Bridging the Gap: Why AI and Biology Must Learn from Each Other
My research focus sits in the intersection of biology and artificial intelligence. If you’ve heard the buzz, you know AI is changing medicine. But for me, it’s not just a tool; it’s the only way we’ll truly solve the biggest, messiest problems in human health. The key to that solution lies in how we approach both research and teaching.
Turning Data Overload into Patient-Specific Answers
Right now, we can access large amounts of biological data such as genomic sequences, systems-level proteomics measurements, patient health records, etc. The sheer volume is impossible for a human team to synthesize. That’s where AI steps in.
My research focuses on Computational Systems Medicine. We aren’t just running data through a standard algorithm; we’re building custom, intelligent systems designed to unify this multi-scale information. Think of it as connecting a million tiny dots to form one clear picture.
The crucial word in my lab is interpretable. We develop AI/ML and network biology models, but if we can’t explain why the AI made a certain recommendation, a doctor can’t ethically or safely use it. Our job is to give doctors actionable insights, not black boxes.
This focus is driven by a deep need: solving complex, devastating diseases. We are using these models to achieve Precision Diagnostics and Personalized Therapy for Cancer and Alzheimer’s Disease. We’re working to move beyond generic treatments to therapies tailored exactly to a patient’s molecular profile.
The Educational Mission: Creating Bilingual Scientists
New tools are useless without skilled hands to wield them. This brings me to my passion for teaching.
I will lead the new course SYBB 464: Artificial Intelligence for Biomedical Research in the Spring. This class isn’t about memorizing definitions. It’s a hands-on experience dedicated to training the next generation to be “bilingual”—fluent in both the language of biology and the language of machine learning.
We will equip students with the skills to apply AI/ML tools directly to the high-dimensional biological datasets they’ll encounter in the real world. The person who asks the most critical biological question should also know how to build the most effective computational tool to answer it.
Collaborating on the Future of Medicine
The future of healthcare depends on scientists who can look at a tumor sample, an algorithm, and a patient’s chart and see a single, unified problem. It requires collaboration across disciplines—between those who understand the code and those who understand the cell.
If you’re working on similar challenges, or if you believe in bridging the teaching gap between these two fields, you are with me. The most exciting breakthroughs are always just one integrated insight away.
Come listen to me at Breaking Boundaries: AI & Biology event at ThinkBox