Ray and Stephanie Lane Computational Biology Department
How do genetic mutations affect a person’s risk of acquiring complex disease, such as cancer or Alzheimer’s, or their potential to respond to different treatments? How can we find new drugs and estimate the effectiveness of a new drug before we test them on human beings? How do living systems function across scales from nanometer molecular complexes up through cells, tissues, organs, and whole organisms? And how do we make productive use of the mountains of diverse forms of biological and healthcare data being collected to answer such questions?
Answering major biomedical research questions like these today depends on computational thinking — new mathematical models, algorithms, artificial intelligence, and statistical inference — to make sense of the immense complexity of biological systems in light of vast amounts of heterogeneous data. Our researchers
develop the tools to answer these questions; discover how living systems function in health and disease; and pioneer new areas of research at the intersection of computational and experimental science. They develop the algorithms that look for patterns in genetic data and try to understand the chemical and physical
interactions responsible for all human, animal, and plant life. They build computer models that predict how biological processes act and react under certain conditions. They develop machine learning methods to mine data resources and make predictions about future disease progression.
"There is no corner of biomedical research today that does not depend on computational thinking to pioneer new research directions, enable rigorous and reproducible science, and convert increasingly vast datasources into knowledge. We are working to solve hard computational problems of modern biomedical science while nurturing new generations of computational biologists to serve this growing need."
Russell Schwartz, Head, Ray and Stephanie lane Computational Biology Department, Carnegie Mellon University
Research Themes
Our work builds on the strong history of interdisciplinary research at Carnegie Mellon and cuts across the fields of computer science, mathematics, statistics, as well as sciences of biology, chemistry, physics, and beyond. We aim to develop a deeper global understanding of the building blocks of life, and to develop tools for individualized diagnosis and treatment of diseases. Some of our major research themes include:- Elucidating the Genetic Basis of Disease: Our faculty develop tools linking genetic variation to human illness, with a focus on emerging areas and hard computational problems.
- Algorithms for Biological Big Data: Our faculty develop new advances in algorithmic theory to allow us to work with vast and ever-growing data sets of sequence, mass spectrometry, bioimaging, and other multi-omic data sources.
- Automated Discovery: We are developing artificial intelligence integrated with robotic laboratories to create fully automated AI-driven experimentation to accelerate scientific discovery.
Student Spotlights
Monica Dayao
Pursuing Ph.D. in Computational Biology
Single-cell spatial proteomics imaging data allows scientists to measure the abundance of proteins within individual cells while preserving their spatial context, and recent advances in multiplexed imaging have enabled the profiling of dozens of proteins per cell. While this data promises to revolutionalize our ability to study human tissue and disease, it also raises several computational and modeling challenges. Monica develops methods to analyze and model this data, with the ultimate goal of constructing comprehensive molecular human maps and gain insights to disease outcomes. With her collaborators, she has developed frameworks to improve cell segmentation in these images and predict patient outcomes in cancer. By continuing to develop innovative approaches, Monica hopes to harness the full potential of this new generation of spatial proteomics data and provide novel insights into the complex processes underlying human health and disease.
BaDoi Phan
Ph.D. in Computational Biology/Pursuing M.D.
As an M.D./Ph.D. trainee, I’m driven by my goal to blend science and medicine. I pursued a Ph.D. in computational biology, which equipped me with practical experience integrating machine learning and computer science into genomics. Under Dr. Andreas Pfenning’s guidance, I led research into addiction using multi-species genomics, aiming to uncover unique human addiction genetics insights from mammalian brain genomics. I took charge of designing and acquiring diverse “omic” datasets, while also developing innovative algorithms to integrate them with collaborators’ contributions. My involvement in numerous international research
initiatives honed my ability to communicate effectively with both biological and computational
scientists. Notable achievements during my tenure at CMU include securing a National Research
Service Award fellowship from the National Institute on Drug Abuse and publishing in prestigious
biomedical journals like Science. With expertise in machine learning and big data management, I’m well-prepared to tackle the complex challenges in medicine, where intricate problems necessitate thoughtful and sophisticated computation.