Biology subjects

Szczurek, E.

Publications and source records attributed to Szczurek, E..

At least 19 recordsLinked to original sources

bioRxiv2026

Modelling interpretable patient-level representationsfrom structured and simple multimodal data

Patient cohort profiling increasingly includes structured views for multiple modalities, such as single-cell RNA sequencing, spatial transcriptomics or proteomics, and histology, each providing multiple subobservations per patient, including single cells, spatial spots or patches. To model such data along with simple patient-level views, current multimodal integration methods typically rely on separately precomputed summaries and fail to fully leverage information in structured views. Here we present FACTMx, a variational framework that jointly models structured and simple views to learn interpretable patient-level representations. FACTMx couples latent patient factors with subobservation clustering and per-patient component proportions, enabling direct interpretation and downstream association analyses. The framework supports different structured-view mixture assumptions, including topic- and Gaussian-structured data, while retaining modular encoder-decoder parameterisations. In simulations spanning sparse and dense dependencies and multiple noise regimes, FACTMx improved reconstruction, integration and recovery of structured components relative to previous methods. Applied to non-small cell lung cancer cohorts, FACTMx captured survival-associated latent signals linked to immune microenvironments, gene expression pathways and spatially coherent histological patterns. In a longitudinal coronary syndrome cohort, FACTMx highlighted an outcome-associated axis connected to ejection-fraction change, immune cell states, soluble mediators and cardiac injury markers. These results support joint structured-simple modelling for interpretable multimodal patient stratification.

bioinformatics↗

bioRxiv2026

Designing antimicrobials with programmable mechanism and safety

Antimicrobial peptides (AMPs) are a promising solution to antimicrobial resistance, yet generative models for their design cannot control the physicochemical properties and motifs that shape activity and selectivity. Here, we present OmegAMP, a conditional diffusion framework controlling net charge, mean hydrophobicity, and sequence length, supporting de novo, analog, and motif-guided design. Across 204 wet-lab characterized peptides, de novo generation yielded antimicrobials with broad activity against multidrug-resistant Gram-negative isolates. Analog generation converted six inactive prototypes into antimicrobials, with the prototype determining each analog's membrane-disruption mode and mammalian-cell safety. Motif-guided analog generation preserved lipopolysaccharide engagement of active prototypes, and a redesigned non-antimicrobial leucine zipper acquired antimicrobial activity while retaining DNA-perturbing character in vitro. In murine skin and thigh infection models, leads reduced bacterial burden, with a motif-guided DNA-perturbing lead matching the fluoroquinolone control systemically. OmegAMP opens a programmable route to new peptide antibiotics whose mechanism and safety follow from the chosen prototype.

bioinformatics↗

bioRxiv2026

BATTLE-AMP: Benchmarking Antimicrobial Peptide Predictors

As antimicrobial resistance outpaces antibiotic development, antimicrobial peptides (AMPs) have emerged as a promising class of alternative antibacterials, and computational predictors are increasingly used to prioritize AMP candidates. Such predictors are typically evaluated on binary AMP/non-AMP classification, which does not test whether they can identify peptides with clinically relevant potency against specific pathogens. We present BATTLE-AMP, a benchmarking framework that evaluates AMP predictors against experimentally measured minimum inhibitory concentrations (MICs) across clinically relevant bacterial species and strains. We surveyed 48 published methods, finding fewer than 25% reproducible, and benchmarked 10 model families (21 variants) using experimental MIC data, synthetic sequence perturbations, activity cliff analyses, and all-atom molecular dynamics (MD) simulations. Four findings emerge: (i) models trained on MIC data outperform binary classifiers regardless of architecture; (ii) the best model depends on the target pathogen, so model selection must be guided by the biological question; (iii) most models cannot distinguish active peptides from inactive sequences with identical amino acid composition; and (iv) activity cliffs remain unresolved by both machine learning and MD, marking a limit of current computational methods. BATTLE-AMP is released as an open Snakemake framework at https://github.com/szczurek-lab/battleamp-snakemake for benchmarking new models and scoring novel candidate libraries.

