Kris Laukens

This paper introduces SIMBA, a transformer-based model that learns interpretable structural similarity from tandem mass spectra to improve small molecule analog discovery.

The paper introduces a computational framework to efficiently identify significantly neighbor enriched TCR sequences, demonstrating its utility in analyzing memory T cells and T cell responses to vaccination and viral infections.

CARTiBASE curates and standardizes over 10,000 CAR sequences into a single resource, enabling interactive browsing, similarity search, and analysis of CAR design trends.

The paper enhances ANN-SoLo for open modification searching by integrating predicted spectral libraries and improved vector representations, improving peptide identification in complex proteomics workflows.

SquiDBase provides a centralized repository for raw nanopore sequencing data from microbes, along with tools to process and expand reference datasets.

The paper introduces AIRRWAS, a framework to identify T cell receptor convergence with bacterial genera, revealing reproducible associations across cohorts and functional T cell responses.

The paper creates a synovial fluid TCR, cytokine, and cell repertoire atlas to compare disease mechanisms across arthritic conditions using systems immunology approaches.

The paper introduces MoSTERT and MoSTERT-2S, transformer-based models for zero-shot retention time prediction of peptides with unseen post-translational modifications, achieving state-of-the-art performance on an external dataset.

The paper links immunotypes and enterotypes through a systems immunology approach, showing they are orthogonal and connected via the blood transcriptome, with associations between specific bacteria and immune health.

A TCR-first approach to single-cell data analysis improves identification of disease-specific TCR features and reveals previously unknown T-cell clusters and arrangements.

This study analyzes T cell receptor repertoires in MS patients and controls to explore the relationship between EBV-specific and myelin-specific immune responses, finding distinct patterns associated with MS.

The paper analyzes the sequence distribution of epitope-specific TCR repertoires and shows how this affects machine learning model performance.

The paper develops computational models to identify WT1-specific TCRs in AML patients and finds higher TCR diversity in remission compared to relapsed patients.

This study uses semi-supervised learning on a large unlabeled dataset to improve cardiotoxicity prediction for three ion channels, identifying potential cardiac-active compounds.

This paper discusses machine learning strategies to overcome data challenges in mass spectrometry-based proteomics, emphasizing the need for standardized datasets and larger data sizes to improve model performance.

The paper trains a deep learning model to predict fragment ion intensities, improving immunopeptide identification rates using timsTOF instruments.

The paper introduces a cross-attention transformer encoder for multi-sequence inputs and evaluates it on peptide-MHCII binding prediction.

This paper presents a new high-quality reference genome for South American Plasmodium vivax isolates, showing improved representation compared to existing genomes.

The paper shows that biased negative data in TCR-epitope binding prediction leads to poor performance in realistic scenarios.

RapTCR provides a tool for rapid visualization and analysis of T-cell receptor repertoires, capturing both global and local sequence similarities.

This study uses multi-view modelling to improve prediction of HBV vaccine response by integrating bulk RNA-seq, T-cell data, flow cytometry, and clinical metadata.

This study uses interpretable deep learning to analyze TCR-epitope interactions and identify molecular binding patterns that influence TCR affinity.

The paper uses TCR-epitope recognition models to analyze CD8+ T-cell responses in COVID-19 patients, finding that non-critical patients develop unique SARS-CoV-2-specific T-cell responses not seen in critical patients.

This paper integrates semi-supervised machine learning into the ANN-SoLo tool to improve spectral library searching for open modification peptides, increasing identification rates.

The paper reanalyzes public mass spectrometry data to identify post-translational modifications in SARS-CoV-2-host protein interactions, revealing novel modification sites and their potential functional roles.

This study uses multi-omics analysis to show that aneuploidy in Leishmania causes proportional changes in transcript and protein abundance, with post-transcriptional regulation compensating for some effects.

This paper introduces a hierarchical graph convolutional network for predicting compound-protein interactions using molecular structure and protein sequences, showing improved performance over existing methods.

The paper introduces falcon, a tool for efficient clustering of large-scale mass spectrometry data, which produces larger and purer clusters than existing tools.

clusTCR is a Python tool for fast clustering of large CDR3 sequences, offering improved speed over existing methods while maintaining comparable accuracy.

This paper evaluates and adapts the CONSTANd normalization method for use with count data from sequencing, showing its efficiency and ability to remove bias across different experimental conditions.