Theodor Sperlea

This paper develops a random forest model to predict antifouling paint presence in sediment using 16S rRNA sequencing data, achieving high accuracy in presence detection but not concentration.

This paper applies topic modeling to estuarine microbiome data, showing it performs comparably to PCA and PCoA and identifies seasonal microbial sub-communities.

This study uses comparative genomics to identify virulence-related genes in Vibrio vulnificus by analyzing clinical and environmental isolates, revealing convergent evolution and potential diagnostic markers.

The paper detects a semi-annual biotic cycle in temperate aquatic communities using machine learning on DNA metabarcoding data, linking it to insolation patterns and photoautotrophs.

This study investigates how microbial communities adapt after coalescence by mixing freshwater and seawater samples in controlled experiments, finding that environmental filtering has a stronger impact than mixing ratios.

The paper introduces γBOriS, a motif-based machine learning tool for identifying oriC sequences in Gammaproteobacteria, and presents BOriS DB, a database containing 25,827 oriC sequences from 1,217 species.

This study compares machine learning methods for protein sequence classification using FCGR encoding, finding that deep neural networks outperform others.