Latest Blog Posts

When we think about artificial intelligence, we often imagine smart machines that can talk to humans. But what happens when AI systems need to talk to each other? In my recent research, “To What Extent Do Multi-Agent Systems Use Compositionality in Multi-Agent Interactions?”, I explored how AI agents develop and use communication to cooperate on shared goals. I trained AI agents using a speaker-listener setup where one agent had to describe a goal, and the other had to act on

Proteins are often called the workhorses of life because they do so many critical jobs in our cells. But to really understand how a...

If you’ve been hearing about how artificial intelligence is changing drug discovery, genomics, and more, you might wonder: How do scientists actually build and use these AI models?  Thankfully, there’s an ever-growing set of tools and platforms that make AI accessible to biology labs of all sizes. First, there are general-purpose frameworks  like TensorFlow (from Google) and PyTorch (from Meta). These give researchers the core building blocks to develop custom AI models—every

The fusion of AI and computational biology has been on fire for the last couple of years. From groundbreaking research papers to real-world drugs entering clinical trials, the field has never looked more promising. Here are some highlights: One big moment was in 2022, when AlphaFold  released predicted structures for nearly every protein sequence known—over 200 million! Scientists could just look up a predicted model on a public website for free. This database is speeding up

Have you ever wondered how new medicines are developed? It’s a process that typically takes years, or even decades, and can cost billions of dollars. Scientists have to sift through thousands of possible drug candidates, run tests in labs, and finally move to human trials. But today, artificial intelligence (AI) is making that search faster and more precise than ever before. The starting point in drug discovery is often target identification.  This means finding which protein

When people get sick, doctors usually rely on their expertise and medical tests to decide how to treat them. But what if we could use computers to analyze giant datasets—patient histories, lab tests, genetic profiles—to predict how the disease will progress and what treatments will work best? That’s exactly what AI-driven disease modeling is all about. One big area is disease progression prediction.  Take Alzheimer’s disease, for example. Researchers can train AI algorithms o

Genomics and transcriptomics are all about understanding our genetic blueprint and how genes get expressed as RNA. With modern technology, scientists can sequence entire genomes and measure RNA levels in thousands of cells at once. But that produces massive amounts of data. This is where AI steps in. Imagine trying to spot a small typo in a billion-letter text. That’s kind of like searching for a disease-causing mutation in human DNA. Traditional tools have done a decent job,

Introduction In an era of increasing polarization, understanding how artificial intelligence can facilitate meaningful dialogue on...

At the Mircore camp for computational biology, we were tasked to research a specific multifactorial disease and then find certain gene...