Biology subjects

Laukens, K.

Publications and source records attributed to Laukens, K..

At least 19 recordsLinked to original sources

bioRxiv2026

Learning interpretable structural similarity from tandem mass spectra for small molecule analog discovery

Analog discovery remains a central bottleneck in mass spectrometry-based untargeted metabolomics, as conventional spectral similarity scores poorly reflect molecular structure. We introduce SIMBA, a transformer-based model that infers two interpretable graph-based distances, maximum common edge subgraph and substructure edit distance, directly from tandem mass spectra. SIMBA consistently retrieves structurally closer analogs than existing methods, enabling structure-aware small molecule identification beyond exact spectral matching.

bioinformatics↗

bioRxiv2026

Deciphering antigen-driven T cell responses through vectorized TCRdist sequence neighborhood quantification

T cells provide precise mechanisms to defend the body against infection and malignancies, mediated through the expression of their hypervariable T cell receptors (TCRs). Interpreting similarity between TCRs, however, remains a significant challenge. While performant clustering methods exist, these often fail to distinguish between antigen-driven convergent selection and patterns arising stochastically from biases in the V(D)J recombination mechanism. Moreover, defining enrichment in sequence similarity among large repertoires is computationally taxing. To address these limitations, we present an efficient computational framework for rapid approximation of TCRdist distances using fixed-length vector embeddings and highly optimized nearest neighbor search, allowing sequence similarity enrichment testing at a multi-repertoire-wide scale. This framework leverages a novel shuffling-based background model that preserves important repertoire characteristics such as V gene frequency, CDR3 sequence length and generation probability more accurately than synthetic models. Together, these tools enable the efficient and robust identification of significantly neighbor enriched (SNE) TCR sequences at scale. We validate this approach by showing a significant enrichment of SNE clones in memory T cell fractions and further demonstrate its utility in identifying convergent T cell signatures of response to vaccination and viral infections, providing a scalable approach for antigen-agnostic T cell response profiling.

immunology↗

bioRxiv2026

CARTiBASE: an interactive knowledge base for CAR sequence retrieval and similarity analysis

SummaryChimeric Antigen Receptors (CARs) are modular synthetic constructs that have transformed cellular immunotherapy, enabling targeted recognition and killing of malignant cells. Their clinical success has driven an explosive growth in new receptor designs, but these sequences are dispersed across heterogeneous sources such as publications, patents and supplementary files. This fragmentation and inconsistency limits comparative analysis, reproducibility and the reuse of existing constructs. To address this, we curated and standardized more than 10,000 CAR sequences into a single, harmonized resource. CARTiBASE is a web-based platform that provides standardized annotation, interactive browsing and fast similarity search across this curated collection. This unique database was leveraged to analyse the diversity in current CAR constructs within the public domain, revealing common design trends and lineages, as well as highlighting potential avenues for future CAR development. Availability and ImplementationCARTiBASE is freely available for non-commercial use at https://www.cartibase.org, without mandatory registration. The web server is implemented with a Python/Flask API backend and a Vue-based frontend and supports all major browsers. Users can search and filter thousands of CARs, inspect domain boundaries across signal peptide, antigen-binding domain, hinge, transmembrane, co-stimulatory and intracellular signaling regions, compare constructs and download sequences as FASTA files for downstream use.

immunology↗

bioRxiv2025

T cell-microbiome associations captured through T cell receptor convergence analysis

