Boyang Fu (付伯阳）

Boyang Fu (付伯阳）

Postdoctoral Fellow, Department of Biomedical Informatics, Harvard Medical School

About Me

Customer Reviews

“We rise by lifting others.” - Robert Ingersoll

Few things bring me more joy than watching the friends I’ve mentored/ worked with grow and succeed. I’ve been fortunate enough to receive some of their kind words along the way.

Customer 1 – Research mentorship since 2021 Boyang has been my research mentor since September 2021. He led me into Professor Sankararaman's research group and offered extensive help in research projects, graduate application, and other aspects. I never feel overwhelmed when working with Boyang: he allows me to explore research topics freely and gives me concrete tasks to work on when I need more direction. Additionally, Boyang is altruistic and helpful. He acknowledged my effort in a research paper even though he did most of the work. He also explained concepts and algorithms patiently to me during his time off. Besides his easygoing and helpful personality, his solid academic background in statistics, machine learning, and genetics make him competent to lead all related research projects. His research and teaching experiences both proved his expertise in the field of machine learning for bioinformatics.
Customer 2 – Bruins in Genomics 2022 Summer Program Boyang was my direct mentor for the Bruins in Genomics 2022 Summer Program at UCLA. Despite me having little experience in machine learning research, he was extremely helpful and patient in getting me up to speed with the exciting and complex work going on in the lab. His conceptual explanations were very well thought out and clear, allowing me to better understand the overarching goals of the project. He also spent a lot of time with my partner and I each day, making sure we not only succeeded, but enjoyed ourselves along the way. I couldn't have asked for a better mentor for my first large research project!
Customer 3 – BIG Summer 2022 Research Mentor Boyang was my BIG Summer 2022 research mentor at UCLA. Beyond having an extremely deep understanding of his research field and the problems I faced in my project, he was also constantly motivating me and made me genuinely excited about the future of the research. My project was very novel and open-ended, making some aspects of it difficult to answer immediately. However, even in these cases, he always came up with a plan and thought many steps ahead to determine the best course of action. Boyang was very friendly and made me feel a part of the team from the first day. I am so glad to have worked with him this summer and am excited to continue the research we did together.

source: LinkedIn Recommendations

Q&A About My Research

I summarized some of the frequently asking questions from my friends who are not familiar with our field

Am I a biologist or a computer scientist? I consider myself a computer scientist. My daily research routine involves processing data; engaging in method development, designing integrated pipelines for large-scale data analysis; and arguing theoretically and empirically about our results, as other people in this area do. Unlike biologists, I do not touch pipettes, western blot, or experiment model organisms. Maybe one aspect that distinguishes us is the type of data we deal with. We do need to have a decent knowledge of populational genetics, molecular biology, etc., and vital skills for data preprocessing since data in our fields is arguably much more noisy, limited, and less intuitive than other types of data (Image, Natural language)
As a computer science major, why do you study biology? Many computer science researchers develop methods for specific applications. Just like researchers who focus on computer vision, NLP, and cyber-physical systems, we focus on answering biological questions. We need additional effort to understand the data and the relevant biological knowledge to analyze the data.
Why choose computational biology as my research field? I found this is one of the most charming areas. The genetic signal we discovered can help better understand human beings and bring new opportunities for clinical care. We have seen many great works that help us better understand the origin of human beings, the risk of having certain diseases, precision medicine, etc. Yet our knowledge of our own body is still limited, with vast opportunities in this field.
What methods do I use to solve the questions Genetic datasets are usually high dimensional with a limited sample size. Handling this kind of data requires more careful assumptions about the model and solid domain knowledge. Therefore, statistics, linear algebra, and data mining skills are essential for solving the problem.
Do I use deep learning? Yes, but in a prudent manner. The straightforward implementation of deep learning algorithms usually doesn't work well in genetic datasets. Performance aspect, this could be due to the unique structure of the genetic dataset, the limited amount of training dataset, Computation aspect, this could be due to infeasibility to apply to the extremely high dimensional dataset. Finally, current deep learning models are generally hard to interpret, where interpretability is perhaps the most crucial factor in genetics.