BEGIN:VCALENDAR
VERSION:2.0
PRODID:talks.ox.ac.uk
BEGIN:VEVENT
SUMMARY:Ideas for accelerated and integrated compute in imaging\, genomics
 \, and devices\, in Biobank and other datasets - Ben Busby (NVIDIA)
DTSTART;VALUE=DATE-TIME:20250717T130000
DTEND;VALUE=DATE-TIME:20250717T140000
UID:https://talks.ox.ac.uk/talks/id/dde220e6-3388-4989-b789-96b3ba2c1b04/
DESCRIPTION:For our next talk\, in the Digital Phenotyping seminar series\
 , we are delighted to host Ben Busby\, Senior Alliance Manager for Genomic
 s at NVIDIA on 17 July 2025\, 1:00 pm\, BDI seminar room 1. \n\nTitle: Ide
 as for accelerated and integrated compute in imaging\, genomics\, and devi
 ces\, in Biobank and other datasets\nDate: 17 July 2025\nTime: 13:00 – 1
 4:00\nVenue – BDI/OxPop seminar room 1\n\nAbstract\nAs we enter the age 
 of AI\, agents will play a larger role in analysis and knowledge managemen
 t and contextualization will become critical. The scientific (and practica
 l) implementation interfaces will not be limited to AI and chatbots. Accel
 erated scientific computing is extremely likely to play an expanding role 
 in traditional analysis\, particularly when using biobank scale data.  Som
 e vignettes on specific topics in acceleration will be offered:\n\n- Seque
 nce alignment and annotation\n\n- Synthetic image generation\n\n- Knowledg
 e graphs as memory\n\n- Single cell analysis\n\n- On-device computing\n\n-
  Estimation of cis- and trans- effects on variant penetrance by background
  haploblocks\n\nWe’ll end with a discussion of contextualization\, valid
 ation\, and garbage collection of model generated datasets with a focus on
  improvement of healthcare systems.  \n\nBio: Ben Busby is the Senior Alli
 ance Manager for Genomics at NVIDIA\, where he focuses on areas such as pr
 ototyping\, disease subtyping\, deep learning\, and knowledge graphs. He a
 lso holds an adjunct faculty position in the Computational Biology Departm
 ent at Carnegie Mellon University and serves as an advisor to both Johns H
 opkins University and Research to the People at Stanford. Ben earned his P
 hD in Biochemistry from the University of Maryland\, Baltimore\, and did a
  postdoc in evolutionary genomics at NCBI.  \n\n--------------------------
 --------------------------------------------------------------------------
 -------------\n\nHybrid Option:\nPlease note that these meetings are close
 d meetings and only open to members of the University of Oxford. Please re
 spect our speakers and do not share the link with anyone outside of the Un
 iversity. The purpose of these seminars is to foster more communication am
 ong employees throughout the University\, so we strongly advise in-person 
 attendance whenever feasible.\n\nMicrosoft Teams meeting \nJoin the meetin
 g now \nMeeting ID: 377 252 440 130 6 \nPasscode: PB3pp2pZ \n\n-----------
 --------------------------------------------------------------------------
 ----------------------------\n\nIf you wish to know more or receive inform
 ation related to trainings and events at BDI\, please subscribe by emailin
 g bdi-announce-subscribe@maillist.ox.ac.uk. You'll then receive an email f
 rom SYMPA and once you reply you'll be on the list!\nSpeakers:\nBen Busby 
 (NVIDIA)
LOCATION:Big Data Institute (Seminar room 1)\, Old Road Campus OX3 7LF
TZID:Europe/London
URL:https://talks.ox.ac.uk/talks/id/dde220e6-3388-4989-b789-96b3ba2c1b04/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Ideas for accelerated and integrated compute in imaging\,
  genomics\, and devices\, in Biobank and other datasets - Ben Busby (NVIDI
 A)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
BEGIN:VEVENT
SUMMARY:Wearables in mega-scale biobanks – are there some learnings for 
 rare disease research? - Professor Aiden Doherty (University of Oxford)
DTSTART;VALUE=DATE-TIME:20240610T110000
DTEND;VALUE=DATE-TIME:20240610T120000
UID:https://talks.ox.ac.uk/talks/id/d132cedc-2d69-4bc0-8d9b-41f3bb1534f4/
DESCRIPTION:I will discuss the story behind the collection of wrist-worn a
 ccelerometer data in over 150\,000 research participants across the UK and
  China\, while also describing efforts to collect complementary open human
  activity recognition validation datasets to further enhance these resourc
 es. I will share the development of machine learning methods for sleep\, s
 edentary behaviour\, physical activity behaviours and steps\, referring to
  open software tools and data resources of relevance to others in the fiel
 d\, and hopefully beyond to identify opportunities for collaboration with 
 rare disease researchers.\nSpeakers:\nProfessor Aiden Doherty (University 
 of Oxford)
LOCATION:Lecture Theatre
TZID:Europe/London
URL:https://talks.ox.ac.uk/talks/id/d132cedc-2d69-4bc0-8d9b-41f3bb1534f4/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Wearables in mega-scale biobanks – are there some learn
 ings for rare disease research? - Professor Aiden Doherty (University of O
 xford)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
BEGIN:VEVENT
SUMMARY:Wearables & AI – a new opportunity to transform epidemiology in 
 the 21st Century  - Professor Aiden Doherty (University of Oxford)
DTSTART;VALUE=DATE-TIME:20230424T170000
DTEND;VALUE=DATE-TIME:20230424T180000
UID:https://talks.ox.ac.uk/talks/id/ec35e962-cff1-42cd-88bb-ff68cad7f54f/
DESCRIPTION:Professor Aiden Doherty's inaugural lecture\nSpeakers:\nProfes
 sor Aiden Doherty (University of Oxford)
LOCATION:Richard Doll Building (Lecture Theatre)\, Old Road Campus OX3 7LF
TZID:Europe/London
URL:https://talks.ox.ac.uk/talks/id/ec35e962-cff1-42cd-88bb-ff68cad7f54f/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Wearables & AI – a new opportunity to transform epidemi
 ology in the 21st Century  - Professor Aiden Doherty (University of Oxford
 )
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR