Silvio C. E. Tosatto

DOME Copilot automates the generation of transparent AI methodology reports for life science publications, matching or exceeding manual quality while reducing creation time.

The paper identifies a bias in IDR-binding site prediction benchmarks due to differences in disorder propensity between datasets, showing predictors trained on one type of data perform poorly on others.

emb2dis predicts protein disorder using a deep learning model combining ResNets and dilated convolutions, achieving top performance on benchmark datasets.

AlphaFlex generates atomistic conformational ensembles for human proteins with intrinsically disordered regions, integrating AlphaFold models and implicit bilayers for transmembrane proteins.

This study uses a mathematical model combined with OCTA images to simulate tumor-induced angiogenesis in retinal hemangioblastoma, revealing critical insights into the timing and dynamics of vascular development.

GeomeTRe calculates geometric descriptors for tandem repeat proteins, improving their classification by analyzing structural symmetry and variations in spatial arrangements.

STRPsearch detects structured tandem repeat proteins by aligning protein structures to a curated database and mapping repeat units efficiently.

The paper develops a pipeline to transfer annotations between disordered proteins using orthologs and multiple sequence alignments, expanding the availability of annotations beyond globular domains.

The paper evaluates AlphaFold2's ability to predict intrinsically disordered regions and conditionally folded regions using the CAID dataset, finding it highly competitive.

PDB ProtVista is a sequence feature viewer that provides 2D visualization of residue-level annotations and integrates with 3D molecular viewers.

3D-Beacons provides a federated network to unify access to protein structure data from multiple sources, enabling comparative analysis of models.

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

APICURON credits biocurators by tracking their work across knowledgebases, using gamification and an API for resource integration.

The paper shows that evolutionary rates of intrinsically disordered proteins correlate with conformational diversity, suggesting that structural constraints from selected conformers influence rate heterogeneity.

The paper analyzes experimental evidence for long intrinsically disordered protein regions in the PDB, showing increased coverage of intrinsic disorder over the last decade.

The paper evaluates hydroxylation site predictors using independent datasets, finding they perform no better than random, highlighting issues with self-reported performance and generalization.

This study presents a framework for predicting blood cholesterol levels from genotype data by optimizing a simulation algorithm using literature-based patient cholesterol levels.

The paper develops a low-cost NGS gene panel for diagnosing intellectual disability and autism spectrum disorder, achieving a 27% diagnostic yield in 150 patients.

The paper compares structural constraints in ordered and disordered protein ensembles, finding similar proportions of constrained sites and long-range contacts.