Karin M. Verspoor

This study integrates polygenic risk scores and gut metagenomic data to improve prediction of common diseases, showing enhanced predictive performance over conventional risk factors.

This study uses gut microbiome data and machine learning to improve liver disease risk prediction, showing that combining microbiome features with conventional risk factors enhances model performance.

This paper introduces a method to automatically detect inconsistencies in gene ontology annotations using text mining models, achieving high precision on synthetic data.

This study evaluates consensus strategies for haplotype phasing, finding that combining multiple phasing tools reduces switch error and improves accuracy across populations and datasets.

The paper develops an algorithm to detect inconsistent biological sequence database records by comparing them with literature, achieving moderate precision and recall.

The paper assesses sequence database quality by analyzing literature consistency, finding that 25% of records not previously flagged as erroneous are inconsistent with the literature.

This study assesses the scale, types, and impact of duplicates in INSDC nucleotide databases through a benchmark dataset of 67,888 merged groups.

The paper develops new benchmarks for evaluating duplicate detection methods in nucleotide databases, highlighting the limitations of existing benchmarks and the importance of diverse, curated data.