BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/Los_Angeles X-WR-TIMEZONE:America/Los_Angeles BEGIN:VEVENT UID:70@escience.washington.edu DTSTART;TZID=America/Los_Angeles:20240201T163000 DTEND;TZID=America/Los_Angeles:20240201T172000 DTSTAMP:20240123T231102Z URL:https://escience.washington.edu/events/uwdss-komp/ SUMMARY:UW Data Science Seminar: Evan Komp DESCRIPTION:\n\nPlease join us for a UW Data Science Seminar on Thursday\, February 1st from 4:30 to 5:20 p.m. PST. The seminar will feature Evan Kom p\, recent PhD in Chemical Engineering Data Science.\n\nThe seminar will b e held in the Electrical &\; Computer Engineering Building (ECE)\, Room 105\n\n\n \;\n"Leveraging Nature's Translation Between Low and High T emperature Proteins with Deep Learning"\nAbstract: This work presents Neur al Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT)\, a novel approach for designing and ranking high-temperature sta ble proteins using neural machine translation. The training required the d evelopment of a new dataset of protein homologous pairs occurring in organ isms adapted to low and high temperatures\, which is detailed. The dataset is orders of magnitude larger than any dataset of its kind\, with 25 mill ion protein pairs. By training on over 4 million of the highest quality pa irs\, the model demonstrates promising capability in targeting thermal sta bility. A designed variant of the Drosophila melanogaster Engrailed Home odomain shows increased stability at high temperatures\, as validated by e stimators and molecular dynamics simulations. Furthermore\, NOMELT achieve s zero-shot predictive capabilities in ranking experimental melting and ha lf-activation temperatures across two protein families. It achieves this w ithout requiring extensive homology data or massive training datasets as d o existing zero-shot predictors by specifically learning thermophilicity\, as opposed to all natural variation. These findings underscore the potent ial of leveraging organismal growth temperatures in data-rich\, context-de pendent design of proteins for enhanced thermal stability.\nBio: Evan Komp recently finished his PhD in Chemical Engineering Data Science at the Uni versity of Washington under the amazing Prof. David Beck\, meanwhile award ed the data science fellowship from the Clean Energy Institute and a stint as a machine learning engineer in pharma. He has worked on a number of to pics at the intersection of deep learning and the chemical sciences\, incl uding molecular properties\, chemical reaction rates\, and protein thermal stability. Evan is a strong advocate for the use of data science to help us develop a more sustainable\, climate resilient and friendly society\, a nd as such encourages everyone who works in a compute intensive environmen t to track their computation's carbon emissions.\nThe UW Data Science Semi nar is an annual lecture series at the University of Washington that host s scholars working across applied areas of data science\, such as the scie nces\, engineering\, humanities and arts along with methodological areas i n data science\, such as computer science\, applied math and statistics. O ur presenters come from all domain fields and include occasional external speakers from regional partners\, governmental agencies and industry.\nThe 2023-2024 seminars will be held in person\, and are free and open to the public. LOCATION:Electrical and Computer Engineering Building\, Room 105\, 185 W St evens Way NE\, Seattle\, WA\, 98195\, United States X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=185 W Stevens Way NE\, Seat tle\, WA\, 98195\, United States;X-APPLE-RADIUS=100;X-TITLE=Electrical and Computer Engineering Building\, Room 105:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/Los_Angeles X-LIC-LOCATION:America/Los_Angeles BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST END:STANDARD END:VTIMEZONE END:VCALENDAR