BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250629T163354Z UID:32517303-2D45-44B4-87B4-18B13C821358 DTSTART;TZID=America/New_York:20250624T190000 DTEND;TZID=America/New_York:20250624T203000 DESCRIPTION:Boston\, Columbia\, Costa Rica\, Guatemala\, Panama\, Peru and San Antonio Chapters of the IEEE Computer Society\, Boston IEEE Engineerin g in Medicine and Biology Society (EMBS)\, New Jersey Coast and North Flor ida Sections of IEEE and GBC/ACM\n---------------------------------------- -----------------------\n[GabrieleCorso.jpg](https://events.vtools.ieee.or g/tego_/event/GabrieleCorso.jpg)[JeremyWohlwend.jpg](https://events.vtools .ieee.org/tego_/event/JeremyWohlwend.jpg)7:00 PM\, Tuesday\, 24 June 2025\ nMIT Room 32-G449 (Kiva) and online via Zoom\n\nCareers in Technology\n\nB oltz: Towards a Unified Approach for Biomolecular Interaction Modeling\n\n [With updates on new features in Boltz-2 including the ability to predict Binding Affinity]\n\nGabriele Corso and Jeremy Wohlwend\n\nPlease register in advance for this seminar even if you plan to attend in person at\n\n<h ttps://acm-org.zoom.us/webinar/register/5917463193812/WN_U1yhFblMQO-I4n1cB hkBFw>\n\nAfter registering\, you will receive a confirmation email contai ning information about joining the webinar.\n\nIndicate on the registratio n form if you plan to attend in person. This will help us determine whethe r the room is close to reaching capacity. We plan to serve light refreshme nts (probably pizza) before the talk starting at around 6:30 pm. Letting u s know you will come in person will help us determine how much pizza to or der.\n\nWe may make some auxiliary material such as slides and access to t he recording available after the seminar to people who have registered.\nA bstract:\nAccurately modeling biomolecular interactions is a central chall enge in modern biology. While recent advances\, such as AlphaFold3 and Bol tz-1\, have substantially improved our ability to predict biomolecular com plex structures\, these models still fall short in predicting binding affi nity\, a critical property underlying molecular function and therapeutic e fficacy. In this talk\, we present Boltz-2\, a new structural biology foun dation model that exhibits strong performance for both structure and affin ity prediction. Boltz-2 introduces controllability features including expe rimental method conditioning\, distance constraints\, and multi-chain temp late integration for structure prediction\, and is\, to our knowledge\, th e first AI model to approach the performance of free-energy perturbation ( FEP) methods in estimating small molecule--protein binding affinity. Cruci ally\, it achieves strong correlation with experimental readouts on many b enchmarks\, while being at least 1000 times more computationally efficient than FEP.\n\nFor more information see [boltz-2 info](https://boltz.bio/bo ltz2)\n\nBio:\n\nJeremy Wohlwend and Gabriele Corso received PhDs this spr ing for work at the MIT Computer Science and Artificial Intelligence Labor atory where their research focuses on developing novel ML frameworks to ta ckle challenging problems in drug discovery and immunology.\n\nDirections to 32-G449 - MIT Stata Center\, 32 Vassar Street\, Cambridge\, MA: Please use the main entrance to the Stata Center at 32 Vassar Street (the entranc e closest to Main street) as those doors will be unlocked. Upon entering\, proceed to the elevators which will be on the right after passing a large set of stairs and a MITAC kiosk. Take the elevator to the 4th floor and t urn right\, following the hall to an open area\; 32-G449 will be on the le ft. [Location of Stata on campus map](https://whereis.mit.edu/?go=32)\n\nT his joint meeting of the Boston (and other)Chapter(s) of the IEEE Computer and EMBS Societies and GBC/ACM will be hybrid (in person and online).