Jeremy J. Yang

BiomarkerKB integrates and standardizes biomarker data from multiple sources to enable structured exploration and discovery of biomarker-disease relationships.

The paper describes the Common Fund Data Ecosystem (CFDE), which integrates NIH Common Fund data resources to enable discovery, analysis, and collaboration across heterogeneous datasets.

KG2ML identifies disease-associated genes not in existing knowledge graphs using positive unlabeled learning and integrates with machine learning for improved classification.

The paper introduces a knowledge graph framework for integrating and querying biomedical data across domains, demonstrating its utility in eight use cases.

The paper introduces a degree-aware edge sampling method to reduce performance inflation in biomedical graph representation learning caused by imbalanced edge degree distributions.

The paper constructs a reproductive toxicity knowledge graph (ReproTox-KG) to link birth defects, drugs, and genes, identifying potential molecular mechanisms for drug-induced birth defects.

The paper builds a knowledge graph analytics platform integrating LINCS and IDG to identify and prioritize novel drug targets for Parkinson's disease.

TIGA aggregates and ranks gene-trait associations from GWAS data to prioritize drug targets using statistical and bibliometric evidence.

The paper identifies sex-biased differential alternative splicing across multiple human tissues and links it to gene function and estrogen response.

The paper uses machine learning to identify potential autophagy-related genes, finding 23% of top predictions in existing databases and suggesting 193 genes as possible 'dark genes'.

The paper introduces the Drug Target Ontology (DTO) to classify and integrate drug discovery data by formalizing druggable protein targets and their characteristics.