News

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

Cancer drug target visualized at the atomic level, the protein p97 is trapped in an inactive state by a new inhibitor (red) and the molecule cannot proceed into its normal reaction cycle. Image created using cryo-electron microscopy.

New NCI-DOE Collaboration Project, IMPROVE, Seeks Deep Learning Model Approaches

IMPROVE focuses on improving deep learning models to predict the efficacy of cancer treatments. The research community, including data scientists and informaticists, is asked to respond to an RFI for creating protocols to evaluate model performance by April 15, 2022, at 5:00 p.m. ET. Additionally, they are encouraged to respond to an RFP for improving model comparison by May 9, 2022.

Abstract technical image of a brain with connected lines and blue, green, and red circles representing neurons and activity traversing the brain.

NCI Cancer Blog Defines Artificial Intelligence and Elaborates on its Potential for Cancer Imaging Research

Over the past several years, scientists have made exciting advances in the realm of artificial intelligence (AI) and its integration into the cancer imaging field. New AI tools could make cancer imaging faster, more accurate, and more informative. But are they ready for real-world implementation?

Humaniod depiction of artificial intelligence/machine learning

Apply for Supplemental Funds to Support Collaborations Concerning the Ethical Development and Use of AI/ML in Biomedical and Behavioral Sciences

Do you work on a project funded by an active NIH grant? Is this project rooted in artificial intelligence, machine learning, and/or ethics components? Apply to this Notice of Special Interest by March 31, 2022.

A magnifying glass searches through data code. In the center is the word fraud. The word fraud is highlighted in red to show importance.

Keeping Big Data Fraud at Bay With Machine Learning

NCI’s Office of Cancer Clinical Proteomics Research’s new blog highlights recent findings from scientists in the Clinical Proteomic Tumor Analysis Consortium. It describes a proof-of-concept approach to identifying fraudulent data in biological data sets.

Tumor cells (colored red and brown) are shown in 3-dimensions against a black background. The cells are close together, emphasizing the importance of cell-cell interactions in supporting tumor growth.

Machine Learning Modeling Generates Accurate Insights into RAS-membrane Biology

In RAS-related diseases, such as cancer, mutations in the RAS genes or their regulators render RAS proteins persistently active. Investigating RAS activation events is challenging when using conventional techniques. An unprecedented multiscale platform is using machine learning to change that.

Going from left to right, white transitions to the silhouette of a man facing left with futuristic graphics in red and blue depicting brain activity, data, artificial intelligence.

Apply for Image Bioinformatics Scientist Position Supporting NCI’s Center for Cancer Research Artificial Intelligence Resource

NCI’s Center for Cancer Research invites applicants with image processing, machine learning, and deep learning experience to be considered for a federal image bioinformatics scientist position supporting the Artificial Intelligence Resource. The successful candidate will develop and implement automated imaging and data processing workflows to analyze large image data sets generated by confocal microscopes.

Colored silhouette depiction of two human "digital twin models"

Commentary Describes How Digital Twins Could Transform Cancer Care

Drs. Emily Greenspan and Eric Stahlberg of NCI’s CBIIT and Frederick National Laboratory for Cancer Research, respectively, recently contributed to an article, “Digital twins for predictive oncology will be a paradigm shift for precision cancer care,” published in Nature Medicine. The commentary examines the vision that members of NCI’s Envisioning Computational Innovations for Cancer Challenges (ECCIC) community have for developing cancer patient digital twins. Such a platform could revolutionize how clinicians and policymakers approach cancer care and further advance precision medicine.

Silver microphone on a short stand off to the left hand side of a desk; piece of paper and pen sitting on table to the right.

Latest Podcast Features NCI Leaders Sharing How Data and Tech Shape the Future of Cancer Research

In a recent podcast, NCI leaders from CBIIT and the Small Business Innovation Research Development Center shared how technological developments have enhanced cancer research and have helped usher in new diagnostics, treatments, and patient care.

View of DNA strands as viewed under a microscope.

NCI’s Division of Cancer Biology Supports Diverse Cancer Data Science That Uses Machine Learning and Artificial Intelligence

A few of NCI’s Division of Cancer Biology grantees recently released publications on topics such as machine learning and artificial intelligence. These research results hold clues to how we research and develop various cancer treatments.

Figure shows the graphical abstract from the recent article by Hong et al., “Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models,” which was published in Cell Reports Medicine. Using this machine learning model, researchers were able to interpret histological slides to identify four key subtypes of endometrial cancer (CNV-H, CNV-L, MSI-H, and POLE).

NCI-funded Machine Learning Gives New Insight into Endometrial Cancer

A new publication using NCI funding and resources shows that a machine learning model, called Panoptes, allowed cancer researchers to reliably predict subtypes of endometrial cancer. Such “computational pathology” offers a useful framework for supporting human pathologists, trimming the labor needed to interpret histological findings to under 4 minutes per slide, and eliminating the time and cost of genetic sequencing.

SUBSCRIBE TO UPDATES

Categories

Archive