\n\n Co-sponsored by: gbc/acm\n\nSpeaker(s): Gabriele Corso\, Jeremy Wohlwend\, \n\nRoom: MIT Room 32-G449 (Kiva)\, Bldg: Stata Center\, MIT building 32\ , 32 Vassar St\, Cambridge\, Massachusetts\, United States\, Virtual: http s://events.vtools.ieee.org/m/483979 LOCATION:Room: MIT Room 32-G449 (Kiva)\, Bldg: Stata Center\, MIT building 32\, 32 Vassar St\, Cambridge\, Massachusetts\, United States\, Virtual: h ttps://events.vtools.ieee.org/m/483979 ORGANIZER:p.mager@computer.org SEQUENCE:42 SUMMARY:Boltz: Towards a Unified Approach for Biomolecular Interaction Mode ling URL;VALUE=URI:https://events.vtools.ieee.org/m/483979 X-ALT-DESC:Description: <br /><h2>Boston\, Columbia\, Costa Rica\, Guatemal a\, Panama\,&nbsp\; Peru and San Antonio&nbsp\; Chapters of the IEEE Compu ter Society\, Boston IEEE Engineering in Medicine and Biology Society (EMB S)\, New Jersey Coast and North Florida Sections of IEEE and GBC/ACM</h2>\ n<hr>\n<blockquote><a href="https://events.vtools.ieee.org/tego_/event/Gab rieleCorso.jpg"><img src="https://events.vtools.ieee.org/tego_/event/Gabri eleCorso.jpg" alt="GabrieleCorso.jpg" width="200" height="200" align="righ t" border="0" hspace="9" vspace="9"></a><a href="https://events.vtools.iee e.org/tego_/event/JeremyWohlwend.jpg"><img src="https://events.vtools.ieee .org/tego_/event/JeremyWohlwend.jpg" alt="JeremyWohlwend.jpg" width="200" height="200" align="right" border="0" hspace="9" vspace="9"></a>7:00 PM\, Tuesday\, 24 June 2025\n<p>MIT Room 32-G449 (Kiva) and online via Zoom</p> \n<p>Careers in Technology</p>\n<h4>Boltz: Towards a Unified Approach for Biomolecular Interaction Modeling</h4>\n<h4>[With updates on new features in Boltz-2 including the ability to predict Binding Affinity]</h4>\n<h4>Ga briele Corso and Jeremy Wohlwend</h4>\n<p>&nbsp\;</p>\n<h4>Please register in advance for this seminar even if you plan to attend in person at</h4>\ n<p class="p1">&lt\;https://acm-org.zoom.us/webinar/register/5917463193812 /WN_U1yhFblMQO-I4n1cBhkBFw&gt\;</p>\n<p>After registering\, you will recei ve a confirmation email containing information about joining the webinar.< /p>\n<p>Indicate on the registration form if you plan to attend in person. This will help us determine whether the room is close to reaching capacit y. We plan to serve light refreshments (probably pizza) before the talk st arting at around 6:30 pm. Letting us know you will come in person will hel p us determine how much pizza to order.</p>\n<p>We may make some auxiliary material such as slides and access to the recording available after the s eminar to people who have registered.</p>\nAbstract:</blockquote>\n<blockq uote>\n<p>Accurately modeling biomolecular interactions is a central chall enge in modern biology. While recent advances\, such as AlphaFold3 and Bol tz-1\, have substantially improved our ability to predict biomolecular com plex structures\, these models still fall short in predicting binding affi nity\, a critical property underlying molecular function and therapeutic e fficacy. In this talk\, we present Boltz-2\, a new structural biology foun dation model that exhibits strong performance for both structure and affin ity prediction. Boltz-2 introduces controllability features including expe rimental method conditioning\, distance constraints\, and multi-chain temp late integration for structure prediction\, and is\, to our knowledge\, th e first AI model to approach the performance of free-energy perturbation ( FEP) methods in estimating small molecule--protein binding affinity. Cruci ally\, it achieves strong correlation with experimental readouts on many b enchmarks\, while being at least 1000 times more computationally efficient than FEP.</p>\n<p>For more information see&nbsp\;<a href="https://boltz.b io/boltz2">boltz-2 info</a></p>\n</blockquote>\n<blockquote>\n<p>Bio:</p>\ n<p>Jeremy Wohlwend and Gabriele Corso received PhDs this spring for work at the MIT Computer Science and Artificial Intelligence Laboratory where t heir research focuses on developing novel ML frameworks to tackle challeng ing problems in drug discovery and immunology.</p>\n<p>Directions to 32-G4 49 - MIT Stata Center\, 32 Vassar Street\, Cambridge\, MA: Please use the main entrance to the Stata Center at 32 Vassar Street (the entrance closes t to Main street) as those doors will be unlocked. Upon entering\, proceed to the elevators which will be on the right after passing a large set of stairs and a MITAC kiosk. Take the elevator to the 4th floor and turn righ t\, following the hall to an open area\; 32-G449 will be on the left.&nbsp \;<a href="https://whereis.mit.edu/?go=32">Location of Stata on campus map </a></p>\n<p>&nbsp\;</p>\n<p class="norm10">&nbsp\;This joint meeting of t he Boston (and other)Chapter(s) of the IEEE Computer and EMBS Societies an d GBC/ACM will be hybrid (in person and online).</p>\n</blockquote> END:VEVENT END:VCALENDAR