News

Keep up with the latest news from the NCI Center for Biomedical Informatics and Information Technology (CBIIT) and the data science communities.

Learn how researchers used machine learning models to identify the specific genetic mutations that trigger clonal hematopoiesis. In this condition, mutated hematopoietic stem cells multiply more rapidly, increasing the risk of blood cancers.

NCI-funded researchers are testing a new platform that blends statistical and deep learning models, giving you a fuller picture of the variants driving cancer progression.

Deciphering bulk data is challenging. See how a recent DREAM challenge is helping researchers benchmark bioinformatics and data science approaches for unraveling bulk genetic cancer data.

Are you investigating structural variations underlying cancer-causing genes? NCI-funded researchers are testing a new algorithm that could help you track down both coding and non-coding cancer-causing genes.

Looking for new data sources for your machine learning model? NCI researchers combined data from dogs and people to identify risk factors for osteosarcoma.

The hallmark of a good AI model is its ability to work the same in different groups, settings, and situations. See how these NCI researchers used in-house and external images to test their prostate model’s generalizability.

Want to learn more about bioinformatics? Tap into these two newly published articles to see what some prominent researchers are saying about the field and where it’s headed.

Construction of the Advanced Research Projects Agency for Health’s (ARPA-H’s) BDF Toolbox program is well underway. ARPA-H has awarded contracts to nearly 20 teams—representing academia, nonprofits, and commercial organizations—who are tackling a broad range of projects, many of which are directly related to cancer research.

Looking for an easier way to sort and quantify key cellular information from immunofluorescent images? NCI-funded researchers have a new semi-automated tool, called “GammaGateR,” that may help.

An NCI-funded technology blends specific molecular markers along with traditional morphological features in the same cells and in one digital slide. This tool could someday help pathologists and ML models better predict cancer treatment response and outcomes.