Tomasz Kościółek

A large-scale comparative metagenomic analysis of short-read sequencing platforms indicates high taxonomic concordance and functional analysis challenges

This study compares taxonomic and functional profiles of human gut microbiome samples sequenced on two platforms, finding high taxonomic concordance but functional discrepancies.

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

This paper introduces GUT-FORMer, a transformer-based autoencoder for gut microbiome analysis, achieving accurate disease classification and host trait prediction.

Scaling and democratising structure-based protein function prediction with metagenomic-deepFRI

The paper introduces metagenomic-deepFRI, a framework that integrates protein structure models into functional annotation pipelines, improving GO term prediction confidence and coverage in metagenomic datasets.

Novel insights into the genetic architecture and mechanisms of host/microbiome interactions from a multi-cohort analysis of outbred laboratory rats

The paper identifies host genetic effects on microbiome composition in rats and finds evidence of indirect genetic effects contributing to missing heritability.

High-altitude mountaineering induces adaptive gut microbiome shifts associated with dietary intake and performance markers

This study shows high-altitude mountaineering alters gut microbiome composition and function, linked to dietary intake and performance markers in alpinists.

Integrative Metagenomic and Blood Biomarker Analysis Reveals Distinct Metabolic Responses to Aerobic and Anaerobic Interventions in Athletic and Non-Athletic Individuals

This study integrates metagenomic and blood biomarker data to show that aerobic and anaerobic exercise elicit distinct metabolic responses mediated by the gut microbiome in athletes and non-athletes.

Aggregating gut: on the link between neurodegeneration and bacterial functional amyloids

The paper identifies gut microbiome functional amyloids and links their abundance to neurodegenerative diseases like Parkinson's and Alzheimer's.

Adaptation to space conditions of novel bacterial species isolated from the International Space Station revealed by functional gene annotations and comparative genome analysis

The paper functionally annotates genomes of ISS-isolated bacteria and identifies adaptations to space conditions through comparative genomics and proteome analysis.

Expanding the cultivated human archaeome by targeted isolation of novel Methanobrevibacter strains from fecal samples

This study isolates and characterizes novel Methanobrevibacter strains from human fecal samples, expanding the cultivated archaeome and linking them to gastrointestinal health.

Microbiome time series data reveal predictable patterns of change

This study analyzes microbiome time series data to show that the gut microbiome is stable and predictable over time despite individual bacterial volatility.

Large protein databases reveal structural complementarity and functional locality

This work analyzes protein structure databases to reveal functional clustering and creates a unified low-dimensional representation for exploring sequence-structure-function relationships.

Gut Microbiome Dynamics and Predictive Value in Hospitalized COVID-19 Patients: A Comparative Analysis of Shallow and Deep Shotgun Sequencing

This study examines gut microbiome changes in hospitalized COVID-19 patients using shallow and deep shotgun sequencing to assess their predictive value for clinical outcomes.

Effects of Data Transformation and Model Selection on Feature Importance in Microbiome Classification Data

This study evaluates how data transformations and model selection affect feature importance in microbiome classification, showing that presence-absence transformations perform well and only a small subset of features is critical for classification.

Comprehensive function annotation of metagenomes and microbial genomes using a deep learning-based method

The paper develops a metagenome analysis workflow combining de novo genome reconstruction, taxonomic profiling, and deep learning-based functional annotation, showing improved coverage over existing methods.

Reply to: Caution Regarding the Specificities of Pan-Cancer Microbial Structure

The authors reanalyze their pan-cancer microbiome findings using decontaminated data to address concerns about contamination, batch effects, and machine learning approaches.

Deep embeddings to comprehend and visualize microbiome protein space

The paper uses a deep learning model to represent microbial proteins for alignment-free analysis and visualization, showing it can capture structural and functional features.

Sequence-structure-function relationships in the microbial protein universe

The paper predicts structures and annotates functions for diverse microbial protein sequences, identifying novel folds and highlighting the saturation of structural space.

Structure-Based Function Prediction using Graph Convolutional Networks

This paper introduces a Graph Convolutional Network for predicting protein function and identifying important residues, showing improved accuracy over sequence-based methods.