bioinformatics↗

bioRxiv2026

Pathogen-specific host responses define distinct pneumonia endotypes in the human lung

Pneumonia is the leading cause of death from infectious disease worldwide. The diagnosis and treatment of patients with pneumonia lag behind other major conditions, relying on syndromic definitions that lack molecular resolution and ignore underlying endotypes. We sought to test the hypothesis that dynamic pathogen-specific host responses in the alveolar space represent distinct pneumonia endotypes linked to different clinical features and outcomes. We prospectively enrolled a cohort of 690 patients (including immunocompromised patients) with known or suspected pneumonia receiving mechanical ventilation in whom the etiology of pneumonia was determined by gold-standard analysis of distal lung fluid obtained by bronchoalveolar lavage (BAL) combined with clinical adjudication. From these patients, we analyzed 792 BAL fluid samples, including 310 serial samples, using flow cytometry (482 patients) and single-cell RNA-sequencing (170 patients; 263 samples, complemented by 9 healthy controls and 25 post-COVID-19 patients, yielding [~]2.4 million single cells across 28 cell types), and extracted daily clinical data from the electronic health record (>15,000 patient-days). We used machine learning models to identify pathogen-specific host responses in the transcriptome of alveolar immune cells that were associated with changes in alveolar cell abundance and clinical features. Our results suggest that therapeutic strategies for pneumonia should be individualized to specific host-pathogen interactions.

immunology↗

bioRxiv2026

A universal taxonomic and functional human gut microbiome model for disease classification and phenotype discovery

The human gut microbiome is a powerful indicator of host health, yet its compositional nature, high sparsity, and inter-individual variability complicate downstream analysis. Here, we introduce two complementary approaches to characterize gut microbiome structure at population scale. First, we define eight functional signatures of the human gut microbiome using Non-negative Matrix Factorization, revealing coordinated metabolic patterns that partially decouple from taxonomic composition. Second, we present GUT-FORMer, a transformer-based autoencoder that jointly models taxonomic and functional metagenomic profiles from close to 21,000 publicly available samples. The learned latent representations capture biologically meaningful structure, reflect geographic and disease-associated variation, and enable accurate classification of 25 diseases in both binary and multiclass settings, as well as regression of host age and BMI. GUT-FORMer outperforms existing microbiome indices and deep learning methods across all tasks, establishing a generalizable framework for microbiome-based precision medicine.

bioinformatics↗

bioRxiv2026

Integrated kidney and urine proteomics define encrypted antimicrobial peptides as effectors of host defence in human pyelonephritis

Antimicrobial peptides (AMPs) are key effectors of host defence, however, their functional deployment across renal tissue and urine in pyelonephritis (PN) remains incompletely understood. Here, we integrate kidney and urine proteomics with urinary peptidomics and computational prediction to define AMP organisation and function. Proteomic analysis indicated coordinated induction of multiple AMPs in infected kidneys. These patterns were recapitulated in the urinary proteome, where AMP abundance correlated with leukocyte counts. Multiplex immunofluorescence microscopy localised these AMPs to myeloid cells, identifying them as central effector sources. Importantly, analysis of the urine peptidome revealed multiple encrypted AMPs (EPs), which arise from proteolytic processing of precursor proteins. To systematically assess their relevance for host defence, we applied an ensemble of machine learning-based predictors to prioritise candidates with activity in the urinary environment. This approach identified several potential EPs, among which the S100A12-derived peptide Calcitermin was confirmed in patient urine. Furthermore, it exerts antibacterial activity against uropathogenic E. coli (UPEC) and modulates myeloid cell responses. Together, these findings define a coordinated and compartmentalised AMP defence programme in human PN that extends beyond increased peptide expression, highlighting EPs as functionally relevant effectors with therapeutic potential.

