, which are synthesized from atom embeddings. As small molecules usually share substructures, computing a molecule embedding from those common substructures allows us to learn better generic models. We then combined the HGCN with a one-dimensional convolutional network to construct a complete model for predicting compound-protein interactions. Furthermore we apply an explanation technique, Grad-CAM, to visualize the contribution of each amino acid into the prediction. ResultsExperiments using different datasets show the improvement of our model compared to other GCN-based methods and a sequence based method, DeepDTA, in predicting compound-protein interactions. Each prediction made by the model is also explainable and can be used to identify critical residues mediating the interaction. Availability and implementationhttps://github.com/banhdzui/cpi_hgcn.git

bioinformatics↗

bioRxiv2021

Four layer multi-omics reveals molecular responses to aneuploidy in Leishmania

Aneuploidy causes system-wide disruptions in the stochiometric balances of transcripts, proteins, and metabolites, often resulting in detrimental effects for the organism. The protozoan parasite Leishmania has an unusually high tolerance for aneuploidy, but the molecular and functional consequences for the pathogen remain poorly understood. Here, we addressed this question in vitro and present the first integrated analysis of the genome, transcriptome, proteome, and metabolome of highly aneuploid Leishmania donovani strains. Our analyses unambiguously establish that aneuploidy in Leishmania proportionally impacts the average transcript- and protein abundance levels of affected chromosomes, ultimately correlating with the degree of metabolic differences between strains. This proportionality was present in both proliferative and non-proliferative in vitro promastigotes. However, protein complex subunits and non-cytoplasmic proteins, showed dosage compensation, responding less or even not at all to aneuploidy-induced dosage changes. In contrast to other Eukaryotes, we did not observe the widespread regulation at the transcript level that typically modulates some of the negative effects of aneuploidy. Further, the majority of differentially expressed proteins between aneuploid strains were encoded by non-aneuploid chromosomes and were not driven by a significant underlying transcript change, suggesting that aneuploidy is accompanied by extensive post-transcriptional protein-level modulation. This makes Leishmania a unique Eukaryotic model for elucidating post-transcriptional protein-abundance modulation in the context of aneuploidy.

systems biology↗

bioRxiv2021

Constrained standardization of count data from massive parallel sequencing

In high-throughput omics disciplines like transcriptomics, researchers face a need to assess the quality of an experiment prior to an in-depth statistical analysis. To efficiently analyze such voluminous collections of data, researchers need triage methods that are both quick and easy to use. Such a normalization method for relative quantitation, CONSTANd, was recently introduced for isobarically-labeled mass spectra in proteomics. It transforms the data matrix of abundances through an iterative, convergent process enforcing three constraints: (I) identical column sums; (II) each row sum is fixed (across matrices) and (III) identical to all other row sums. In this study, we investigate whether CONSTANd is suitable for count data from massively parallel sequencing, by qualitatively comparing its results to those of DESeq2. Further, we propose an adjustment of the method so that it may be applied to identically balanced but differently sized experiments for joint analysis. We find that CONSTANd can process large data sets with about 2 million count records in less than a second whilst removing unwanted systematic bias and thus quickly uncovering the underlying biological structure when combined with a PCA plot or hierarchical clustering. Moreover, it allows joint analysis of data sets obtained from different batches, with different protocols and from different labs but without exploiting information from the experimental setup other than the delineation of samples into identically processed sets (IPSs). CONSTANds simplicity and applicability to proteomics as well as transcriptomics data make it an interesting candidate for integration in multi-omics workflows.

bioinformatics↗

bioRxiv2021

clusTCR: a Python interface for rapid clustering of large sets of CDR3 sequences

The T-cell receptor (TCR) determines the specificity of a T-cell towards an epitope. As of yet, the rules for antigen recognition remain largely undetermined. Current methods for grouping TCRs according to their epitope specificity remain limited in performance and scalability. Multiple methodologies have been developed, but all of them fail to efficiently cluster large data sets exceeding 1 million sequences. To account for this limitation, we developed clusTCR, a rapid TCR clustering alternative that efficiently scales up to millions of CDR3 amino acid sequences. Benchmarking comparisons revealed similar accuracy of clusTCR with other TCR clustering methods. clusTCR offers a drastic improvement in clustering speed, which allows clustering of millions of TCR sequences in just a few minutes through efficient similarity searching and sequence hashing. clusTCR was written in Python 3. It is available as an anaconda package (https://anaconda.org/svalkiers/clustcr) and on github (https://github.com/svalkiers/clusTCR).

