Discover the results of the largest, real-world, federated learning study focusing on glioblastoma and leveraging data from thousands of patients across six continents. The speaker, Dr. Bakas, comes from the University of Pennsylvania’s Perelman School of Medicine.

Learn more about open-source artificial intelligence and machine learning models available to you!

Learn more about the safety and ethics of artificial intelligence in healthcare.

The NCI Center for Cancer Research’s Dr. Eytan Ruppin will present on “SELECT,” a computational approach that aims to identify clinically relevant synthetic lethal interactions and then harnesses them to predict patient response to cancer therapy from the bulk tumor transcriptome.

Dr. Obi L. Griffith will discuss CIViC, an open access, open source, community-driven web resource for clinical interpretation of variants in cancer. The goal of this resource is to enable precision medicine by providing an educational forum for dissemination of knowledge and active discussion of the clinical significance of cancer genome alterations.

Dr. Svitlana Volkova will discuss a suite of augmented intelligence solutions powered by Artificial Intelligence models. She’ll show how these models can be used to detect, anticipate, and reason with technical expertise and capability development to analyze and extract knowledge from large amounts of unstructured scientific literature data.

Dr. Grassberger will highlight the current computational and mathematical approaches for modeling the impact of radiotherapy on the immune system, as well as designing the next generation of combination trials.

Dr. Malachi Griffith will give an introduction to neoantigens, a promising area for cancer immunotherapy and precision medicine. Dr. Griffith will describe how immunogenomic and bioinformatic approaches are helping to identify neoantigens and therapeutic modalities to target these abnormal proteins. He also will offer insight into tools to support related clinical trial efforts.

Dr. Ben Raphael will describe how tumors are heterogeneous mixtures of normal and cancerous cells with distinct genetic and transcriptional profiles. He’ll also discuss computational approaches to quantify tumor heterogeneity and reconstruct tumor evolution using data from single-cell DNA and spatial RNA sequencing technologies.

Dr. Elana J. Fertig (whose lab also uses multiplatform genomics data, blended with mathematical modeling and artificial intelligence) will demonstrate how CoGAPS, an established method for identifying transcriptional signatures related to cell type and state, can be applied to single cell data to identify patterns underlying immunotherapy response and resistance. Combining CoGAPS with transfer learning approaches provides insight into the patterns found in preclinical models, which then can be applied to patient samples to find shared features across data sets from different species.