{"675439":{"#nid":"675439","#data":{"type":"news","title":"New Machine Learning Method Lets Scientists Use Generative AI to Design Custom Molecules and Other Complex Structures","body":[{"value":"\u003Cp\u003ENew research from Georgia Tech is giving scientists more control options over generative artificial intelligence (AI) models in their studies. Greater customization from this research can lead to discovery of new drugs, materials, and other applications tailor-made for consumers.\u003C\/p\u003E\u003Cp\u003EThe Tech group dubbed its method PRODIGY (PROjected DIffusion for controlled Graph Generation). PRODIGY enables diffusion models to generate 3D images of complex structures, such as molecules from chemical formulas.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EScientists in pharmacology, materials science, social network analysis, and other fields can use PRODIGY to simulate large-scale networks. By generating 3D molecules from multiple graph datasets, the group proved that PRODIGY could handle complex structures.\u003C\/p\u003E\u003Cp\u003EIn keeping with its name, PRODIGY is the first plug-and-play machine learning (ML) approach to controllable graph generation in diffusion models. This method overcomes a known limitation inhibiting diffusion models from broad use in science and engineering.\u003C\/p\u003E\u003Cp\u003E\u201cWe hope PRODIGY enables drug designers and scientists to generate structures that meet their precise needs,\u201d said\u0026nbsp;\u003Ca href=\u0022https:\/\/ksartik.github.io\/\u0022\u003EKartik Sharma\u003C\/a\u003E, lead researcher on\u0026nbsp;\u003Ca href=\u0022https:\/\/prodigy-diffusion.github.io\/\u0022\u003Ethe project\u003C\/a\u003E. \u201cIt should also inspire future innovations to precisely control modern generative models across domains.\u201d\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EPRODIGY works on diffusion models, a generative AI model for computer vision tasks. While suitable for image creation and denoising, diffusion methods are limited because they cannot accurately generate graph representations of custom parameters a user provides.\u003C\/p\u003E\u003Cp\u003EPRODIGY empowers any pre-trained diffusion model for graph generation to produce graphs that meet specific, user-given constraints. This capability means, as an example, that a drug designer could use any diffusion model to design a molecule with a specific number of atoms and bonds.\u003C\/p\u003E\u003Cp\u003EThe group tested PRODIGY on two molecular and five generic datasets to generate custom 2D and 3D structures. This approach ensured the method could create such complex structures, accounting for the atoms, bonds, structures, and other properties at play in molecules.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMolecular generation experiments with PRODIGY directly impact chemistry, biology, pharmacology, materials science, and other fields. The researchers say PRODIGY has potential in other fields using large networks and datasets, such as social sciences and telecommunications.\u003C\/p\u003E\u003Cp\u003EThese features led to PRODIGY\u2019s acceptance for presentation at the upcoming International Conference on Machine Learning (\u003Ca href=\u0022https:\/\/icml.cc\/\u0022\u003EICML 2024\u003C\/a\u003E). ICML 2024 is the leading international academic conference on ML. The conference is taking place July 21-27 in Vienna.\u003C\/p\u003E\u003Cp\u003EAssistant Professor\u0026nbsp;\u003Ca href=\u0022https:\/\/faculty.cc.gatech.edu\/~skumar498\/\u0022\u003ESrijan Kumar\u003C\/a\u003E is Sharma\u2019s advisor and paper co-author. They worked with Tech alumnus\u0026nbsp;\u003Ca href=\u0022https:\/\/www.rtrivedi.me\/\u0022\u003ERakshit Trivedi\u003C\/a\u003E (Ph.D. CS 2020), a Massachusetts Institute of Technology postdoctoral associate.\u003C\/p\u003E\u003Cp\u003ETwenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Kumar is one of six faculty representing the School of Computational Science and Engineering (CSE) at the conference.\u003C\/p\u003E\u003Cp\u003ESharma is a fourth-year Ph.D. student studying computer science. He researches ML models for structured data that are reliable and easily controlled by users. While preparing for ICML, Sharma has been interning this summer at Microsoft Research in the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.microsoft.com\/en-us\/research\/group\/research-for-industry\/overview\/\u0022\u003EResearch for Industry\u003C\/a\u003E lab.