BMIR Services + Tools

BMIR’s software platforms, tools, services, and research methodologies accelerate the translation of discoveries to patient health and healthcare improvements at Stanford Medicine, in the U.S., and around the world.

—Prof. Purvesh Khatri, Stanford Center for Biomedical Informatics Research


The Center for Expanded Data Annotation and Retrieval (CEDAR) developed by the Musen Lab provides a computational ecosystem designed to helps researchers archive their experimental data in a manner that allows them and other investigators to retrieve the data, to verify the data, and to make new discoveries. CEDAR helps to make data Findable, Accessible, Interoperable, and Reusable (FAIR).  CEDAR makes it simple for investigators to take advantage of community standards when authoring metadata for their datasets—enabling better data description and enabling better science.

Eterna Diagnostics

Eterna, an online puzzle, enlists video gamers to try to design a sensor module that could make diagnosing tuberculosis as easy as taking a home pregnancy test. BMIR Associate Professor of Medicine Purvesh Khatri, PhD and Eterna’s co-creator, Rhiju Das, PhD, Associate Professor of Biochemistry, hope that Eterna will allow citizen-scientists to participate in designing a molecule that could help save the lives of the millions of people who are infected with tuberculosis. 


Developed by the Gevaert Lab, LungNet is a  machine-learning neural network designed to obtain accurate classifying information to better diagnose and stage patients’ lung cancer status from lung CT scans. 


The PRECOGsystem, developed by the Gentles Lab, queries associations between genomic profiles and cancer outcomes. It enables researchers to understand whether, for example, high expression of a gene is suggestive of shorter or longer patient survival.


CoINcIDE is a novel methodological framework developed by the Gevaert Lab to discover patient subtypes through analysis of large databases of clinical information. The value of CoINcIDE has been demonstrated using a collection of breast and ovarian cancer gene-expression data.

Green Button

Green Button is a clinical consultation service offering the promise of personalizing medical practice, in real time. Since 2017, Nigam Shah, MBBS, PhD, and his team at BMIR have been offering a Clinical Informatics Consultation Service at Stanford that helps physicians learn what has happened to patients seen previously by clinicians at Stanford Health Care who are similar to patients of their own. The service links the doctors to the information they need to make evidence-based decisions for patients whose problems at first glance do not have clear solutions.


The National Center for Biomedical Ontology (NCBO) manages a repository of all the world’s publicly available biomedical ontologies and terminologies. For more than 15 years, BMIR has provided leadership and support for NCBO’s BioPortal system, the world’s most comprehensive repository of biomedical ontologies.   BioPortal is used by thousands of investigators every day to help suggest standardized ways to describe biomedical phenomena, to assist with natural language processing, and to help investigators to describe their datasets in the best way possible.


Protégé is a free, open-source ontology editor and general-purpose framework for building intelligent systems. It is supported by a strong community of hundreds of thousands of academic, government, and corporate users, who turn to Protégé to build knowledge-based solutions in areas as diverse as biomedicine, e-commerce, and organizational modeling.  The World Health Organization—for which BMIR has been designated an official Collaborating Center, uses Protégé extensively to manage terminologies such as the International Classification of Diseases (ICD).