The gut microbiome modulates mucosal immunity, yet how specific bacterial taxa shape the diversity and specificity of T cell receptor (TCR) repertoires remains poorly understood. Existing approaches emphasize single-species effects or broad immune features, without pinpointing which microbes drive specific T cell clonotypes. We present AIRRWAS, a computational framework that integrates TCR-microbiome interaction analysis with targeted in vitro validation to detect genus-level TCR convergence. Applied to three independent cohorts, AIRRWAS identified reproducible associations between convergent TCR clusters and 21 bacterial genera spanning core commensals, probiotics and taxa with immunomodulatory roles. Predicted clonotypes were enriched within the TCR-microbiome interaction network and preferentially activated by genus-matched stimuli, eliciting different functional T cell responses. These findings demonstrate that distinct repertoires can share genus-specific TCR motifs, enabling detection of shared immune signatures. AIRRWAS can map these TCR- microbiome interactions, laying the groundwork for biomarker discovery immune monitoring and the development of microbiome-targeted therapies.

bioinformatics↗

bioRxiv2025

Improved open modification searching via unified spectral search with predicted libraries and enhanced vector representations in ANN-SoLo

The primary computational challenge in mass spectrometry-based proteomics is determining the peptide sequence responsible for generating each measured tandem mass spectrum. This task is traditionally addressed through sequence database searching, as well as alternative approaches such as spectral library searching. ANN-SoLo is a powerful spectral library search engine optimized for open modification searching, enabling the detection of peptides carrying any post-translational modification. Here, we present an enhanced version of ANN-SoLo that combines strengths of both spectral library searching and sequence database searching, by integrating with Prosit to generate predicted spectral libraries from protein sequence databases. Additionally, it provides functionality to generate decoys at both the spectrum and the peptide level, introduces an optimized internal file structure for large-scale analytics, and improves search accuracy by incorporating neutral loss information into spectrum vector representations. These advancements collectively address challenges associated with missing spectral libraries and enhance peptide identification in large-scale and complex proteomics workflows.

bioinformatics↗

bioRxiv2025

SquiDBase: a community resource of raw nanopore data from microbes

Experimental data-driven research relies on raw data, which consist of unprocessed experimental outputs, whereas derived data are transformed through a number of processing steps to reveal specific insights. Such processing, however, can potentially introduce biases or information loss, compromising transparency and reproducibility. In nucleic acid sequencing, nucleotide sequences stored in the FASTQ format are widely shared, but FASTQ files are generated from platform-specific raw data outputs, which vary depending on the sequencing platform used. The raw data produced by Oxford Nanopore Technologies (ONT) sequencing devices contain valuable biological information and are also useful to improve data processing methods, which includes basecaller optimisation and modification detection. Increasing attention goes to exploring these raw signals to develop algorithms that could improve ONT device portability and enhance target enrichment efficiency through adaptive sampling. Despite these benefits, the storage and sharing of raw nanopore data remain limited due to technical constraints and the lack of appropriate, standardised and centralised infrastructure. To address this challenge, we developed SquiDBase (https://squidbase.org), a dedicated repository to collect raw microbial nanopore sequencing data. To maximise the utility of SquiDBase from its inception, we built SquiDPipe, a Nextflow pipeline for the automated removal of human or unwanted reads from raw nanopore data. Additionally, we sequenced 24 clinically relevant viruses and incorporated them into SquiDBase, significantly expanding the diversity of publicly available reference datasets. By offering a centralised, open-access raw data collection platform, SquiDBase facilitates data sharing, enhances reproducibility, and supports the development and benchmarking of novel computational tools, reinforcing open science in nanopore sequencing research.

bioinformatics↗

bioRxiv2025

Generation of a T cell receptor, cytokine and cell repertoire synovial fluid atlas to define commonalities and dissimilarities between arthritic diseases through systems immunology approaches

