Transcriptome prediction performance across machine learning models and diverse ancestries
Position: Data Scientist II. Marcus Institute for Aging Research – Harvard Medical School
ASHG: Can you describe the type of research that has your primary focus?
Paul Okoro: My research centers on developing and utilizing data-driven integrated bioinformatics and statistical frameworks. Specifically, I work on multiple omics data including genomics, transcriptomics, epigenomics, metabolomics, and microbiome, in building omics-based models, analysis pipelines, and tools in direct application to musculoskeletal diseases, aging, and other complex traits.
ASHG: Throughout your life, what have been some of the biggest career goals that you have wanted to accomplish?
Okoro: In the short term, I desire to go on to do a PhD. While leveraging all the professional collaborations and mentorships available to me, I want to grow to the level of leading my own research team as a principal investigator or senior scientist. My long term goal is to continue carrying out data-driven research on complex diseases using integrative bioinformatics approaches and advanced statistical methods to expertly and innovatively harmonize multiple omics data, and advance precision medicine.
ASHG: What are some of the reasons you chose to study genetics instead of anything else?
Okoro: Back in high school, I was generally interested in all the sciences including biology, chemistry, mathematics, and physics. However, my interest in genetics peaked when I learnt about the human genome project. I knew I wanted to be adept in utilizing the knowledge in the much publicized advances in genomics to solving problems of medical importance.
ASHG: What are three words that you would use to describe yourself?
Okoro: Proactive, Inquisitive, Tenacious.