immunology↗

bioRxiv2026

Cross-View Latent Integration via Nonparametric Gamma Shrinkage Factor Analysis

Factor analysis is a dominant paradigm for multi-omic heterogeneous data, but is challenged by partially redundant signals and noise across views and by an unknown true number of factors. We present CLING, an unsupervised multi-view factor model with hierarchical Bayesian sparsity priors: a product-of-Gammas prior inducing cumulative column-wise shrinkage (increasing with factor index) coupled with a Gamma-Gamma local-precision hierarchy on loadings yielding heavy-tailed marginals. This pairing enables automatic factor selection by adaptively deactivating unsupported factors while retaining active ones during inference, and induces selective sparsity that allows salient loadings to escape shrinkage while collapsing negligible ones. As a fully conjugate hierarchical model, CLING admits a scalable variational inference algorithm for multi-view data. Across synthetic benchmarks and multiomics datasets, CLING recovers more accurate factors and more informative loadings while explaining at least as much variance as competitive multi-view baselines; on glioblastoma gene expression and DNA methylation data, CLING identifies pathways linked to tumor subtype and patient age. Source code: https://github.com/szczurek-lab/CLING.

bioinformatics↗

bioRxiv2025

Cellohood: multi-granular discovery of cellular neighborhoods with a permutation-invariant set transformer auto-encoder

Discovering cellular neighborhoods and their roles in disease requires computational methods that consider the full breadth of data and offer multi-level granularity and interpretability. Here, we introduce Cellohood, a permutation-invariant set transformer auto-encoder equipped with a clinical association pipeline. Cellohood encodes full readouts for bags of spatially co-localized cells and supports multi-level analyses, providing interpretability by mapping latent dimensions to spatial tissue features. Our model surpasses current methods in accuracy of cellular neighborhood detection for spatial transcriptomics of the human cortex and CODEX spleen data measuring lupus progression. Applied to cancer data across three granularity levels, our method recovers neighborhoods along the expected immune-cold to immune-hot spectrum and further refines them into biologically and clinically meaningful subclasses, revealing spatial patterns linked to prognosis, histology, stage, and tumor mutational burden, and uncovering subgroups that transcend standard classifications. Overall, Cellohood enables in-depth analysis of complex tissues, revealing clinically informative spatial neighborhoods.

bioinformatics↗

bioRxiv2025

PepGlider: Property Regularized VAE for interpretable and controllable peptide design

AO_SCPLOWBSTRACTC_SCPLOWComputational peptide design requires precise control over peptide properties that often exhibit complex correlations. Existing generative models for peptide design rely on simplistic discrete conditioning mechanisms rather than precise targeting of specific property values. We present PepGlider, a continuous property regularization framework that enables direct control over their specific values. The method achieves structured latent space with superior disentanglement quality and displays smooth property gradients along regularized dimension. In silico experimental results demonstrate that PepGlider enables independent control of naturally correlated properties, and supports both de novo generation and targeted optimization of existing peptides. PepGlider applied to antimicrobial peptide design allows generation of candidates with desired antibacterial activity profile and maintained low toxicity profile. Unlike existing approaches, PepGlider provides precise control over continuous property distributions while maintaining generation quality, thus offering a generalizable solution for therapeutic and materials applications requiring exact property specifications.

bioinformatics↗

bioRxiv2023

DelSIEVE: joint inference of single-nucleotide variants, somatic deletions, and cell phylogeny from single-cell DNA sequencing data

With rapid advancements in single-cell DNA sequencing (scDNA-seq), various computational methods have been developed to study evolution and call variants on single-cell level. However, modeling deletions remains challenging because they affect total coverage in ways that are difficult to distinguish from technical artifacts. We present DelSIEVE, a statistical method that infers cell phylogeny and single-nucleotide variants, accounting for deletions, from scDNA-seq data. DelSIEVE distinguishes deletions from mutations and artifacts, detecting more evolutionary events than previous methods. Simulations show high performance, and application to cancer samples reveals varying amounts of deletions and double mutants in different tumors.