bioinformatics↗

bioRxiv2021

Predicted epitope binding core motifs and common amino acid polymorphisms distinguish protective- from susceptibility-associated HLA alleles in leishmaniasis

Susceptibility for leishmaniasis is largely dependent on genetic- and immune factors of the host. Despite the previously described association of human leukocyte antigen (HLA) gene cluster variants as genetic susceptibility factors, little is known on the mechanisms that mediate these associations. To characterize the functionality underpinning these associations between HLA and disease, we predicted the epitope binding repertoires for all known leishmaniasis-associated HLA variants collected in a thorough literature review. We identified several amino acid polymorphisms in the HLA sequences that distinguished protective-from risk-associated HLA-DRB1 alleles. Proteome-wide and multi-species T cell epitope binding predictions were carried out across these alleles, enabling us to map the effects on the epitope binding repertoires. The protective-associated HLA-DRB1 alleles were characterized by common binding core motifs, which map to the identified amino acid polymorphisms. These results strongly suggest that polymorphism in the HLA region, resulting in differential antigen presentation, affects the association between HLA and leishmaniasis disease development. Finally, we established a valuable open-access resource of putative epitopes, of which a set of 14 HLA-unrestricted strong-binding epitopes, conserved across species, were prioritized for further epitope discovery in the search for novel subunit-based vaccines.

immunology↗

bioRxiv2020

Tracking SARS-CoV-2 T cells with epitope T-cell receptor recognition models

Despite the general agreement on the importance of T cells during SARS-CoV-2 infection, the clinical impact of specific and cross-reactive T-cell responses remains uncertain, while this knowledge may indicate how to adjust vaccines and maintain robust long-term protection against continuously emerging variants. To characterize CD8+ T-cell response to epitopes unique to SARS-CoV-2 (SC-unique) or shared with other coronaviruses (CoV-common), we trained a large number of TCR-epitope recognition models for MHC-I-presented SARS-CoV-2 epitopes from publicly available data. Applying those models to longitudinal COVID-19 TCR repertoires of critical and non-critical COVID-19 patients, we discovered that notwithstanding comparable CD8+ T-cell depletion and the sizes of putative CoV-common CD8+ TCR repertoires in all symptomatic patients at the initial stage of the disease, the temporal dynamics of putative SC2-unique TCRs differed depending on the disease severity. Only non-critical patients had developed large and diverse SC2-unique CD8+ T-cell response by the second week of the disease. Additionally, only this patient group demonstrated redundancy in CD8+ TCRs putatively recognizing unique and common SARS-CoV-2 epitopes. Our findings thus emphasize the role of the de novo CD8+ T-cell response and support the argument against the clinical benefit of pre-existing cross-reactive CD8+ T cells. Now, the analytical framework of this study can not only be employed to track specific and cross-reactive SARS-CoV-2 CD8+ T cells in any TCR repertoire but also be generalized to more epitopes and be employed for adaptive immune response assessment and monitoring to inform public health decisions.

bioinformatics↗

bioRxiv2020

Preexisting memory CD4 T cells in naïve individuals confer robust immunity upon vaccination

Antigen recognition through the T cell receptor (TCR) {beta} heterodimer is one of the primary determinants of the adaptive immune response. Vaccines activate naive T cells with high specificity to expand and differentiate into memory T cells. However, antigen-specific memory CD4 T cells exist in unexposed antigen-naive hosts. In this study, we use high-throughput sequencing of memory CD4 TCR{beta} repertoire and machine learning to show that individuals with preexisting vaccine-reactive memory CD4 T cell clonotypes elicited earlier and higher antibody titers and mounted a more robust CD4 T cell response to hepatitis B vaccine. In addition, integration of TCR{beta} sequence patterns into a hepatitis B vaccine specific model can predict which individuals will have an early and more vigorous vaccine-elicited immunity. Thus, the presence of preexisting memory T clonotypes has a significant impact on immunity and can be used to predict immune responses to vaccination.

