Paweł Szczerbiak

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.

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.

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.

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.