Madhavi Ganapathiraju's ACT (Algorithms for Computational and Translational) Biomedicine Lab focuses on applying machine learning and signal processing algorithms for Computational Systems Biology. Specifically, the team is interested in discovering protein-protein interactions. They also work on predicting protein function and cellular localization. Core areas of specialization of students working in this group are machine learning and/or signal processing, and they come from the Department of Biomedical Informatics Training Program, the Intelligent Systems Program, the Joint CMU-Pitt PhD Program in Computational Biology, or internships through the TECBio Research Experiences for Undergraduates Program (www.tecbioreu.pitt.edu) or First Experiences in Research Program, at University of Pittsburgh.
Centers and Labs
ACT Biomedicine Lab
Center for Causal Discovery
As an inaugural member of the NIH Big Data to Knowledge (BD2K) Consortium, the Center for Causal Discovery (CCD) will: Develop highly efficient causal discovery algorithms that can be practically applied to very large biomedical datasets Conduct projects addressing 3 distinct biomedical questions (cancer driver mutations, lung fibrosis, brain causome) as a vehicle for algorithm development and optimization Disseminate causal discovery algorithms, software, and tools Train data scientists and biomedical investigators in the use of CCD tools Train data scientists and biomedical investigators to collaborate in the discovery of causality Led by Drs. Gregory Cooper, Ivet Bahar, Jeremy Berg, and Clark Glymour (see figure below), the Center represents a partnership among data scientists from the University of Pittsburgh (Pitt), Carnegie Mellon University (CMU), and the Pittsburgh Supercomputing Center (PSC) who will develop the algorithms, software...
Early, reliable detection of outbreaks of disease, whether natural (e.g., West Nile virus) or bioterrorist-induced (e.g., anthrax and smallpox), is a critical problem today. It is important to detect outbreaks early in order to provide the best possible medical response and treatment, as well as to improve the chances of identifying the source. A primary goal of this project has been to develop new Bayesian models and inference algorithms that then are applied to monitor electronically available healthcare data to achieve early, reliable detection of outbreaks. The scientific challenge of monitoring for outbreaks within an entire population creates major computational challenges in building and applying Bayesian models that are orders of magnitude larger than those developed previously. The project applied and extended state-of-the-art probabilistic inference methods to achieve efficient inference. If inference indicates that an outbreak is likely, an alert is raised automatically...
The PRoBE Lab Mission and Goals: To harness prior knowledge for effective knowledge discovery from biomedical data. To design and develop novel machine learning algorithms using symbolic, probabilistic and hybrid approaches to solve bioinformatics problems of clinical importance such as biomarker discovery and disease classification. To develop complex pattern recognition tools that can be plugged into computer-aided diagnostic systems to facilitate evidence combination from heterogeneous sources such as data from imaging, de-identified clinical information and biochemical profiling.
RODS—Real-time Outbreak and Disease Surveillance LaboratoryThe RODS Laboratory is a biosurveillance research laboratory at the University of Pittsburgh, Department of Biomedical Informatics. We are the home of the National Retail Data Monitor (NRDM), Pennsylvania RODS and the Real-time and Outbreak Surveillance Software.RODS Web Site
The Vis Lab
The Vis Lab is focused on the application of artificial intelligence and machine learning to problems in the Learning Health System (LHS) that include: 1) development of a learning Electronic Medical Record (LEMR) system, 2) precision medicine and personalized modeling, 3) reuse of Electronic Medical Record (EMR) data for clinical, translational, and informatics research, 4) data mining and causal discovery from biomedical data, and 5) automated visual analytics. The Vis Lab Website
The purpose of the TRanslational Informatics Applied to Drug Safety(TRIADS) lab is to conduct research at the intersection of informatics, pharmacoepidemiology, personalized medicine, and comparative effectiveness to improve medication safety for older adults. Current projects include: * Comparing the effectiveness personalized medication therapy with standard of care in older adults with numerous chronic conditions * The dynamic enhancement of drug product labels through Semantic Web technologies * Active monitoring of adverse event risk in patients exposed to pharmacokinetic drug-drug interactions * Semantic modeling of pharmacogenomics statements to support decisions made by pharmacists, clinicians, and patient Please e-mail Dr. Richard Boyce for more information or if you would like to attend TRIADS lab meetings.
The Tsui lab is affiliated with the Department of Biomedical Informatics at the University of Pittsburgh. Under the direction of Profssor Tsui, the lab works closely with hospitals and frontline clinicians to collect and analyze big clinical data that leads to new hypotheses, patient outcome prediction and management, and risk reduction and intervention. We focus on four key research areas: Clinical data science, Natural language processing, Mobile health, and Real-time production systems.