This Institute for Quantitative Biomedicine Crash Course will present a broad overview of how Artificial Intelligence/Machine Learning (AI/ML) methods are being used for de novo protein structure prediction and provide hands-on experience with both AlphaFold2 and RoseTTAFold.

CASP14 revealed that AlphaFold2, developed by Google DeepMind, Inc., can predict threedimensional structures of small globular proteins with accuracies comparable to experimental methods. RoseTTAFold, developed at the University of Washington/Howard Hughes Medical Institute, approaches AlphaFold2 in terms of prediction accuracy while requiring fewer computational resources.

In this Crash Course, expert speakers will provide a solid foundation on the role of AI/ML in structural biology and showcase ongoing research efforts at Rutgers. During the hands-on tutorial, participants will learn how to utilize these new computational tools to compute structure models from amino acid sequences and download precomputed structure models from the AlphaFoldDB database. Local computing resources (Rutgers University Amarel Cluster) and access to Google Colab and the RoseTTAFold server will be made available during the hands-on session.
Please click on the event title for more information.

The Eastern Regional Network’s (ERN) Broadening the Reach Working Group is pleased to launch the first in a series of workshops in support of leveraging the cloud in research.

The virtual workshop is bringing together researchers, faculty, research computing and central IT professionals, as well as other institutional stakeholders, including students and administrators, to share information and facilitate discussions about successful implementation of the cloud for research from the researcher and institutional perspectives.

Please click on the event title for more information.

Materials Discovery is one of the research areas where gaining a deeper understanding of the workflows, research computing and data requirements, collaborations, and challenges will enable the ERN to have the broadest impact across multiple research disciplines, pedagogical approaches, senior level college and university administrators, and other organizations within the region and beyond. Researchers in materials discovery are realizing their traditional data-intensive HPC workflows are reaching the limits of original progress. For this reason, they are looking to new paradigms that include convergence of HPC and Machine Learning (ML) methodologies, algorithm development, and novel ways to access the data distributed across multiple institutions used in training systems as promising approaches to overcome the major computational performance limitations they are faced with. Exploratory conversations with Penn State, Rutgers, SUNY Buffalo, MIT, and others suggest that Materials Discovery offers an attractive testbed for advanced cyberinfrastructure of the sort the ERN can offer through future funding opportunities such as the Mid-Scale RI-1 program. As with Cryo-EM/Cryo-ET, this session will explore possibilities for extending collaborations to include other institutions as well as the community of Research Computing and Networking organizations.
Please click on the event title to view the agenda on the next webpage.