Although different chronic arthritic diseases are defined by clinical factors like gender, psoriasis and auto-antibodies, the biology of inflamed joints while comparing the different diseases remains neglected. Here, after curating an inflamed joint derived T-cell receptor (TCR) database, our new TRIASSIC tool identified 66303 significantly convergent TCR clonotypes. Clustering TCR clonotypes showed that synovial fluid convergence clusters (SFCCs) characterized HLA-B27+ mediated diseases (spondyloarthritis, SpA, and enthesitis-related juvenile idiopathic arthritis, JIA-ERA), Lyme arthritis and oligoarticular JIA. Single-cell transcriptomics and bulk proteomics showed upregulated interferon type I and II and TNF- pathways in oJIA. Adult and juvenile psoriatic arthritis, (JIA-)PsA, was characterized by upregulated HSP expression in monocytes and TXNIP in T-cells. We discovered an abundance of CCL5 expressing CD8+ T-cells in SF from HLA-B27+ JIA-ERA and SpA patients. JIA-ERA patients showed upregulation of CD74 and LGALS1 in Th1 and Th17 cells and IGHV7-4.1 in B-cells. oJIA patients shared a TRBV28 RG-motif on CXCL13 producing helper T-cells. Rheumatoid arthritis and (JIA-)PsA patients carried EBV-reactive cytotoxic CD8+ T-cells. Annexin signalling was shown to be important in the intercellular communication for all arthritis groups. Collectively, our work showed that chronic arthritis is characterized by both disease-specific and broadly shared mechanisms.

immunology↗

bioRxiv2024

Zero-shot retention time prediction for unseen post-translational modifications with molecular structure encodings

Mass spectrometry-based proteomics relies on accurate peptide property prediction models to enhance peptide identification and characterization, especially when dealing with peptidoforms. However, current approaches are limited in their ability to generalize to peptides with novel post-translational modifications (PTMs) due to insufficient training data. To address this challenge, we introduce MoSTERT (Molecular Structure Transformer Encoder for Retention Time prediction) and its enhanced variant, MoSTERT-2S, two transformer-based models designed for zero-shot prediction of retention times of peptides with unseen PTMs. Unlike conventional models, MoSTERT encodes peptide residues at the molecular structure level, allowing it to handle diverse PTMs. MoSTERT-2S further improves accuracy by employing a two-step strategy: first predicting the retention time of the unmodified peptide, then estimating the retention time shift induced by the PTMs. Evaluation on an external dataset demonstrates that MoSTERT-2S achieves state-of-the-art performance, reducing prediction errors compared to existing methods. Its ability to accurately predict retention times for peptides with a wide variety of PTMs not seen during training highlights its potential for advancing proteomic workflows analyzing proteoforms and protein modifications.

bioinformatics↗

bioRxiv2024

Bridging immunotypes and enterotypes using a systems immunology approach

Unveiling the systemic effects of disease and health requires an holistic approach that has mainly revolved around well established, directly determinable molecular relationships such as the protein synthesis cascade and epigenetic mechanisms. In this study, involving 394 individuals, we found direct linkage of branches spanning human biological functions often not studied in conjunction, using clinical data, gut microbial abundances, blood immune cell repertoires, blood transcriptomic and blood T cell receptor data. Contrary to current paradigms, we demonstrate that immunotypes and enterotypes are orthogonal, likely fulfilling distinct roles in maintaining homeostasis, only bridged via the blood transcriptome. We also identified two distinct inflammatory profiles: the first driven by interferon signalling and the other characterised by non-viral, NF-kB and IL-6 markers. Lastly, we present compelling data showing strong associations of the Ruminococcaceae and Christensenellaceae bacteria with a healthy immunotype and transcriptomic pattern, highlighting their potential role in immune health. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=194 HEIGHT=200 SRC="FIGDIR/small/625344v1_ufig1.gif" ALT="Figure 1"> View larger version (52K): org.highwire.dtl.DTLVardef@c6b5eorg.highwire.dtl.DTLVardef@15d0c3forg.highwire.dtl.DTLVardef@1cf29eeorg.highwire.dtl.DTLVardef@1c9ff8d_HPS_FORMAT_FIGEXP M_FIG C_FIG

systems biology↗

bioRxiv2024

Linking myelin and Epstein-Barr virus specific immune responses in multiple sclerosis: insights from integrated public T cell receptor repertoires

