Biology is fast becoming an information science, with large databases and sophisticated algorithms now essential tools in the field. Allen School faculty and students collaborate with researchers in biology and medicine on a wide range of computational problems that will ultimately enable us to understand complex biological systems. The Allen School and the University of Washington are at the forefront of exciting innovations at the intersection of computation and biology to advance scientific discovery, develop new diagnostics and therapeutics, and usher in a new era of personalized medicine. Learn more about our work by visiting the pages of our individual researchers and labs and explore some of our highlighted projects below.
Also check out or work on molecular information systems, a partnership with Microsoft aimed at developing digital data storage and computing capabilities using synthetic DNA.
Center for Neurotechnology
The Center for Neurotechnology focuses on the development of innovative neural devices and methods for engineering neuroplasticity in the brain and spinal cord. The goal is to revolutionize the treatment of people living with spinal cord injury, stroke and other debilitating neurological conditions by engineering devices that restore lost or injured connections in parts of the nervous system to improve, assist, and restore sensory and motor function. The center also focuses on the discovery of fundamental neuroscience an engineering principles with broader implications for the treatment of neurological diseases such as Parkinson's and essential tremor.
Laboratory of Artificial Intelligence for Medicine and Science
Members of the AIMS Lab develop explainable artificial intelligence for applications in health care and the life sciences. Working in partnership with biomedical researchers and clinicians in the UW School of Medicine and external institutions, the team aims to improve our understanding of the biology underlying diseases such as cancer and Alzheimer's; enable physicians to target disease treatments based on a patient's individual molecular profile; and to provide useful, interpretable predictions for a range of conditions and risk factors to improve patient outcomes.
Neural Systems Laboratory
The Neural Systems Laboratory aims to advance our understanding of the brain using computational models and simulations, and apply this knowledge to the task of building intelligent robotic systems and brain-computer interfaces (BCIs). The lab's work combines data and techniques from a variety of fields, ranging from neuroscience and psychology, to machine learning and statistics. Members are focused on understanding probabilistic information processing and learning in the brain; building biologically-inspired robots that can learn through experience and imitation; and developing interfaces for controlling computers and robots using brain- and muscle-related signals.
Seelig Lab for Synthetic Biology
Members of the Seelig Lab aim to advance our understanding of how biological organisms process information using complex biochemical networks and how to engineer those networks to program cellular behavior. Their work integrates the design of molecular circuity in the test tube and in the cell with the investigation of existing biology pathways. The aim is to engineer biological control circuits with DNA and RNA components that can be applied to new problems in disease diagnostics and treatment.
News & Highlights
- TreeExplainer, a set of tools for computing optimal local explanations for tree-based machine learning models used to predict mortality and disease risk, is featured on the cover of Nature Machine Intelligence. A team of researchers in the AIMS Lab led by recent Ph.D. alumnus Scott Lundberg and professor Su-In Lee worked with collaborators in UW Medicine on the project.
- A team led by professor Rajesh Rao published the results of a study that employs computational methods to explain human choices in group decision-making in Science Advances.
- The EMBARKER project led by professor Su-In Lee and Ph.D. student Safiye Celik that focuses on the identification of genetic markers of Alzheimer's disease wins the 2019 Madrona Prize.
- The Prescience interpretable machine-learning system for predicting hypoxemia during surgery, led by professor Su-In Lee and Ph.D. student Scott Lundberg, appears on the cover of Nature Biomedical Engineering.
- MERGE algorithm developed by a team of researchers and clinicians led by Professor Su-In Lee and Ph.D. student Safiye Celik that combines machine learning and big data to target treatment for acute myeloid leukemia is published in Nature Communications.
- "DNA domino" architecture created by members of the Seelig Lab and Microsoft Research to enable fast and modular DNA-based computing is featured in Nature Nanotechnology.
- SPLIT-seq, a new method for performing large-scale analysis of gene activity at the cellular level developed by members of the Seelig Lab and Allen Institute, was published in Science.
- Professor Larry Ruzzo co-edited and appeared in the book RNA Sequence, Structure, Function: Computational and Bioinformatic Methods, presenting new methodologies in RNA bioinformatics.