Research
URL Crawl and Classification for Open Access Datasets and Software (OADS) in Scholarly Documents – Dr. Jian Wu, Spencer Peloquin
Abstract:
The purpose of this experiment was to crawl and classify the OADS research repository to uncover which disciplines were losing research data to URL link rot for future remediation.
URL link rot is an ongoing problem in digital academia, with numerous studies and research being lost due to changes in access and indexing. In order to maintain the permanence of critical research in the online domain, it is necessary to discover which studies are most impacted and the reasons why this occurs.
Oceanic and Atmospheric Studies (OEAS) – Dr. Jessie Turner
Abstract:
Placeholder
Genomic heterogeneity inflates the performance of variant pathogenicity predictions – Dr Jiangwen Sun,
Bashar Fakhreddin and Spencer Peloquin
Abstract:
Recent studies have reported unprecedented accuracy predicting pathogenic variants across the genome, including in noncoding regions, using large AI models trained on vast genomic data. We present a comprehensive evaluation of these frontier models, showing that performance is inflated by differences in the prevalence of pathogenic variants across genomic contexts. We identify the best-performing models for each variant type and establish a benchmark to guide future progress.