Biology subjects

Walz, J. S.

Publications and source records attributed to Walz, J. S..

6 recordsLinked to original sources

bioRxiv2026

Deep learning enables direct HLA typing from immunopeptidomics data

The immune system eliminates malignant and infected cells through T-cell-mediated recognition of peptides presented by human leukocyte antigen molecules. Mass spectrometry-based immunopeptidomics enables unbiased identification of naturally presented HLA-restricted peptides and has become central to the development of T-cell-based immunotherapies. However, immunopeptidomics data reflects the combined peptide presentation of multiple HLA alleles, and determining which allotypes are represented in this multi-allelic complexity remains an unmet computational challenge. Here, we introduce immunotype, a deep learning-based ensemble predictor for HLA class I allotyping directly from immunopeptidomics data. Immunotype integrates peptide and HLA protein sequence information through transformer encoders and a graph neural network, complemented by a curated mono-allelic reference of known peptide-HLA binding preferences. Immunotype achieves an overall accuracy of 87.2% at protein-level resolution across diverse tissues and thereby enables rapid, cost-effective HLA typing of large-scale immunopeptidomics datasets.

bioinformatics↗

bioRxiv2026

t2pmhc: A Structure-Informed Graph Neural Network to predict TCR-pMHC Binding

Mapping of T cell receptors (TCRs) to their cognate MHC-presented peptides (pMHC) is central for the development of precision immunotherapies and vaccine design. However, accurate prediction of TCR affinity to peptide antigens remains an open challenge. Most approaches rely solely on sequence information, although increasing evidence suggests that TCR-pMHC binding is primarily determined by three-dimensional structural interactions within the entire TCR-pMHC complex. Consequently, sequence-based methods often fail to generalize to peptides not included in the training data (unseen peptides). Here we introduce t2pmhc, a structure-based graph neural network framework for predicting TCR-pMHC binding using predicted structures of the entire TCR-pMHC complex. We evaluated a Graph Convolutional Network (GCN) and a Graph Attention Network, both demonstrating improved generalization to unseen peptides compared to state-of-the-art models across a variety of public datasets. Evaluation with crystallographic structures yields high-confidence predictions, indicating that current limitations of structure-based models are largely driven by the accuracy of structure prediction. Analysis of node attention patterns in t2pmhc-GCN reveals biologically consistent patterns, assigning high attention to the peptide and the CDR3 regions. Within the peptide sequence, canonical MHC anchor residues are consistently downweighted, whereas potential TCR-binding residues are upweighted. These findings establish t2pmhc as a structure-informed framework for robust TCR-pMHC binding prediction, enabling improved generalization to unseen antigens and providing a foundation for integrating TCR repertoire sequencing into vaccine design and immunotherapy.

bioinformatics↗

bioRxiv2024

TIMS2Rescore: A DDA-PASEF optimized data-driven rescoring pipeline based on MS2Rescore

The high throughput analysis of proteins with mass spectrometry (MS) is highly valuable for understanding human biology, discovering disease biomarkers, identifying therapeutic targets, and exploring pathogen interactions. To achieve these goals, specialized proteomics subfields - such as plasma proteomics, immunopeptidomics, and metaproteomics - must tackle specific analytical challenges, such as an increased identification ambiguity compared to routine proteomics experiments. Technical advancements in MS instrumentation can counter these issues by acquiring more discerning information at higher sensitivity levels, as is exemplified by the incorporation of ion mobility and parallel accumulation - serial fragmentation (PASEF) technologies in timsTOF instruments. In addition, AI-based bioinformatics solutions can help overcome ambiguity issues by integrating more data into the identification workflow. Here, we introduce TIMS2Rescore, a data-driven rescoring workflow optimized for DDA-PASEF data from timsTOF instruments. This platform includes new timsTOF MS2PIP spectrum prediction models and IM2Deep, a new deep learning-based peptide ion mobility predictor. Furthermore, to fully streamline data throughput, TIMS2Rescore directly accepts Bruker raw mass spectrometry data, and search results from ProteoScape and many other search engines, including MS Amanda and PEAKS. We showcase TIMS2Rescore performance on plasma proteomics, immunopeptidomics (HLA class I and II), and metaproteomics data sets. TIMS2Rescore is open-source and freely available at https://github.com/compomics/tims2rescore.

