BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260715T224103Z
UID:55ce8ac0-b50f-4c88-949f-a76440719f51
DTSTART:20250219T150000Z
DTEND:20250219T160000Z
DESCRIPTION:Susanna Zucca from enGenome will talk about "Using artificial i
 ntelligence for the interpretation of genomic variants"  at the GHGA lectu
 re series "Advances in Data-Driven Biomedicine" on February 19\, 2025.\n\n
 Registration:\n\nPlease register here.\n\nBiography:\n\nSusanna is a co-fo
 under of enGenome and holds a Master's Degree in Biomedical Engineering\, 
 as well as a Ph.D. in Bioengineering and Bioinformatics. She is an expert 
 in genomic data analysis and the development of bioinformatics tools. Curr
 ently\, she serves as the Chief Science Officer at enGenome SRL\, utilizin
 g her extensive academic expertise to spearhead innovative projects and pr
 opel scientific progress within the organization. Her current focus is on 
 harnessing generative AI technologies to enhance genomic data analysis.\n\
 nAbstract:\n\nAs personalized medicine continues to advance\, the ability 
 to predict how genetic variants affect individual health has become increa
 singly important. Artificial Intelligence (AI) is playing a pivotal role i
 n this progress by enabling the analysis of vast datasets and uncovering p
 atterns that were previously inaccessible. AI encompasses a variety of met
 hods and algorithms\, some of which have been used for decades.\n\nEarly a
 pplications of AI in genomics focused on simple rule-based systems and mac
 hine learning (ML) models designed to assess the pathogenicity of genetic 
 variants. ML-based in silico predictors were among the first AI-driven too
 ls to make a significant impact on genomic prediction. Rule-based systems 
 also emerged during this time\, automating the application of variant inte
 rpretation guidelines and laying the groundwork for more advanced approach
 es.\n\nIn recent years\, deep learning has revolutionized AI applications 
 in genomics\, especially in the interpretation of complex genomic data. Th
 is has led to the development of advanced variant effect predictors\, such
  as AlphaMissense\, SpliceAI\, and PrimateAI. Simultaneously\, the integra
 tion of clinical data into AI frameworks has become crucial in clinical di
 agnostics\, enhancing both the accuracy and efficiency of variant interpre
 tation. Emerging techniques like explainable AI and transfer learning prom
 ise to further improve model transparency and reliability\, addressing key
  concerns in the field.\n\nThe 2023 rise of generative AI is transforming 
 many disciplines\, including genomics. Tools leveraging these methods are 
 now being developed to enhance variant interpretation\, proving the potent
 ial of this technology to redefine the landscape of genomic analysis.\n\nL
 ooking ahead\, the role of AI in genomics is expected to grow\, driving ad
 vances in precision medicine and becoming a routine part of clinical pract
 ice\, while aligning with the upcoming regulations in the field\, such as 
 the AI Act. These innovations are poised to refine personalized disease ri
 sk assessments and treatment outcome predictions.
SUMMARY:GHGA Lecture Series with Susanna Zucca
URL;VALUE=URI:https://www.ghga.de/events/detail/ghga-lecture-series-susanna
 -zucca-virtual
END:VEVENT
END:VCALENDAR