From the moment that a tumor is born, it is evolving across several levels: including at the genetic, epigenetic, metabolic, and microenvironmental levels. The central goal of the Jones Lab is to develop innovative computational and technological approaches to uncover the mechanisms of tumor evolution, with the ultimate aim of identifying new therapeutic targets and creating predictive models to monitor tumor initiation and progression. Matthew Jones’s research integrates advances in computation and high-throughput technologies to investigate the molecular mechanisms underlying the spatiotemporal dynamics of copy-number alterations (particularly extrachromosomal DNA) in cancer populations, develop new methods to trace cellular lineages; and elucidate the principles by which tumors are organized over time. 

The Lewis lab integrates neuroscience and engineering to develop advanced methods for multimodal imaging, and applies them to understand the neurobiological origins of sleep. To enable measurement of previously undetectable aspects of brain function, Laura Lewis and her lab develop advanced MRI and multimodal approaches to measure neural, vascular, and CSF physiology. The lab applies these tools to identify neural circuits that regulate sleep, and explore neurophysiology in aging, sleep disorders, and hormonal modulation. Projects integrate computational methods, imaging technology, and neuroscience to identify how the brain creates a spectrum of arousal and attentional states, as this state-dependent flexibility is essential to human cognition.

Understanding how proteins and small molecules interact with one another is a component in improving our understanding of many biological processes and speeding up drug discovery. In particular, molecular docking (i.e. finding the 3D structure of these interactions), holds the keys to predicting interaction strength and how this can be altered. The Barzilay lab has pioneered the use of machine learning methods to generate the structure of the binding poses, paving the way for the replacement of costly and inaccurate traditional search-based methods. The Barzilay Lab is also developing methods for modeling molecular interactions in the context of cellular metabolism and immunology. The group has developed methods for metabolism ranging from from the individual reaction level, which is vital to enzyme screening and drug discovery, to the overall metabolic system, which is key to understanding disease and optimizing biomanufacturing. The Barzilay Lab is also utilizing binding models to help increase our understanding of immune system function.

Polina’s primary research interest is in developing novel techniques for biomedical image analysis and understanding. She particularly enjoys working on algorithms that either explore the geometry of the world and the imaging process in a new way or improve image-based inference through statistical modeling of the image data. She is interested in shape modeling and representation, predictive modeling, and visualization of statistical models.

Our lab is focused is on these areas of special interest:  Predictive analytics, Natural language processing; Clinical informatics, machine learning, genomics/bioinformatics, infectious disease; Medical ultrasound, interventional guidance, planning, and assessment

The MIT Laboratory for Computational Physiology (MIT-LCP), under the direction of Professor Roger Mark, conducts research at the intersection of medicine, engineering, and data science. Our laboratory focuses on developing computational methods and tools for analyzing physiological signals and clinical data, with particular emphasis on critical care medicine and patient monitoring systems.

Our research and product development interests cross the boundaries of computer vision, acoustic and ultrasonic imaging, large‐scale computation and simulation, optimization, metrology, autonomous systems, and robotics. We use computation, and computer science, as methodology for attacking complex instrumentation problems—our work combines mathematical modeling, simulation, optimization, and experimental observations, to develop instruments and measurement solutions.

Led by David Sontag, the Clinical Machine Learning Group is interested in advancing machine learning and artificial intelligence, and using these techniques to advance health care. Broadly, we have two goals: (1) Clinical: To make a difference in health care, we need to create algorithms that are useful for solving real clinical problems. (2) Machine learning: We need rigorous solutions, which can pave the way for safe deployment of machine learning in high-stakes settings like healthcare.

The interdisciplinary research in the Shalek Lab aims to create and implement new approaches to elucidate cellular and molecular features that inform tissue-level function and dysfunction across the spectrum of human health and disease. Professor Shalek’s research encompasses both the development of broadly enabling technologies as well as their application to characterize, model, and rationally control complex multicellular systems. Current studies with partners around the world seek to methodically dissect human disease to understand links between cellular features and clinical observations, including how: immune cells coordinate balanced responses to environmental changes with tissue-resident cells; host cell-pathogen interactions evolve across time and tissues during pathogenic infection; and, tumor cells evade homeostatic immune activity.