The autoimmune responses in multiple sclerosis (MS), particularly those mediated by T cells targeting CNS-derived antigens, are broadly recognized. However, the defining triggers underlying these responses remain poorly understood. Epstein-Barr virus (EBV) infection has emerged as a primary risk factor for MS, suggesting a potential role for molecular mimicry in which EBV-specific immune responses cross-react with myelin antigens. In this study, we analyzed the T cell receptor (TCR) repertoires of MS patients (n = 129) and controls (n = 94) from public datasets, to explore the relationship between EBV-specific and myelin-specific T cell responses. Our analysis identified clusters of TCRs that were significantly depleted among MS patients, many of which were associated with cytomegalovirus (CMV). By generating a library of myelin-reactive TCRs from stimulated peripheral blood mononuclear cells (PBMCs) obtained from MS patients and mapping these sequences to the public TCR repertoire database, we also uncovered a lower frequency of myelin-reactive TCRs in MS samples compared to controls in the public datasets. In addition, epitope-specificity prediction revealed a broader response to EBV-, but not CMV-derived epitopes. Collectively, these findings underscore the complex role of chronic viral infections in MS. Particularly, they suggest that EBV-specific immune responses contribute to the dysregulation of the immune system in MS patients, potentially through mechanisms of molecular mimicry. While the broader response to EBV-derived epitopes and the lower frequency of myelin-reactive TCRs in MS samples are both associated with the disease, further research is needed to clarify the nature of this relationship. These observations suggest that viral and autoimmune mechanisms may contribute independently or interact in MS pathogenesis.

immunology↗

bioRxiv2024

Revealing the hidden sequence distribution of epitope-specific TCR repertoires and its influence on machine learning model performance

Numerous efforts have been made to decipher the epitope-T cell receptor (TCR) recognition code. Both simple machine learning techniques and deep learning strategies have been used to train models to predict the binding of epitopes by TCR sequences. A good training data set rests at the basis of every accurate prediction model, yet little attention has been given to the composition of these data sets. In this paper, we studied the natural distribution of TCR sequences within epitope-specific TCR repertoires, i.e. a set of TCRs binding the same epitope, and its impact on the predictability of TCR-epitope interactions. We found that the observed diversity of these repertoires can result from a smaller set of core binding motifs constrained by TCR generation. Moreover, a clear relationship was found between the sequence distribution of the training data and performance metrics, emphasizing the importance of the used ground-truth data when using machine learning models in this domain. Taken together, these findings inform data set composition to help push epitope-TCR prediction models to the next level.

bioinformatics↗

bioRxiv2024

Semi-Supervised Learning to Boost Cardiotoxicity Prediction by Mining a Large Unlabeled Small Molecule Dataset

Predicting drug toxicity is a critical aspect of ensuring patient safety during the drug design process. Although conventional machine learning techniques have shown some success in this field, the scarcity of annotated toxicity data poses a significant challenge in enhancing models performance. In this study, we explore the potential of leveraging large unlabeled datasets using semi-supervised learning to improve predictive performance for cardiotoxicity across three targets: the voltage-gated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5). We extensively mined the ChEMBL database, comprising approximately 2 million small molecules, then employed semi-supervised learning to construct robust classification models for this purpose. We achieved a performance boost on highly diverse (i.e. structurally dissimilar) test datasets across all three targets. Using our built models, we screened the whole ChEMBL database and a large set of FDA-approved drugs, identifying several compounds with potential cardiac channel activity. To ensure broad accessibility and usability for both technical and non-technical users, we developed a cross-platform graphical user interface that allows users to make predictions and gain insights into the cardiotoxicity of drugs and other small molecules. The software is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred2.

pharmacology and toxicology↗

bioRxiv2024

Machine learning strategies to tackle data challenges in mass spectrometry-based proteomics

