Joseph Loscalzo

The paper identifies domain-specific phenotypic effects of MACF1 variants outside the GAR domain, revealing broader neurodevelopmental and craniofacial anomalies.

This paper shows that 2-hydroxyglutarate (2HG) alters fatty acid partitioning, reducing lipotoxic stress by shifting fatty acids toward storage and away from oxidation and membrane synthesis.

This paper demonstrates that ensilication preserves DNA integrity at ambient temperature, enabling diagnostic-quality long-read sequencing without cold-chain infrastructure.

ExplainBind predicts protein-ligand binding likelihood and identifies key residues and non-covalent interactions without structural inputs, outperforming existing methods and enabling drug discovery insights.

NetMedGPT is a transformer-based foundation model trained on biomedical knowledge graphs to predict drug-disease associations and support drug repurposing, outperforming specialized models in multiple tasks.

NetMedPy provides a computational package for efficient Network Medicine analyses, supporting diverse scoring functions and metrics for large-scale molecular screening.

ATOMICA learns transferable representations of intermolecular interactions across diverse molecular types, enabling cross-modal comparisons and experimentally testable hypotheses.

DREAMER identifies molecular mechanisms of adverse drug reactions and disease phenotypes using network-based analysis, revealing key proteins and pathways involved in various conditions.

This paper introduces Pathopticon, a network-based method integrating pharmacogenomics, cheminformatics, and disease phenotypes to prioritize cell lines and drugs for cell type-guided drug discovery.

This study identifies branched chain α-ketoacids (BCKAs) as novel signaling metabolites that activate HIF1α signaling in normoxia and modulate vascular smooth muscle cell function in pulmonary vascular disease.

The paper introduces PIONEER, a deep learning framework for predicting protein-protein interfaces, and shows disease mutations are enriched in these interfaces, identifying oncoPPIs linked to cancer survival and drug responses.

The paper evaluates 24 network-based methods for predicting protein-protein interactions across five interactomes, identifies top-performing methods, and validates their predictions experimentally.

The paper analyzes the robustness of multilayer biological networks by integrating gene regulatory, protein-protein interaction, and metabolic data to assess how perturbations affect system stability.

This study identifies disease mutations that perturb protein-protein interactions in the human 3D interactome, showing their association with cancer survival and drug response.

The paper develops a network medicine framework to predict polyphenol therapeutic effects by analyzing the proximity of their protein targets to disease proteins in the human interactome.

The paper identifies NFATC4 as a key regulator of Type 2 Diabetes genes by analyzing a gene regulatory network in pancreatic islets and linking it to eQTLs and differential expression.

This paper introduces a new disease classification system (NCD) that integrates phenotypic and molecular networks to improve disease specificity and redefine disease boundaries.