BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20230413T102017Z
DTSTART:20230502T130000Z
DTEND:20230502T140000Z
SUMMARY:IDSAI Seminar: Professor Claudio Angione
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}d1c6-lgeyyc
 vu-gbuw37
DESCRIPTION:Speaker: Claudio Angione\, Professor of Artificial Intelligen
 ce at Teesside University (TU)\n\nTitle: Combining machine learning and 
 metabolic modelling approaches to characterise the cell phenotype\n\nIn 
 recent biomedical research\, deep learning has been widely used for the 
 exploitation of omics data when predicting the cell phenotype\, sufferin
 g however from a lack of biological interpretability. In parallel\, cons
 traint-based mathematical modelling of metabolism has gained popularity 
 due to its scope and flexibility\, enabling mechanistic insights into th
 e genotype-phenotype-environment relationship within cells.\n\nThese two
  computational frameworks have mostly been used in isolation\, having di
 stinct research communities associated with them. However\, their comple
 mentary characteristics and common mathematical bases make them particul
 arly suitable to be combined. I will describe how machine learning can b
 e combined with constraint-based modelling\, discuss the mathematical an
 d practical aspects involved\, and show several applications in biotechn
 ology and biomedicine.\n\nInstead of applying machine learning to omics 
 data directly\, we propose a multi-view approach merging experimental om
 ics data and model-generated predictions\, based on known biochemistry. 
 This architecture can contribute with disjoint information towards biolo
 gically-informed and interpretable machine learning\, including key mech
 anistic information in an otherwise biology-agnostic learning process.
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
END:VEVENT
END:VCALENDAR