Future Data Scientists and Biomedical Informatics Researchers Will Be Trained in Master’s Program at Yale

Yale School of Medicine (YSM) has begun a new concentration within the computational biology and bioinformatics program, giving students the opportunity to earn a master’s degree and the necessary training to become biomedical data scientists/biomedical informaticians.

It also aims to train students to meet the growing demand of professionals who can organize and analyze biomedical and healthcare data using the latest developments in AI and related areas, said Lucila Ohno-Machado, MD, PhD, deputy dean and chair for biomedical informatics.

Cynthia Brandt, MD, MPH, vice-chair for education and professor in the new section of biomedical informatics & data science, says this is the first time the graduate program offers the degree with a focus on biomedical informatics. It is now accepting applications until December 1. The first group of students will start in September 2024.

More than a specialized degree, this program offers students the opportunity to understand and translate computational data to the bench and bedside, says Brandt.

“Without the workforce and the individuals who understand how data is created, how it's captured, how it's stored, and how different computational methods are necessary to analyze it, it causes a limitation that slows down what you can learn from the data that scientists are creating,” explains Brandt. “Then it makes it more difficult to translate that data, which could be used for clinical trials and for medical advances.”

The terminal master’s degree in computational biology and bioinformatics (CBB) with a biomedical informatics concentration consists of 9 courses, three of which are core studies, says Brandt.

Foundational classes for this master’s degree are Introduction to Health Informatics, Core Topics in Biomedical Informatics and Data Science or Modeling Biological Systems II, and Biomedical Data Science: Mining and Modeling.

The remaining courses are electives and can vary, depending on each student’s interests and research focus. With the help of an advisor, students will choose elective courses in biomedical informatics. Examples of courses in this area include Natural Language Processing, Clinical Decision Support and Clinical Database Management Systems & Ontologies.

Students entering the program who do not have a background in biology will be required to take a course in biology or genetics.

Brandt added that additional courses students take could also be offered in the Department of Statistics and Data Science (S&DS), Computer Science (CPSC), or Engineering. Once a Department of Biomedical Informatics and Data Science (BIDS) is established at YSM, as is planned, newly developed courses will also have that designation.

To complete the graduate program successfully, students will need to pass at least two courses with honor grades and complete coursework with an average of a “High Pass.” Additionally, Grant detailed, “students will complete a master’s degree project, where they will come up with an idea, write a research paper, and defend it. They will also present their project in a seminar where they will answer questions about it as well as breadth knowledge of their coursework and track of study at the end of the two-year program.”

Students interested in pursuing a doctoral degree in computational biology and bioinformatics or biomedical informatics can do so at Yale, said Brandt. According to Brandt, most of the students who apply to a bioinformatics program already have a background in biology and math, computer science, statistics, or data science. However, such programs also accept students who have a predominant clinical or biology background if they have a facility for math, statistics, or computer science.

“My goal would be to have 10 to 20 students in the first year [of the master’s program] where 10% or 20% of them would decide that they want to go on and get a PhD,” says Brandt.

Brandt says that it is crucial to train individuals who are able to ask research questions, know how to analyze research data and other kinds of data, and understand computation and other computational methods.

The CBB PhD has existed in Yale’s Biological and Biomedical Sciences (BBS) since 2003. However, the biomedical informatics concentration was recently incorporated as a new independent section at YSM with several new faculty members, according to Brandt.

The master’s degree in computational biology and bioinformatics was originally created by Perry Miller, MD, PhD and Mark Gerstein, PhD, in 2004 with the program intended to be a step for those interested in pursuing a doctoral degree in computational biology and bioinformatics.

The creation of a new academic unit in biomedical informatics and data science in 2023 expanded the teaching faculty significantly, said Ohno-Machado.

In addition to Brandt, senior faculty in biomedical informatics and data science include Ohno-Machado; Hua Xu, PhD, professor and vice chair for research; Daniella Meeker, PhD; associate professor in biomedical informatics & data science and chief research information officer.

Newly recruited junior faculty in biomedical informatics and data science include Qingyu Chen, PhD; Hoon Cho, PhD, Mary-Anne Hartley, MD, PhD, MPH, Xenophon Papademetris, PhD; Kei-Hoi Cheung, PhD; Huan He, PhD, Na Hong, PhD, Mark Iscoe, MD, MHS; Andrew Taylor, MD, MHS; Fongci Lin, PhD, Anthony Lisi, DC; and Kalpana Raja, PhD, who join the existing team of biomedical informatics research scientists.

The growing team of 31 faculty who have secondary appointments at biomedical informatics and data science currently includes representatives from the Yale Child Study Center and YSM departments of Dermatology, Emergency Medicine, Laboratory Medicine, Molecular Biophysics, Biochemistry, Neurology, Ophthalmology, Pathology, Pediatrics, Psychiatry, Surgery, and Therapeutic Radiology, in addition to faculty at YSPH, SEAS, FAS, and YSN.