The Pheno-Type: Simon Eng
Simon Eng, a Senior Data Scientist at BioSymetrics, has built a career at the intersection of immunology and computer science. With a Ph.D. in Immunology from the University of Toronto, his research has spanned machine learning, bioinformatics, and computational biology, shaping his journey in drug discovery. In this interview, he reflects on his journey – from early academic influences to the challenges of bridging multiple scientific domains – offering insights into the value of interdisciplinary knowledge and effective communication in data-driven research.
“if you really want to differentiate yourself [as a data scientist], your X-factor is going to be your domain knowledge in a field that isn’t Computer Science or Machine Learning.”
Tell us more about your journey leading up to BioSymetrics.
My journey started long ago in high school. I was deciding what courses to take for my International Baccalaureate diploma, and I saw a couple of new offerings at my school: Information Technology in a Global Society and higher-level Biology. After high school, I couldn’t decide between Computer Science and Biology for my undergraduate studies, so I ended up doing both Computer Science and Immunology and haven’t looked back since.
I then moved to Toronto for my Ph.D. in Immunology. Little did I know, however, that machine learning was quickly growing as a field and Toronto happened to be one of the places for it. My graduate work ended up having a heavy machine learning focus, and I’m grateful to have had the opportunity to lead the way for a new generation of Computational Immunology trainees.
During the pandemic, Kevin Ha, one of my colleagues during grad school, reached out about doing an informational interview with Gabe Musso, our Chief Scientific Officer. Easy to see where that went!
You trained in quite a few diverse domain areas! What were some of the challenges in training in both Computer Science and Immunology at the same time? What advice would you give to younger trainees who would want to follow a similar path?
When I moved to Toronto for my Ph.D., I made a deliberate decision to join the Immunology department at the University of Toronto. I wanted every result that I produced computationally to have some biologically or clinically plausible explanation. It’s one thing to plug in models and churn out numbers, but if you really want to differentiate yourself, your X-factor is going to be your domain knowledge in a field that isn’t Computer Science or Machine Learning. You also need to be comfortable with the fact that unlike your peers specializing in only one of those areas, the knowledge you gain throughout your studies is going to be relatively more broad than deep. You still get to occupy your own niche, though. Jack of many trades, but definitely not master of none!
And that leads to the importance of developing communication skills. These skills are important regardless of subject area, but they’re especially critical to develop when you occupy the intersection between multiple areas like I did. In my case, I had to deal with clinicians, immunologists, and computer scientists, and I had to figure out how to communicate concepts from one area in a way that those in another area could understand. I eventually settled on a plainer, more direct, and conversational style of communication focused on avoiding unnecessary jargon – don’t let criticisms of appearing “unacademic” scare you off! You’ll need to experiment to figure out what works and what doesn’t, but the earlier you figure out how to communicate between fields, the better off you’ll be – not just in your graduate studies but in numerous other parts of life as well.
Now you have transitioned into drug discovery. Tell us what the transition was like and how you leveraged your skills, particularly your understanding of Immunology and Machine Learning, to drive early-stage drug development for BioSymetrics?
The transition into drug discovery has definitely taken me outside my comfort zone in working with immunological diseases. I had to make a couple of adjustments. I had to figure out how to think about data we obtain from zebrafish as I previously worked with data primarily from humans. And then there was the world of cheminformatics to explore as someone who was more focused on bioinformatics before graduate school.
My background in Immunology has helped in one significant way – by helping me see connections between various systems, pathways, and mechanisms, even in non-immunological contexts. I often like to joke that the immune system is involved in everything, which simply underlies the value of domain knowledge when we generate results. Generating results and insights is thrilling, but it’s even more thrilling to contextualize them using the knowledge we have or gain.
Other interesting things happen when you combine Machine Learning with other science fields, including Immunology. You gain new insights into what techniques you’re running and how you’re running them. I’ve certainly run into situations where, instead of running some technique for the sake of doing so, I had take a step back and ask, why? Does what I expect this technique to produce as a data scientist align with what I expect it to produce as a biologist?
Now for something light-hearted! What's something interesting or unique about you that not many people might know about?
Many years ago, I played the clarinet, bass clarinet, and tenor sax in high school, and in university, I took a couple of music theory courses. I decided a couple of years ago to springboard from there and learn the bass guitar. It’s been a fun journey – even if I still haven’t figured out where to reasonably store an electric bass guitar, an acoustic bass guitar, and a pedalboard at home!
March 14, 2025