BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260605T154543Z
LOCATION:Bldg. 6 - Room 004
DTSTART;TZID=Europe/Stockholm:20260630T134500
DTEND;TZID=Europe/Stockholm:20260630T141500
UID:submissions.pasc-conference.org_PASC26_sess143_msa222@linklings.com
SUMMARY:Spectra to Molecule: Language Models for Automated Structure Eluci
 dation
DESCRIPTION:Marvin Alberts (IBM Research)\n\nStructure elucidation is inte
 gral in the day-to-day operation of any organic chemistry laboratory allow
 ing the composition of unknown substances to be determined. Most commonly 
 this is achieved via different spectroscopic techniques. First among them 
 Nuclear Magnetic Resonance (NMR), Infrared (IR) spectroscopy and Mass Spec
 trometry (MS). While the acquisition of the spectra has been largely autom
 ated, the analysis of them is not straightforward making the analysis of s
 pectra, particularly in large quantities, a time-consuming and tedious und
 ertaking. \n\nWe have developed AI-driven approaches to tackle these chall
 enges. We demonstrated for the first time that molecular structures can be
  reliably predicted from IR spectra alone, a task previously impossible fo
 r human chemists due to the limited interpretable information present in I
 R spectra. This approach was extended to the deconvolution of IR spectra o
 f mixtures, where we developed a method to predict the components present 
 in a mixture based solely on the IR spectrum and a molecular formula. Toge
 ther, these advances point toward a future where AI tools can aid and assi
 st chemists in structure elucidation, freeing them to focus on interpretat
 ion and discovery rather than routine analysis.\n\nDomain: Climate, Weathe
 r, and Earth Sciences\n\nSession Chair: Marco Lattuada (Universiity of Fri
 bourg)\n\n
END:VEVENT
END:VCALENDAR