3 Questions: Building predictive models to characterize tumor progression

Source: MIT News - AI

Introduction

Just as Darwin’s finches evolved in response to natural selection, the cells that make up a cancerous tumor similarly counter selective pressures in order to survive, evolve, and spread. Tumors are complex sets of cells with their own unique structure and ability to change.

Today, artificial intelligence and machine learning tools offer an unparalleled opportunity to illuminate the generalizable rules governing tumor progression on the genetic, epigenetic, metabolic, and microenvironmental levels.

Matthew G. Jones, an assistant professor in the MIT Department of Biology, the Koch Institute for Integrative Cancer Research, and the Institute for Medical Engineering and Science, hopes to use computational approaches to build predictive models—playing a game of chess with cancer, making sense of a tumor’s ability to evolve and resist treatment with the ultimate goal of improving patient outcomes. In this interview, he describes his current work.

What aspect of tumor progression are you working to explore and characterize?

A very common story with cancer is that patients will respond to a therapy at first, and then eventually that treatment stops working. This largely happens because tumors have an incredible, and very challenging, ability to evolve: they can change their genetic makeup, protein‑signaling composition, and cellular dynamics. The tumor as a system also evolves at a structural level. Often, a patient succumbs because the tumor has evolved to a state we can no longer control, or it evolves in an unpredictable manner.

Cancers can be thought of as both incredibly dysregulated and disorganized, and as having their own internal logic that is constantly changing. The central thesis of my lab is that tumors follow stereotypical patterns in space and time, and we’re hoping to use computation and experimental technology to decode the molecular processes underlying these transformations.

We’re focused on one specific way tumors evolve: a form of DNA amplification called extrachromosomal DNA (ecDNA). Excised from the chromosome, these ecDNAs are circularized and exist as a separate pool of DNA particles in the nucleus.

Initially discovered in the 1960s, ecDNA were thought to be a rare event in cancer. However, as researchers began applying next‑generation sequencing to large patient cohorts in the 2010s, it became clear that ecDNA amplifications not only confer the ability of tumors to adapt to stresses and therapies faster, but are also far more prevalent than initially thought.

We now know these ecDNA amplifications appear in about 25 % of cancers, especially the most aggressive types: brain, lung, and ovarian cancers. For a variety of reasons, ecDNA amplifications can change the “rule book” by which tumors evolve, allowing them to accelerate to a more aggressive disease in surprising ways.

How are you using machine learning and artificial intelligence to study ecDNA amplifications and tumor evolution?

There’s a mandate to translate what I’m doing in the lab to improve patients’ lives. I start with patient data to discover how various evolutionary pressures are driving disease and the mutations we observe.

One of the tools we use to study tumor evolution is single‑cell lineage tracing. Broadly, these technologies allow us to track the lineages of individual cells. When we sample a particular cell, we not only see its phenotype, but we can (ideally) pinpoint exactly when aggressive mutations appeared in the tumor’s history. That evolutionary history gives us a way of studying dynamic processes that we otherwise couldn’t observe in real time, and helps us make sense of how we might intercept that evolution.

I hope we’ll get better at stratifying patients who will respond to certain drugs, anticipating and overcoming drug resistance, and identifying new therapeutic targets.

What excited you about joining the MIT community?

One of the things that attracted me was the integration of excellence in both engineering and biological sciences. At the Koch Institute, every floor is structured to promote this interface between engineers and basic scientists, and beyond campus we can connect with the broader biomedical research enterprises in the Boston area.

Another draw was MIT’s strong emphasis on education, training, and investing in student success. I’m a firm believer that what distinguishes academic research from industry research is that academic research is fundamentally a service job: we are training the next generation of scientists.

It has always been my mission to bring excellence to both computational and experimental technology disciplines. The trainees I hope to recruit are eager to collaborate and solve big problems that require both approaches. The KI is uniquely set up for this type of hybrid lab: my dry lab is right next to my wet lab, fostering collaboration and reflecting the institute’s general vision.