immunology↗

bioRxiv2019

Treating biomolecular interaction as an image classification problem - a case study on T-cell receptor-epitope recognition prediction

The prediction of epitope recognition by T-cell receptors (TCRs) has seen many advancements in recent years, with several methods now available that can predict recognition for a specific set of epitopes. However, the generic case of evaluating all possible TCR-epitope pairs remains challenging, mainly due to the high diversity of the interacting sequences and the limited amount of currently available training data. In this work, we provide an overview of the current state of this unsolved problem. First, we examine appropriate validation strategies to accurately assess the generalization performance of generic TCR-epitope recognition models when applied to both known and novel epitopes. In addition, we present a novel feature representation approach which we call ImRex (interaction map recognition). This approach is based on the pairwise combination of physicochemical properties of the individual amino acids in the CDR3 and epitope sequences, which provides a convolutional neural network with the combined representation of both sequences. Lastly, we highlight various challenges that are particular to TCR-epitope data and that can adversely affect model performance. These include the issue of selecting negative data, the imbalanced epitope distribution of curated TCR-epitope datasets, and the potential exchangeability of TCR alpha and beta chains. Our results indicate that while extrapolation to novel epitopes remains a difficult challenge, ImRex makes this feasible for a subset of epitopes that are not too dissimilar from the training data. We show that appropriate feature engineering methods and rigorous benchmark standards are required to create and validate TCR-epitope predictive models.

bioinformatics↗

bioRxiv2019

C-5 DNA methyltransferase 6 does not generate detectable DNA methylation in Leishmania

Cytosine C5 methylation is an important epigenetic control mechanism in a wide array of Eukaryotic organisms and generally carried out by proteins of C-5 DNA methyltransferase family (DNMTs). In several protozoans the status of this mechanism remains elusive, such as in Leishmania, the causative agent of the disease leishmaniasis in humans and a wide array of vertebrate animals. In this work, we show that the Leishmania donovani genome contains a C-5 DNA methyltransferase (DNMT) from the DNMT6 subfamily, of which the function is still unclear, and verified its expression at RNA level. We created viable overexpressor and knock-out lines of this enzyme and characterised their genome-wide methylation patterns using whole-genome bisulfite sequencing, together with promastigote and amastigote control lines. Interestingly, despite DNMT6 presence, we found that methylation levels were equal to or lower than 0.0003% at CpG sites, 0.0005% at CHG sites and 0.0126% at CHH sites at genome scale. As none of the methylated sites were retained after manual verification, we conclude that there is no evidence for DNA methylation in this species. We demonstrate that this difference in DNA methylation between the parasite (no detectable DNA methylation) and the vertebrate host (DNA methylation), allows enrichment of parasite versus host DNA using Methyl-CpG-binding domain columns, readily available in commercial kits. As such, we depleted methylated DNA from mixes of Leishmania promastigote and amastigote DNA with human DNA, resulting in average Leishmania:human enrichments from 62x up to 263x. These results open a promising avenue for unmethylated DNA enrichment as a pre-enrichment step before sequencing Leishmania clinical samples.

molecular biology↗

bioRxiv2018

Using expert driven machine learning to enhance dynamic metabolomics data analysis.

