Webinar Description

Autonomous MRI systems at work At the University of California, San Diego, they’re using the latest in AI and machine learning technologies to advance the future of healthcare research as we know it. Albert Hsiao MD, PhD, an expert in augmented imaging and data analytics at University of California, San Diego, joins the team at Oracle to share details around his important research. Synthetic data and lifelike simulations are forever changing the way scientists are able to understand the complexities of the human heart.

Webinar Description

Assistant Professor Jon Tamir and his team at the Computational Sensing Imaging Lab are developing fast, robust and standardized MRI reconstruction methods that can be used across many institutions with disparate system hardware and clinical needs. For this project, recent advances in deep learning will be tailored to MRI reconstruction, and an online public platform will be developed to help other institutions train collaborative models. The objective is to alleviate some of the drawbacks associated with this important diagnosis tool.

Webinar Description

Associate Professor Marc Riedel and his team are using Oracle technologies to predict how strongly peptides derived from viral proteins will bind to cell-surface molecules as part of immune response.
This project tackles a grand challenge in computational science: predicting how strongly peptides derived from viral proteins will bind to cell-surface molecules as part of our immune response. The set of all the peptides that bind strongly is called a person’s immunopeptidome. This set is unique and determines the capacity of their immune system. The immune response to a virus such as SARS-CoV-2 hinges on whether the viral protein fragments bind into a groove in these cell-surface proteins -- like a key into a lock. The problem is that simulating the binding of a single pair of molecules takes hours, or even days, on a powerful computing cluster with existing approaches. There are millions of pairs. In this research we will develop new, highly targeted algorithms to make the computation tractable. We will turn billions of days of computing into millions of minutes, and solve the problem by deploying the algorithms at scale on Oracle’s cloud-computing infrastructure, completing the task in weeks. The computational results that we are proposing could play a critical role at two ends of the time spectrum of a pandemic response: (1) In the early phases, when identifying and characterizing the threat a new pathogen. (2) In the long term, to develop a deep understanding of the molecular mechanisms of the infection.