BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NJBDA - New Jersey Big Data Alliance - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://njbda.org
X-WR-CALDESC:Events for NJBDA - New Jersey Big Data Alliance
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20241112T120000
DTEND;TZID=America/New_York:20241112T133000
DTSTAMP:20260416T034845
CREATED:20241031T151835Z
LAST-MODIFIED:20241031T151839Z
UID:2845-1731412800-1731418200@njbda.org
SUMMARY:Language model-guided anticipation and discovery of unknown metabolites
DESCRIPTION:Speaker: Michael Skinnider\, Princeton University \n\n\n\nLunch is available beginning at 12 PM \n\n\n\nSpeaker to begin promptly at 12:30 PM \n\n\n\nAbstract: Despite decades of study\, large parts of the human metabolome remain unexplored. Mass spectrometry-based metabolomics routinely detects thousands of unidentified small molecules within human tissues and biofluids\, but structure elucidation of novel metabolites remains a low-throughput endeavour. Here\, we present an approach that leverages chemical language models to discover previously uncharacterized metabolites. We introduce DeepMet\, a language model that learns the latent biosynthetic logic embedded within the chemical structures of known metabolites and exploits this understanding to anticipate the existence of as-of-yet undiscovered metabolites. Prospective synthesis of metabolites predicted to exist by DeepMet directs their targeted discovery. Integrating DeepMet with tandem mass spectrometry (MS/MS) data enables automated metabolite discovery within complex tissues. We demonstrate the potential for language models to accelerate the mapping of the metabolome by harnessinging DeepMet to discover several dozen mammalian metabolites. 
URL:https://njbda.org/event/language-model-guided-anticipation-and-discovery-of-unknown-metabolites/
LOCATION:Bendheim House\, Princeton University\, 26 Prospect Avenue\, Princeton\, New Jersey\, United States
CATEGORIES:lectures/talks
ATTACH;FMTTYPE=image/jpeg:https://njbda.org/wp-content/uploads/2024/10/mike_skinnider.jpg
END:VEVENT
END:VCALENDAR