Data analysis for metabolomics is undergoing rapid progress thanks to the proliferation of novel tools and the standardization of existing workflows. However, as datasets and experiments continue to increase in size and complexity, standardized workflows are often not sufficient. In addition, as the ground truth for metabolomics experiments is intrinsically unknown, there is no way to critically evaluate the performance of tools. Here, we investigate the problem of dynamic multi-class metabolomics experiments using a simulated dataset with a known ground truth and evaluate the performance of tinderesting, a new and intuitive tool based on gathering expert knowledge to be used in machine learning, and compare it to EDGE, a statistical method for sequence data. This paper presents three novel outcomes. First we present a way to simulate dynamic metabolomics data with a known ground truth based on ordinary differential equations. This method is made available through the MetaboLouise R package. Second, we show that the EDGE tool, originally developed for genomics data analysis, is highly performant in analyzing dynamic case vs control metabolomics data. Last, we introduce the tinderesting method to analyse more complex dynamic metabolomics experiments that performs on par with statistical methods. This tool consists of a Shiny app for collecting expert knowledge, which in turn is used to train a machine learning model to emulate the decision process of the expert. This approach does not replace traditional data analysis workflows for metabolomics, but can provide additional information, improved performance or easier interpretation of results. The advantage is that the tool is agnostic to the complexity of the experiment, and thus is easier to use in advanced setups. All code for the presented analysis, MetaboLouise and tinderesting are freely available.

bioinformatics↗

bioRxiv2018

TCRex: a webtool for the prediction of T-cell receptor sequence epitope specificity

High-throughput T cell receptor (TCR) sequencing allows the characterization of an individuals TCR repertoire and directly query their immune state. However, it remains a non-trivial task to couple these sequenced TCRs to their antigenic targets. In this paper, we present a novel strategy to annotate full TCR sequence repertoires. The strategy is based on a machine learning algorithm to learn the TCR patterns common to the recognition of a specific epitope. These results are then combined with a statistical analysis to evaluate the occurrence of specific epitope-reactive TCR sequences per epitope in repertoire data. In this manner, we can directly study the capacity of full TCR repertoires to target specific epitopes of the relevant vaccines or pathogens. We demonstrate the usability of this approach on three independent datasets related to vaccine monitoring and infectious disease diagnostics by independently identifying the epitopes that are targeted by the TCR repertoire. The developed method is freely available as a web tool for academic use at tcrex.biodatamining.be.

bioinformatics↗

bioRxiv2018

Fast open modification spectral library searching through approximate nearest neighbor indexing

Open modification searching (OMS) is a powerful search strategy that identifies peptides carrying any type of modification by allowing a modified spectrum to match against its unmodified variant by using a very wide precursor mass window. A drawback of this strategy, however, is that it leads to a large increase in search time. Although performing an open search can be done using existing spectral library search engines by simply setting a wide precursor mass window, none of these tools have been optimized for OMS, leading to excessive runtimes and suboptimal identification results. Here we present the ANN-SoLo tool for fast and accurate open spectral library searching. ANN-SoLo uses approximate nearest neighbor indexing to speed up OMS by selecting only a limited number of the most relevant library spectra to compare to an unknown query spectrum. This approach is combined with a cascade search strategy to maximize the number of identified unmodified and modified spectra while strictly controlling the false discovery rate, as well as a shifted dot product score to sensitively match modified spectra to their unmodified counterparts. ANN-SoLo achieves state-of-the-art performance in terms of speed and the number of identifications. On a previously published human cell line data set, ANN-SoLo confidently identifies more spectra than SpectraST or MSFragger and achieves a speedup of an order of magnitude compared to SpectraST.\n\nANN-SoLo is implemented in Python and C++. It is freely available under the Apache 2.0 license at https://github.com/bittremieux/ANN-SoLo.

bioinformatics↗

bioRxiv2018

The workings and failings of clustering T-cell receptor beta-chain sequences without a known epitope preference

The T-cell receptor is responsible for recognizing potentially harmful epitopes presented on cell surfaces. The binding rules that govern this recognition between receptor and epitope is currently an unsolved problem, yet one of great interest. Several methods have been proposed recently to perform supervised classification of T-cell receptor sequences, but this requires known examples of T-cell sequences for a given epitope. Here we study the viability of various methods to perform unsupervised clustering of distinct T-cell receptor sequences and how these clusters relate to their target epitope. The goal is to provide an overview of the performance of various distance metrics on two large independent T-cell receptor sequence data sets. Our results confirm the presence of structural distinct T-cell groups that target identical epitopes. In addition, we put forward several recommendations to perform T-cell receptor sequence clustering.

bioinformatics↗