Biology subjects

Mozejko, M.

Publications and source records attributed to Mozejko, M..

6 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

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↗

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↗

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↗

bioRxiv2019

ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

bioinformatics↗