The human microbiome is remarkably personalized—even people living together harbor distinct microbial communities. On the skin, individuals in a family often share the same species yet harbor distinct but dynamic strain-level communities. This personalization may explain why most microbiome therapies fail to consistently engraft across patients. The Lieberman Lab seeks to understand how ecology and evolution shape these personalized communities, and the role of this personalization on human health. 

The Mirny lab combines quantitative, typically physics-rooted, approaches with analysis of genomics data to address fundamental problems in biology, most recently they focused on two problems: (1) higher-order chromatin structure; (2) evolution of cancer during neoplastic progression. Studies of the Mirny lab on chromosomes aim to characterize 3D architecture of the genome and processes that lead to its organization and reorganization in the cell cycle and development. Works of the Mirny lab on cancer aim at understanding the role of multiple “passenger” genetic events, such as individual mutations and chromosomal alterations, in cancer progression.

Dr. Mark’s research activities focus on physiological signal processing and database development, cardiovascular modeling, and machine learning for critical care decision support and predictive modeling. His group launched the NIH-supported “PhysioNet” (Research Resource for Complex Physiologic Signals) in 1999 to provide open access to major collections of well-characterized physiologic signals and associated signal processing software.

The Chakraborty Lab is focused on understanding the mechanisms underlying how the immune system functions. This basic knowledge can then be harnessed for the design of better strategies to cure and prevent disease. The lab is also interested in transcriptional condensates. Arup Chakraborty’s work represents a crossroad of the physical, computational and life sciences. A hallmark of his research is the close synergy and collaboration between his lab’s theoretical and computational studies and investigations led by experimental biologists and clinicians.

The Healthy ML group at MIT, led by Dr. Marzyeh Ghassemi, focuses on creating and applying machine learning to understand and improve health in ways that are robust, private and fair. We work on robust machine learning models that can efficiently and accurately model events from healthcare data, and investigate best practices for multi-source integration, and learning domain appropriate representations.

Thomas’s research interests focus on signal processing, mathematical modeling, and model identification to support real-time clinical decision making, monitoring of disease progression, and titration of therapy, primarily in neurocritical and neonatal critical care. In particular, Thomas is interested in developing a mechanistic understanding of physiologic systems, and in formulating appropriately chosen computational physiologic models for improved patient care. His research is conducted in close collaboration with colleagues at MIT and clinicians from Boston-area hospitals.

Focusing on the interface of fluid dynamics and epidemiology, The Fluid Dynamics of Disease Transmission Laboratory, within the Fluids and Health Network, led by Prof. Bourouiba, aims to elucidate the fundamental physical mechanisms shaping the transmission dynamics of pathogens in human, animal, and plant populations where drops, bubbles, multiphase and complex flows are at the core, in addition to broader questions at the intersection of health, broadly defined, and fluid physics.

Using combinations of likelihood, Bayesian, state-space, time-series and point process approaches, a primary focus of the research in my laboratory is the development of statistical methods and signal-processing algorithms for neuroscience data analysis.  We use a systems neuroscience approach to study how the state of general anesthesia is induced and maintained. To do so, we are using fMRI, EEG, neurophysiological recordings, micro dialysis methods and mathematical modeling in interdisciplinary collaborations with investigators in HST, the Department of Brain and Cognitive Sciences at MIT, Massachusetts General Hospital, and Boston University. 

Professor Szolovits’research interests broadly include much of biomedical informatics. He has defined his research interests by the demands of health care and how they could be satisfied by computing approaches. These include creation of decision support tools, machine learning to develop predictive models for alternative interventions, clinical natural language processing to extract information from notes and reports, use of multi-modal data, and means of combining medical knowledge with models learned from data.

Research in the Computational Cardiovascular Research Group is focused on three areas: 1) Understanding conformational changes in biomolecules that play an important role in common human diseases, 2) Using machine learning to develop models that identify patients at high risk of adverse clinical events, and 3) Developing new methods to discover optimal treatment strategies for high risk patients.  The group uses an interdisciplinary approach combining computational modeling and machine learning to accomplish these tasks.