bioinformatics↗

bioRxiv2023

ST-Assign: a probabilistic model for joint cell type identification in spatial transcriptomics and single-cell RNA sequencing data

Understanding the intricate composition of tissues in complex living organisms is crucial for unraveling the mechanisms underlying health and disease. This study addresses the challenge of dissecting cell types within tissues by integrating information from two powerful experimental techniques: single-cell RNA-sequencing (scRNA-seq) and spatial transcriptomics (ST). While scRNA-seq offers insights into transcriptional heterogeneity at the cellular level, ST provides spatial information within tissues. Current methods for cell-type annotation in scRNA-seq and mixture decomposition in ST data are often conducted independently, resulting in reduced statistical power and accuracy. To bridge this gap, we propose ST-Assign, a novel hierarchical Bayesian probabilistic model that jointly performs cell-type annotation in scRNA-seq data and cell-type mixture decomposition in ST data. ST-Assign accounts for shared variables such as gene expression profiles and leverages prior knowledge about marker genes, amplifying statistical strength and mitigating experimental noise. The models excellent performance is demonstrated on simulated and real mouse brain data, showcasing accurate cell-type mixture decomposition and cell-type assignment. In comparison to existing tools, ST-Assign demonstrates superior capabilities, particularly in the task of assigning cell types to individual cells. ST-Assign enables exploring the spatial composition of cell types and holds the potential for enhancing our comprehension of diverse biological systems.

bioinformatics↗

bioRxiv2022

Tumoroscope: a probabilistic model for mapping cancer clones in tumor tissues

Spatial and genomic heterogeneity of tumors is the key for cancer progression, treatment, and survival. However, a technology for direct mapping the clones in the tumor tissue based on point mutations is lacking. Here, we propose Tumoroscope, the first probabilistic model that accurately infers cancer clones and their high-resolution localization by integrating pathological images, whole exome sequencing, and spatial transcriptomics data. In contrast to previous methods, Tumoroscope explicitly addresses the problem of deconvoluting the proportions of clones in spatial transcriptomics spots. Applied to a reference prostate cancer dataset and a newly generated breast cancer dataset, Tumoroscope reveals spatial patterns of clone colocalization and mutual exclusion in sub-areas of the tumor tissue. We further infer clone-specific gene expression levels and the most highly expressed genes for each clone. In summary, Tumoroscope enables an integrated study of the spatial, genomic, and phenotypic organization of tumors.

cancer biology↗

bioRxiv2022

SLIDE-VIP: a comprehensive, cell line- and patient-based framework for synthetic lethality prediction in DNA damage repair, chromatin remodeling and cell cycle

Discovering synthetic lethal (SL) gene partners of cancer genes is an important step in developing cancer therapies. However, identification of SL interactions is challenging, due to a large number of possible gene pairs, inherent noise and confounding factors in the observed signal. To discover robust SL interactions, we devised SLIDE-VIP, a novel framework combining eight statistical tests, including a new patient data-based test iSurvLRT. SLIDE-VIP leverages multi-omics data from four different sources: gene inactivation cell line screens, cancer patient data, drug screens and gene pathways. We applied SLIDE-VIP to discover SL interactions between genes involved in DNA damage repair, chromatin remodeling and cell cycle, and their potentially druggable partners. The top 883 ranking SL candidates had strong evidence in cell line and patient data, 250-fold reducing the initial space of 200K pairs. Drug screen and pathway tests provided additional corroboration and insights into these interactions. We rediscovered well-known SL pairs such as RB1 and E2F3 or PRKDC and ATM, and in addition, proposed strong novel SL candidates such as PTEN and PIK3CB. In summary, SLIDE-VIP opens the door to the discovery of SL interactions with clinical potential. All analysis and visualizations are available via the online SLIDE-VIP WebApp.

