Michel Dumontier

This paper improves sound recognition by incorporating semantic information into deep neural networks, showing better alignment with human perception than traditional categorical models.

The paper introduces the GA4GH Phenopacket schema to standardize the exchange of phenotypic data for precision medicine applications.

FAIRshake evaluates the FAIRness of research digital resources through community-driven metrics, automated assessments, and visualization tools, revealing opportunities for improvement.

The paper introduces a framework to evaluate FAIRness of digital resources through automated, community-governed maturity indicators and compliance tests.

The paper develops a machine learning algorithm to predict MCI conversion to AD using clinical data, achieving high AUROC and sensitivity.

The paper presents a large-scale cancer pharmacogenomic screen with 11,576 experiments on 910 drug combinations across 85 cancer cell lines, enabling crowd-sourced prediction of synergistic drug pairs and biomarkers.

Vec2SPARQL integrates vector space representations with SPARQL queries to enable semantic similarity and classification within a single query for biomedical applications.

The paper introduces FAIR Evaluator, a tool to assess FAIRness of digital resources, and compares automated vs manual evaluations across repositories.

The paper outlines ten lessons for designing, provisioning, and reusing persistent identifiers to improve data integration in life sciences.

The paper publishes DisGeNET as nanopublications using Trusty URIs to enable versioned, provable data linking for gene-disease associations.

The paper introduces FALDO, an ontology for standardizing the description of sequence feature locations, enabling integration of annotations across different data sources and formats.