bioinformatics↗

bioRxiv2020

NeutrobodyPlex - Nanobodies to monitor a SARS-CoV-2 neutralizing immune response

As the COVID-19 pandemic escalates, the need for effective vaccination programs, therapeutic intervention, and diagnostic tools increases. Here, we identified 11 unique nanobodies (Nbs) specific for the SARS-CoV-2 spike receptor-binding domain (RBD) of which 8 Nbs potently inhibit the interaction of RBD with angiotensin-converting enzyme 2 (ACE2) as the major viral docking site. Following a detailed epitope determination and characterization of the binding mode by structural analysis, we constructed a hetero-bivalent Nb targeting two different epitopes within the RBD:ACE2 interface. This resulted in a high-affinity binder with a viral neutralization efficacy in the picomolar range. Using the bivalent Nb as a surrogate, we established a competitive multiplex binding assay ("NeutrobodyPlex") for detailed analysis of the presence and performance of neutralizing RBD-binding antibodies in the serum of convalescent or vaccinated patients. As demonstrated, the NeutrobodyPlex enables high-throughput screening and detailed analysis of neutralizing immune responses in infected or vaccinated individuals, helping to monitor immune status or guide vaccine design. This approach is easily transferrable to diagnostic laboratories worldwide.

immunology↗

bioRxiv2019

The HLA Ligand Atlas. A resource of natural HLA ligands presented on benign tissues.

The human leukocyte antigen (HLA) complex controls adaptive immunity by presenting defined fractions of the intracellular and extracellular protein content to immune cells. Here, we describe the HLA Ligand Atlas, an extensive collection of mostly matched HLA-I and -II ligandomes from 225 benign samples (29 tissues, 21 subjects). The initial release covers 51 HLA-I and 86 HLA-II allotypes presenting 89,853 HLA-I- and 140,861 HLA-II ligands. We observe that the immunopeptidomes differ considerably between tissues and individuals on both source protein and HLA-ligand level. 1,407 HLA-I ligands stem from non-canonical genomic regions. We highlight the importance of comparatively analyzing both benign and malignant tissues to inform tumor association, based on a case study in three glioblastoma patients. The resource provides insights into applied and basic immune-associated questions in the context of cancer immunotherapy, infection, transplantation, allergy, and autoimmunity. It is publicly available at www.hla-ligand-atlas.org.

immunology↗

bioRxiv2018

Association of HLA class I type with prevalence and outcome of patients with acute myeloid leukemia and mutated nucleophosmin

Acute myeloid leukemia with mutated nucleophosmin (NPMc+ AML) forms a distinct AML subgroup with better prognosis which can potentially be associated with immune response against the mutated nucleophosmin (NPM). As the T-cell-mediated immunity involves antigen presentation on HLA class I molecules, we hypothesized that individuals with suitable HLA type could be less prone to develop NPMc+ AML. We compared HLA class I distribution in NPMc+ AML patient cohort (398 patients from 5 centers) with the HLA allele frequencies of the caucasian population and found HLA-A*02, B*07, B*40 and C*07 underrepresented in the NPMc+ AML group. Presence of B*07 or C*07:01 antigen was associated with better survival in patients without concomitant FLT3 internal tandem duplication. Candidate NPM-derived immunopeptides were found for B*40 and B*07 using prediction software tools. Our findings suggest that a T-cell-mediated immune response could actually explain better prognosis of NPMc+ patients and provide a rationale for attempts to explore the importance of immunosuppressive mechanisms in this AML subgroup.

cancer biology↗