Mihai Dimian

This paper introduces a hybrid training model to enhance bioinformatics capacity globally, demonstrating its effectiveness through an Eastern European workshop series.

This study shows that better software development practices for RNA-seq tools lead to more citations, as evidenced by a strong statistical association between development quality and citation counts.

This study benchmarks large language models in bioinformatics tasks, finding GPT-4 leads in most areas while Gemini excels in math and LLaMA struggles with code generation.

This study assesses metadata completeness in public omics studies, finding that most important phenotypes are often omitted, with only 11.5% of studies fully sharing all phenotypes.