Andrew I. Su

This paper introduces DBR-X, an explainable GNN framework for drug repositioning that outperforms existing models in predicting drug-disease associations and provides interpretable biological explanations.

This paper introduces BTE-RAG, a retrieval-augmented generation framework that improves LLM performance on biomedical benchmarks by integrating mechanistic evidence from federated knowledge sources.

This paper introduces a weighted ensemble method for knowledge graph completion that improves drug-disease candidate discovery by combining knowledge graph embeddings and path-based reasoning.

The paper introduces DrugMechDB, a manually curated database of drug mechanisms for training and evaluating computational drug repurposing models.

This paper evaluates seven link prediction methods on a biomedical knowledge graph to identify drug repurposing candidates by combining path-based reasoning with knowledge graph embedding approaches.

The paper develops a metadata schema based on Schema.org to improve the findability of infectious disease datasets and computational tools across repositories.

The paper introduces outbreak.info Research Library, a platform that aggregates and standardizes over 350,000 COVID-19 resources from sixteen repositories for easy search and exploration.

The paper develops a knowledge network to prioritize drug mechanisms for repositioning, finding it can predict mechanisms with high accuracy.

The paper introduces the BioThings SDK, a toolkit for building high-performance data APIs in biomedical research, enabling integration of annotations from multiple data sources.

The paper introduces a browser-based tool to help researchers and repository developers use schema.org standards to improve the FAIRness of biomedical data.

The paper describes a protocol for enhancing Wikidata with structured knowledge using Shape Expressions, demonstrating its application to SARS-CoV-2 and other coronaviruses.

The paper describes Wikidata as a FAIR knowledge graph for life sciences, showcasing its breadth, tools for integration, and use cases in biomedical analysis.

The paper presents a structured review of NGLY1 Deficiency as a knowledge graph, improving hypothesis generation through FAIR principles and enabling collaborative curation.

The paper demonstrates how open innovation competitions improve computational biology methods for antibody clustering, gene expression imputation, and CMap querying.

The paper demonstrates that citizen scientists can perform relationship extraction from biomedical abstracts using Mark2Cure, highlighting the importance of accurate named entity recognition.

This study used whole-exome sequencing to investigate genetic factors associated with long-term kidney transplant rejection but found no statistically significant associations.

This study demonstrates that triflic acid treatment solubilizes insoluble bacterial biomass, enabling comprehensive proteomic analysis of Gram- and Gram+ bacteria and human microbiome samples.

This study identifies and prioritizes damaging mutations in the Jurkat cell line using whole-genome sequencing and public databases, linking them to known expression defects.

The paper explores using crowdsourcing for cryo-EM particle picking, showing its potential and limitations through experiments with untrained citizen scientists.

The paper implements JSON-LD on BioThings APIs to enhance interoperability through semantic annotations, enabling cross-linking and improved query capabilities.

The paper uses metaproteomics to analyze colonic microbiota in colitic mice and controls, identifying changes in protein functions linked to inflammation.

The paper introduces Science Game Lab, a platform to support the creation and enhancement of scientific games with a purpose.

EXPLANe annotates scientific posters with genetic variant information using mobile devices and optical text recognition.

WikiGenomes provides a web platform for community curation of gene annotations in Wikidata, addressing the lack of resources for comprehensive genomic data curation.

The paper introduces RASLseqTools, an open-source software package for designing and analyzing RASL-seq experiments, and demonstrates normalization methods for improving reproducibility.

The paper imports human and mouse gene and protein data into Wikidata to improve data integration and dissemination, enabling updates to Wikipedia Gene Wiki infoboxes and multilingual access.

The paper describes Wikidata as a platform for integrating and disseminating life science data, linking genes, drugs, and diseases to enhance Wikipedia and foster community collaboration.

Omics Pipe automates multi-omics data analysis pipelines, supporting RNA-seq, miRNA-seq, Exome-seq, Whole Genome sequencing, and ChIP-seq with reproducible and extensible tools.

MyGene.info provides a scalable service for querying gene annotations across species, supporting over 14K species and 17M genes with 50+ annotation types through two web service endpoints.

OncoRep is an RNA-Seq based tool for breast cancer patients that provides molecular classification, actionable targets, and drug recommendations in an interactive report.