In computational proteomics, machine learning (ML) has emerged as a vital tool for enhancing data analysis. Despite significant advancements, the diversity of ML model architectures and the complexity of proteomics data present substantial challenges in the effective development and evaluation of these tools. Here, we highlight the necessity for high-quality, comprehensive datasets to train ML models and advocate for the standardization of data to support robust model development. We emphasize the instrumental role of key datasets like ProteomeTools and MassIVE-KB in advancing ML applications in proteomics and discuss the implications of dataset size on model performance, highlighting that larger datasets typically yield more accurate models. To address data scarcity, we explore algorithmic strategies such as self-supervised pretraining and multi-task learning. Ultimately, we hope that this discussion can serve as a call to action for the proteomics community to collaborate on data standardization and collection efforts, which are crucial for the sustainable advancement and refinement of ML methodologies in the field.

bioinformatics↗

bioRxiv2023

A cross-attention transformer encoder for paired sequence data

Transformer-based sequence encoding architectures are often limited to a single-sequence input while some tasks require a multi-sequence input. For example, the peptide-MHCII binding prediction task where the input consists of two protein sequences. Current workarounds to solve this input-type mismatch lack resemblance with the biological mechanisms behind the task. As a solution, we propose a novel cross-attention transformer encoder that creates a cross-attended embedding of both input sequences. We compare its classification performance on the peptide-MHCII binding prediction task to a baseline logistic regression model and a default transformer encoder. Finally, we make visualizations of the attention layers to show how the different models learn different patterns.

bioinformatics↗

bioRxiv2023

Analysis of Wilms' tumor protein 1 specific TCR repertoire in AML patients uncovers higher diversity in patients in remission than in relapsed

The Wilms tumor protein 1 (WT1) is a well-known and prioritized tumor-associated antigen expressed in numerous solid and blood tumors. Its abundance and immunogenicity have led to the development of different WT1-specific immune therapies. The driving player in these therapies, the WT1-specific T-cell receptor (TCR) repertoire, has received much less attention. Importantly, T cells with high affinity against the WT1 self-antigen are normally eliminated after negative selection in the thymus and are thus rare in peripheral blood. Here, we developed computational models for the robust and fast identification of WT1-specific TCRs from TCR repertoire data. To this end, WT137-45 (WT1-37) and WT1126-134 (WT1-126)-specific T cells were isolated from WT1 peptide-stimulated blood of healthy individuals. The TCR repertoire from these WT1-specific T cells was sequenced and used to train a pattern recognition model for the identification of WT1-specific TCR patterns for the WT1-37 or WT1-126 epitopes. The resulting computational models were applied on an independent published dataset from acute myeloid leukemia (AML) patients, treated with hematopoietic stem cell transplantation, to track WT1-specific TCRs in silico. Several WT1-specific TCRs were found in AML patients. Subsequent clustering analysis of all repertoires indicated the presence of more diverse TCR patterns within the WT1-specific TCR repertoires of AML patients in complete remission in contrast to relapsing patients. We demonstrate the possibility of tracking WT1-37 and WT1-126-specific TCRs directly from TCR repertoire data using computational methods, eliminating the need for additional blood samples and experiments for the two studied WT1 epitopes.

bioinformatics↗

bioRxiv2023

STEGO.R: an application to aid in scRNA-seq and scTCR-seq processing and analysis.

