Biology subjects

Strazar, M.

Publications and source records attributed to Strazar, M..

6 recordsLinked to original sources

bioRxiv2026

Peptide-HLA II interaction prediction for post-translationally modified peptides

CD4+ T cells recognize peptides presented by human leukocyte antigen (HLA) II, implementing a fundamental mediation mechanism of the adaptive immune system. Although post-translational modifications (PTMs) alter immune responses, PTM-peptide-HLA interaction prediction remains challenging due to data scarcity resulting from substoichiometric levels of PTMs. To overcome this, we developed PepChem, a deep learning model utilizing novel, molecular-level peptide representations that enable predictions for sidechain modifications. Using monoallelic datasets that we reanalyze for PTMs of interest, we show accurate predictions on PTMs that were unseen during training. Furthermore, we introduce a novel training protocol that improves PTM-peptide generalization compared to conventional methods. We predict and experimentally validate citrullination-induced binding increase of rheumatoid arthritis (RA)-linked peptides to HLA II risk allele DRB1*04:01. This framework bridges the critical gap in PTM-aware immune recognition prediction, with immediate applications in autoimmunity, cancer, and infectious disease.

bioinformatics↗

bioRxiv2026

A structure-informed deep learning framework for modeling TCR-peptide-HLA interactions

The interaction between T cell receptors (TCRs), peptides, and human leukocyte antigens (HLAs) underlies antigen-specific T cell immunity. Despite substantial advances in peptide- HLA presentation prediction, accurate modeling of coupled TCR-peptide-HLA recognition remains underdeveloped, limiting applications such as TCR and neoepitope prioritization in cancer and antigen identification in autoimmunity. Here we present StriMap, a unified framework for predicting TCR-peptide-HLA interactions by integrating physicochemical, sequence-context, and structural features at recognition interfaces. StriMap achieves state-of-the-art performance with improved generalizability and enables applications in both cancer and autoimmunity. As a case study in ankylosing spondylitis (AS), we screened 13 million peptides derived from 43,241 bacterial proteins and identified candidate molecular mimics that were experimentally validated to activate T cells expressing an AS-associated TCR. Notably, a top validated peptide was enriched in patients with inflammatory bowel disease (IBD), suggesting potential shared microbial triggers between AS and IBD. Overall, StriMap provides a generalizable framework for rational immunotherapy design and for dissecting antigenic drivers of autoimmunity.

bioinformatics↗

bioRxiv2022

Annotating metabolite mass spectra with domain-inspired chemical formula transformers

Metabolomic studies have succeeded in identifying small molecule metabolites that mediate cell signaling, competition, and disease pathology in part due to large-scale community efforts to measure mass spectra for thousands of metabolite standards. Nevertheless, the vast majority of spectra observed in clinical samples cannot be unambiguously matched to known structures, suggesting powerful opportunities for further discoveries in the dark metabolome. Deep learning approaches to small molecule structure elucidation have surprisingly failed to rival classical statistical methods, which we hypothesize is due to the lack of in-domain knowledge incorporated into current neural network architectures. We introduce a new neural network driven workflow for untargeted metabolomics, Metabolite Inference with Spectrum Transformers (MIST), to annotate mass spectrometry peaks with chemical structures generalizing beyond known standards. Unlike other neural approaches, MIST incorporates domain insights into its architecture by forcing the network to more directly link peaks to physical atom representations, neutral losses, and chemical substructures. MIST outperforms both standard neural architectures and the state-of-the-art kernel method on fingerprint prediction from spectra for over 70% of metabolite standards and retrieves over 66% of metabolites with equal or improved accuracy, with 29% strictly better. We further demonstrate the utility of MIST in a prospective setting to identify new differentially abundant metabolite structures from an inflammatory bowel disease patient cohort and subsequently annotate dipeptides and alkaloid compounds without spectral standards.

bioinformatics↗

bioRxiv2022

Spatial host-microbiome sequencing

Mucosal and barrier tissues such as the gut, lung or skin, are composed of a complex network of cells and microbes forming a tight niche that prevents pathogen colonization and supports host-microbiome symbiosis. Characterizing these networks at high molecular and cellular resolution is crucial for our understanding of homeostasis and disease. Spatial transcriptomics has emerged as a key technology to positionally profile RNAs at high resolution in tissues. Here, we present spatial host-microbiome sequencing, an all-sequencing based approach that captures tissue histology, polyadenylated RNAs and bacterial 16S sequences directly from tissues on spatially barcoded glass surfaces. We apply our approach to the mouse gut as a model system, use a novel deep learning approach for data mapping and detect spatial niches impacted by microbial biogeography. Spatial host-microbiome sequencing should enhance study of native host-microbe interactions in health and disease.

genomics↗

bioRxiv2019

openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding

SummaryPoint-based visualisations of large, multi-dimensional data from molecular biology can reveal meaningful clusters. One of the most popular techniques to construct such visualisations is t-distributed stochastic neighbor embedding (t-SNE), for which a number of extensions have recently been proposed to address issues of scalability and the quality of the resulting visualisations. We introduce openTSNE, a modular Python library that implements the core t-SNE algorithm and its extensions. The library is orders of magnitude faster than existing popular implementations, including those from scikit-learn. Unique to openTSNE is also the mapping of new data to existing embeddings, which can surprisingly assist in solving batch effects.\n\nAvailabilityopenTSNE is available at https://github.com/pavlin-policar/openTSNE.\n\nContactpavlin.policar@fri.uni-lj.si, blaz.zupan@fri.uni-lj.si

bioinformatics↗

bioRxiv2019

Embedding to Reference t-SNE Space Addresses Batch Effects in Single-Cell Classification

Dimensionality reduction techniques, such as t-SNE, can construct informative visualizations of high-dimensional data. When working with multiple data sets, a straightforward application of these methods often fails; instead of revealing underlying classes, the resulting visualizations expose data set-specific clusters. To circumvent these batch effects, we propose an embedding procedure that takes a t-SNE visualization constructed on a reference data set and uses it as a scaffold for embedding new data. The new, secondary data is embedded one data-point at the time. This prevents any interactions between instances in the secondary data and implicitly mitigates batch effects. We demonstrate the utility of this approach with an analysis of six recently published single-cell gene expression data sets containing up to tens of thousands of cells and thousands of genes. In these data sets, the batch effects are particularly strong as the data comes from different institutions and was obtained using different experimental protocols. The visualizations constructed by our proposed approach are cleared of batch effects, and the cells from secondary data sets correctly co-cluster with cells from the primary data sharing the same cell type.

bioinformatics↗