Andrea Di Gioacchino

Designing molecular RNA switches with Restricted Boltzmann machines

The paper designs RNA switches using Restricted Boltzmann machines and validates their structural switching properties through experimental testing.

Repeats Mimic Pathogen-Associated Patterns Across a Vast Evolutionary Landscape

The paper quantifies viral mimicry in genomes across species and shows how repetitive elements maintain pathogen-like features under selection.

Learning the differences: a transfer-learning approach to predict antigen immunogenicity and T-cell receptor specificity

This paper introduces diffRBM, a transfer-learning model using Restricted Boltzmann Machines to predict antigen immunogenicity and T-cell receptor specificity, achieving performance comparable to existing methods.

sgDI-tector: defective interfering viral genome bioinformatics for detection of coronavirus subgenomic RNAs

sgDI-tector detects and quantifies subgenomic RNAs in SARS-CoV-2 NGS data, identifying a ranked set of sgRNAs and comparing their levels to defective interfering viral genomes.

The heterogeneous landscape and early evolution of pathogen-associated CpG dinucleotides in SARS-CoV-2

The paper analyzes CpG dinucleotide distribution in SARS-CoV-2, finding low average CpG content with fluctuations linked to immune evasion and replication strategies.