bioinformatics↗

bioRxiv2022

Celloscope: a probabilistic model for marker-gene-driven cell type deconvolution in spatial transcriptomics data

Spatial transcriptomics maps gene expression across tissues, posing the challenge of determining the spatial arrangement of different cell types. However, spatial transcriptomics spots contain multiple cells. Therefore, the observed signal comes from mixtures of cells of different types. Here, we propose an innovative probabilistic model, Celloscope, that utilizes established prior knowledge on marker genes for cell type deconvolution from spatial transcriptomics data. Celloscope outperformed other methods on simulated data, successfully indicated known brain structures and spatially distinguished between inhibitory and excitatory neuron types based in mouse brain tissue, and dissected large heterogeneity of immune infiltrate composition in prostate gland tissue.

bioinformatics↗

bioRxiv2022

SIEVE: joint inference of single-nucleotide variants and cell phylogeny from single-cell DNA sequencing data

Single-cell DNA sequencing (scDNA-seq) has enabled the identification of single nucleotide somatic variants and the reconstruction of cell phylogenies. However, statistical phylogenetic models for cell phylogeny reconstruction from raw sequencing data are still in their infancy. Here we present SIEVE (SIngle-cell EVolution Explorer), a statistical method for the joint inference of somatic variants and cell phylogeny under the finite-sites assumption from scDNA-seq reads. SIEVE leverages raw read counts for all nucleotides at candidate variant sites, and corrects the acquisition bias of branch lengths. In our simulations, SIEVE outperforms other methods both in phylogenetic accuracy and variant calling accuracy. We apply SIEVE to three scDNA-seq datasets, for colorectal (CRC) and triple-negative breast cancer (TNBC), one of them generated by us. On simulated data, SIEVE reliably infers homo-and heterozygous somatic variants. The analysis of real data uncovers that double mutant genotypes are rare in CRC but unexpectedly frequent in TNBC samples.

bioinformatics↗

bioRxiv2022

HydrAMP: a deep generative model for antimicrobial peptide discovery

Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.

bioinformatics↗

bioRxiv2021

Deep learning-based tumor microenvironment segmentation is predictive of tumor mutations and patient survival in non-small-cell lung cancer

Despite the fact that tumor microenvironment (TME) and gene mutations are the main determinants of progression of the deadliest cancer in the world - lung cancer - their interrelations are not well understood. Digital pathology data provide a unique insight into the spatial composition of the TME. Various spatial metrics and machine learning approaches were proposed for prediction of either patient survival or gene mutations from these data. Still, these approaches are limited in the scope of analyzed features and in their explainability and as such fail to transfer to clinical practice. Here, we generated 23,199 image patches from 55 hematoxylin-and-eosin (H&E)-stained lung cancer tissue sections and annotated them into 9 different tissue classes. Using this dataset, we trained a deep neural network ARA-CNN, achieving per-class AUC ranging from 0.72 to 0.99. We applied the trained network to segment 467 lung cancer H&E images downloaded from The Cancer Genome Atlas (TCGA) database. We used the segmented images to compute human interpretable features reflecting the heterogeneous composition of the TME, and successfully utilized them to predict patient survival (c-index 0.723) and cancer gene mutations (largest AUC 73.5% for PDGFRB). Our approach can be generalized to different cancer types to inform precision medicine strategies.

bioinformatics↗

bioRxiv2021

CONET: Copy number event tree model of evolutionary tumor history for single-cell data

Copy number alterations constitute important phenomena in tumor evolution. Whole genome single cell sequencing gives insight into copy number profiles of individual cells, but is highly noisy. Here, we propose CONET, a probabilistic model for joint inference of the evolutionary tree on copy number events and copy number calling. CONET employs an efficient MCMC procedure to search the space of possible model structures and parameters and utilizes both per-bin and per-breakpoint data. We introduce a range of model priors and penalties for efficient regularization. CONET achieves excellent performance on simulated data and for 260 cells from xenograft breast cancer sample.

bioinformatics↗