BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.3//EN TZID:America/Chicago X-WR-TIMEZONE:America/Chicago BEGIN:VEVENT UID:6@hpc-ai-society.org DTSTART;TZID=America/Chicago:20220127T120000 DTEND;TZID=America/Chicago:20220127T130000 DTSTAMP:20231101T202903Z URL:https://hpc-ai-society.org/Events/january-lunch-learn/ SUMMARY:SHPCP January Lunch & Learn DESCRIPTION:\n\nThe Society of HPC Professionals lunch and learn event\n&nb sp\;\n\n\n\n\n\nLunch &\; Learn – January 2022\nAI-Driven Adaptive Mu ltiresolution Molecular Simulations on Heterogeneous Computing Platforms\n 27 January 2022 | Live stream\nDownload presentations and/or watch videos \n[membership level="1\,2" show_noaccess="true"]\n  Watch video\n  Downl oad from Dropbox\n \;\n\n[/membership]\n\n\n\nAbout the Event\nEmergin g hardware tailored for artificial intelligence (AI) and machine learning (ML) methods provide novel means to couple them with traditional high perf ormance computing (HPC) workflows involving molecular dynamics (MD) simula tions. We propose Stream-AI-MD\, a novel instance of applying deep learnin g methods to drive adaptive MD simulation campaigns in a streaming manner. We leverage the ability to run ensemble MD simulations on GPU clusters\, while the data from atomistic MD simulations are streamed continuously to AI/ML approaches to guide the conformational search in a biophysically mea ningful manner on a wafer-scale AI accelerator. We demonstrate the efficac y of Stream-AI-MD simulations for two scientific use-cases: (1) folding a small prototypical protein\, namely BBA FSD-EY and (2) understanding prote in-protein interaction (PPI) within the SARS-CoV-2 proteome between two pr oteins\, nsp16 and nsp10. We show that Stream-AI-MD simulations can improv e time-to-solution by ~50X for BBA protein folding. In addition\, we also demonstrate the use of Stream-AI-MD in running multi resolution simulation s for understanding the SARS-CoV-2 replication transcription complex.\n\n& nbsp\;\nAbout the Speaker\nArvind Ramanathan\, Ph.D.\n\nArvind Ramanathan is a computational biologist in the Data Science and Learning Division at Argonne National Laboratory and a senior scientist at the University of Ch icago Consortium for Advanced Science and Engineering (CASE). His research interests are at the intersection of data science\, high performance comp uting and biological/biomedical sciences. His research focuses on three ar eas focusing on scalable statistical inference techniques:\n(1) for analys is and development of adaptive multi-scale molecular simulations for study ing complex biological phenomena (such as how intrinsically disordered pro teins self assemble\, or how small molecules modulate disordered protein e nsembles)\n(2) to integrate complex data for public health dynamics\n(3) f or guiding design of CRISPR-Cas9 probes to modify microbial function(s).\n \nArvind obtained his Ph.D. in computational biology from Carnegie Mellon University\, and was the team lead for integrative systems biology team wi thin the Computational Science\, Engineering and Division at Oak Ridge Nat ional Laboratory.  More information about his group and research interest s can be found at http://ramanathanlab.org.\n\n\n\n\n\nA reminder email wi th Zoom join info will be sent the day prior to the meeting to all registr ants.\nNote: please check your spam folder if you don't see it and conside r adding the domain hpc-ai-society.org to your approved list.\nMembers: th e join info is also on the Member Resources web page.\n\n \; END:VEVENT BEGIN:VTIMEZONE TZID:America/Chicago X-LIC-LOCATION:America/Chicago BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 TZNAME:CST END:STANDARD END:VTIMEZONE END:VCALENDAR