Edoardo Saccenti

This study improves microbial oil fatty acid composition in yeast through genetic modification and cultivation parameter optimization.

MiGenPro trains machine learning models to predict microbial traits from annotated genomes using linked data and semantic frameworks.

This study examines the time-dependent gene expression changes in earthworms exposed to ZnO and ZnO:Mn nanomaterials, revealing transient effects on muscle biology and energy metabolism.

The paper evaluates residual variance structures in toxicokinetic models for predicting chemical uptake and elimination in invertebrates, showing that choosing appropriate variance functions improves model accuracy.

The paper introduces four VAE-based deconfounding frameworks for multi-omics clustering, showing they reduce confounding effects and improve biological clustering.

PortPred uses deep learning embeddings to identify transporter proteins and their substrates from amino acid sequences, outperforming existing methods.

The paper introduces mEthAE, an autoencoder for methylation data that reduces dimensions 400-fold while maintaining accuracy and identifies biologically significant CpG sites through perturbation-based interpretation.

This paper benchmarks deep learning-based embeddings for predicting peroxisomal protein-protein interactions using sequence data and integrates AlphaFold2-Multimer predictions for improved accuracy.

The paper introduces a web server with three algorithms for predicting sub-peroxisomal and sub-mitochondrial protein localisation and PTS1 signals, aiming to accelerate research in peroxisomal biology.

In-Pero predicts peroxisomal protein sub-localisation using deep learning embeddings, achieving over 0.9 classification accuracy.

The paper examines how measurement errors affect Pearson correlation coefficients and discusses methods to improve their estimation under various error models.

This study examines name inconsistencies and ambiguities in biochemical databases used for genome-scale metabolic modeling, finding up to 83.1% inconsistency and proposing solutions for better mapping.

The paper evaluates network inference algorithms on metabolite-metabolite association networks using simulated data from a dynamic metabolic model of arachidonic acid.

The paper analyzes the correlation between 16S-rRNA phylogeny and protein domain content in bacterial genomes to assess functional diversity and its relationship with evolutionary distance.