Alessandra Carbone

The paper predicts residue-level protein-protein interactions between hepatitis B virus core and envelope proteins using deep learning and coevolution signatures, comparing results with experimental data.

PLMView is an unsupervised framework for fine-grained protein function classification from sequence, achieving high precision and speed without labeled data or model fine-tuning.

X-PAIR is a multitask deep learning framework that predicts protein-protein interactions and identifies interface residues from sequence data, outperforming existing methods and enabling proteome-scale analysis.

The paper analyzes the genomic structure and evolution of the S-locus in apple to show how balancing selection maintains conserved S-haplotype architectures despite structural divergence.

The paper analyzes olfactory and gustatory receptor genes and transposable elements in aphid genomes to understand their evolutionary dynamics and role in host adaptation.

PRESCOTT predicts the functional impact of missense mutations using sequence and structural data, outperforming existing methods in variant classification and disease-specific mutation analysis.

LoRA-DR-suite predicts intrinsic and soft disorder in proteins using adapter-based embeddings, with SoftDis providing a database of 500,000 PDB chains.

This study analyzes the mutational landscape of the Monkeypox virus proteome using ESCOTT and provides a resource for assessing new variants.

MuLAN predicts protein interactions and binding affinity changes from sequence data using a deep learning approach without requiring structural information.

SENSE-PPI uses deep learning to predict protein-protein interactions across species and between proteins, showing high accuracy and versatility.

DLA estimates binding affinity changes upon mutation by analyzing protein interfaces with 3D convolutions and achieves a Pearson correlation of 0.81 on 2000 mutations.

The paper compares 3D chromatin organization across species to propose a layer cake model that refines the two compartments model by identifying distinct chromatin layers.

This paper shows that soft disorder in proteins influences assembly pathways by modulating interface formation and function during complex assembly.

DLA-mutation predicts mutation-induced changes in protein-protein binding affinity using a deep learning framework trained on protein complex structures.

DLA-Ranker evaluates protein docking conformations using locally oriented cubes to distinguish near-native from incorrect ones, outperforming other deep learning-based scoring functions.

This paper introduces a molecular cross-docking approach to identify protein partners and assesses its performance against sequence-based deep learning methods.

The paper identifies 50 genes with copy number variation in Neandertal, Denisovan, and Early Sapiens genomes, suggesting dietary adaptations related to lipid and carbohydrate metabolism.

The paper introduces a deep learning method to rank protein docking conformations by analyzing local interface geometry and combines it with physics-based and statistical scoring functions.

LEVELNET is a tool for visualizing, exploring, and comparing protein-protein interaction networks using multilayered graphs and structural data from the Protein Data Bank.

The paper identifies widespread transcription initiation at microsatellites across species and develops deep learning models to predict STR-associated transcription and its impact on disease variants.

ProfileView uses probabilistic models to classify protein sequences and resolve functional diversity across different families, outperforming existing methods.

The paper shows that disordered regions and interaction interfaces in proteins share similar amino acids and that disordered regions provide information about alternative interfaces in protein complexes.

This study develops a computational framework to quantify disorder in coiled-coils and design substitutions to modulate their stability and flexibility.

This paper shows that H1 prevents H3K27me3 accumulation at telomeres and ITRs in Arabidopsis by restricting DNA accessibility to TRB proteins, while promoting PRC2 activity at genes.

PhyChro reconstructs phylogenetic trees using synteny breakpoints and gene adjacencies, achieving high accuracy and speed on vertebrate and yeast genomes.

The paper introduces a method to predict protein-DNA interfaces using evolutionary, physico-chemical, and geometric properties, achieving higher sensitivity than existing methods.

GEMME predicts mutational effects by modeling evolutionary history, outperforming existing methods in speed and accuracy for viral and conserved sequences.

The paper introduces methods to predict protein interaction regions by integrating evolutionary, physico-chemical, and geometrical data with docking simulations.

The paper evaluates cross-docking simulations for predicting protein binding sites, finding that alternate binding sites often correspond to interactions with hidden partners not included in the original dataset.

This paper introduces GEMME, a method for predicting mutational effects using sequence data and enhances it with structural and allele frequency data to improve biological insights.