BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Machine learning in Physics\, Chemistry and Materi
 als discussion group (MLDG)
SUMMARY:MOFA: a principled framework for the unsupervised 
 integration of multi-omics data - Ricard Argelague
 t
DTSTART;TZID=Europe/London:20200120T163000
DTEND;TZID=Europe/London:20200120T170000
UID:TALK137476AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/137476
DESCRIPTION:The emergence of high-throughput technologies and 
 the increasing availability of clinical data are r
 adically changing the study of biology and its med
 ical applications. In particular\, the profiling o
 f multiple molecular layers (omics) from the same 
 patient\, provides a unique opportunity to build s
 tatistical models to understand the molecular sour
 ces of patient heterogeneity. \nI will present MOF
 A\, a matrix factorisation framework for the compr
 ehensive integration of multi-omics data. MOFA bui
 lds upon a Group Factor Analysis framework combine
 d with fast variational Bayes inference. The model
  pools information across all -omics to reconstruc
 t a low-dimensional representation of the data\, t
 hereby enhancing data interpretation and facilitat
 ing the definition of predictive models for clinic
 al outcomes.\nTo demonstrate its practical utility
 \, I will present an application of MOFA on a coho
 rt of 200 patient samples of chronic lymphocytic l
 eukaemia that were profiled using multiple molecul
 ar assays\, including somatic mutations\, RNA expr
 ession\, DNA methylation and ex vivo drug response
 s. MOFA identified major dimensions of disease het
 erogeneity\, including mutations on the immunoglob
 ulin heavy-chain variable region and trisomy of ch
 romosome 12.
LOCATION:Mott Seminar (531) room\, top floor of the Mott Bu
 ilding\, in the Cavendish Laboratory\, West Cambri
 dge.
CONTACT:Bingqing Cheng 
END:VEVENT
END:VCALENDAR