The T-cell receptor (TCR) carries critical information regarding T-cell functionality. The TCR, despite its importance, is underutilized in single cell transcriptomics, with gene expression (GEx) features solely driving current analysis strategies. Here, we argue for a switch to a TCR-first approach, which would uncover unprecedented insights into T cell and TCR repertoire mechanics. To this end, we curated a large T-cell atlas from 12 prominent human studies, containing in total 500,000 T cells spanning multiple diseases, including melanoma, head-and-neck cancer, T-cell cancer, and lung transplantation. Herein, we identified severe limitations in cell-type annotation using unsupervised approaches and propose a more robust standard using a semi-supervised method or the TCR arrangement. We then showcase the utility of a TCR-first approach through application of the novel STEGO.R tool for the successful identification of hyperexpanded clones to reveal treatment-specific changes. Additionally, a meta-analysis based on neighbor enrichment revealed previously unknown public T-cell clusters with potential antigen-specific properties as well as highlighting additional common TCR arrangements. Therefore, this paradigm shift to a TCR-first with STEGO.R highlights T-cell features often overlooked by conventional GEx-focused methods, and enabled identification of T cell features that have the potential for improvements in immunotherapy and diagnostics. One Sentence SummaryRevamping the interrogation strategies for single-cell data to be centered on T cell receptor (TCR) rather than the generic gene expression improved the capacity to find relevant disease specific TCR. Key PointsO_LIThe TCR-first approach captures dynamic T cell features, even within a clonal population. C_LIO_LIA novel [~]500,000 T-cell atlas to enhance single cell analysis, especially for restricted populations. C_LIO_LINovel STEGO.R program and pipeline allows for consistent and reproducible interrogating of scTCR-seq with GEx. C_LI

bioinformatics↗

bioRxiv2023

RapTCR: Rapid exploration and visualization of T-cell receptor repertoires

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSThe acquisition of T-cell receptor (TCR) repertoire sequence data has become faster and cheaper due to advancements in high-throughput sequencing. However, fully exploiting the diagnostic and clinical potential within these TCR repertoires requires a thorough understanding of the inherent repertoire structure. Hence, visualizing the full space of TCR sequences could be a key step towards enabling exploratory analysis of TCR repertoire, driving their enhanced interrogation. Nonetheless, current methods remain limited to rough profiling of TCR V and J gene distributions. Addressing this need, we developed RapTCR, a tool for rapid visualization and post-analysis of TCR repertoires. ApproachTo overcome computational complexity, RapTCR introduces a novel, simple embedding strategy that represents TCR amino acid sequences as short vectors while retaining their pairwise alignment similarity. RapTCR then applies efficient algorithms for indexing these vectors and constructing their nearest neighbor network. It provides multiple visualization options to map and interactively explore a TCR network as a two-dimensional representation. Benchmarking analyses using epitope-annotated datasets demonstrate that these RapTCR visualizations capture TCR similarity features on a global level (e.g., J gene) and locally (e.g., epitope reactivity). RapTCR is available as a Python package, implementing the intuitive scikit-learn syntax to easily generate insightful, publication-ready figures for TCR repertoires of any size. Availability and ImplementationRapTCR was written in Python 3. It is available as an anaconda package (https://anaconda.org/vincentvandeuren/raptcr), and on github (https://github.com/vincentvandeuren/RapTCR). Documentation and example notebooks are available at vincentvandeuren.github.io/rapTCR_docs/. Contactpieter.meysman@uantwerpen.be

bioinformatics↗

bioRxiv2023

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction

In the field of drug discovery, there is a substantial challenge in seeking out chemical structures that possess desirable pharmacological, toxicological, and pharmacokinetic properties. Complications arise when drugs interfere with the functioning of cardiac ion channels, leading to serious cardiovascular consequences. The discontinuation and removal of numerous approved drugs from the market or at late development stages in the pipeline due to such inhibitory effects further highlight the urgency of addressing this issue. Consequently, the early prediction of potential blockers targeting cardiac ion channels during the drug discovery process is of paramount importance. This study introduces a deep learning framework that computationally determines the cardiotoxicity associated with the voltagegated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5) for drug candidates. The predictive capabilities of three feature representations--molecular fingerprints, descriptors, and graph-based numerical representations-- are rigorously benchmarked. Additionally, a novel training and evaluation dataset framework is presented, enabling predictive model training of drug off-target cardiotoxicity using a comprehensive and large curated dataset covering these three cardiac ion channels. To facilitate these predictions, a robust and comprehensive small molecule cardiotoxicity prediction tool named CToxPred has been developed. It is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred.

pharmacology and toxicology↗