\u003C\/p\u003E\u003Cp\u003E\u201cICML is the pioneering conference for machine learning,\u201d said Kumar. \u201cA strong presence at ICML from Georgia Tech illustrates the ground-breaking research conducted by our students and faculty, including those in my research group.\u201d\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EVisit \u003C\/em\u003E\u003Ca href=\u0022https:\/\/sites.gatech.edu\/research\/icml-2024\/\u0022\u003E\u003Cem\u003Ehttps:\/\/sites.gatech.edu\/research\/icml-2024\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E for news and coverage of Georgia Tech research presented at ICML 2024.\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ENew research from Georgia Tech is giving scientists more control options over generative artificial intelligence (AI) models in their studies. Greater customization from this research can lead to discovery of new drugs, materials, and other applications tailor-made for consumers.\u003C\/p\u003E\u003Cp\u003EThe Tech group dubbed its method PRODIGY (PROjected DIffusion for controlled Graph Generation). PRODIGY enables diffusion models to generate 3D images of complex structures, such as molecules from chemical formulas.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EScientists in pharmacology, materials science, social network analysis, and other fields can use PRODIGY to simulate large-scale networks. By generating 3D molecules from multiple graph datasets, the group proved that PRODIGY could handle complex structures.\u003C\/p\u003E\u003Cp\u003EIn keeping with its name, PRODIGY is the first plug-and-play machine learning (ML) approach to controllable graph generation in diffusion models. This method overcomes a known limitation inhibiting diffusion models from broad use in science and engineering.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"New research from Georgia Tech is giving scientists more control options over generative artificial intelligence (AI) models in their studies. "}],"uid":"36319","created_gmt":"2024-07-11 19:47:30","changed_gmt":"2024-07-12 15:23:57","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2024-07-11T00:00:00-04:00","iso_date":"2024-07-11T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"674340":{"id":"674340","type":"image","title":"PRODIGY Group.jpg","body":null,"created":"1720727268","gmt_created":"2024-07-11 19:47:48","changed":"1720727268","gmt_changed":"2024-07-11 19:47:48","alt":"CSE PRODIGY Group ICML 2024","file":{"fid":"257840","name":"PRODIGY Group.jpg","image_path":"\/sites\/default\/files\/2024\/07\/11\/PRODIGY%20Group.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/PRODIGY%20Group.jpg","mime":"image\/jpeg","size":125493,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/PRODIGY%20Group.jpg?itok=HEzSu3DE"}},"674339":{"id":"674339","type":"image","title":"CSE_ICML2024.png","body":null,"created":"1720726742","gmt_created":"2024-07-11 19:39:02","changed":"1720726742","gmt_changed":"2024-07-11 19:39:02","alt":"CSE ICML 2024","file":{"fid":"257839","name":"CSE_ICML2024.png","image_path":"\/sites\/default\/files\/2024\/07\/11\/CSE_ICML2024.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/CSE_ICML2024.png","mime":"image\/png","size":173722,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/CSE_ICML2024.png?itok=uiGRsZ3_"}},"674341":{"id":"674341","type":"image","title":"PRODIGY Graphic.png","body":null,"created":"1720727329","gmt_created":"2024-07-11 19:48:49","changed":"1720727329","gmt_changed":"2024-07-11 19:48:49","alt":"CSE PRODIGY Group ICML 2024","file":{"fid":"257841","name":"PRODIGY Graphic.png","image_path":"\/sites\/default\/files\/2024\/07\/11\/PRODIGY%20Graphic.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/PRODIGY%20Graphic.png","mime":"image\/png","size":88305,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/PRODIGY%20Graphic.png?itok=6_Lte6y4"}}},"media_ids":["674340","674339","674341"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"130","name":"Alumni"},{"id":"141","name":"Chemistry and Chemical Engineering"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"192863","name":"go-ai"},{"id":"10199","name":"Daily Digest"},{"id":"9153","name":"Research Horizons"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"39431","name":"Data Engineering and Science"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}