BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Hypergraph Factorisation for Multi-Tissue Gene Expression Imputati
 on - Ramon Vinas Torne
DTSTART:20230530T120000Z
DTEND:20230530T130000Z
UID:TALK200395@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Integrating gene expression across tissues is crucial for unde
 rstanding the coordinated biological mechanisms that drive disease and cha
 racterise homeostasis. However\, traditional multi-tissue integration meth
 ods cannot handle uncollected tissues or rely on genotype information\, wh
 ich is often unavailable and subject to privacy concerns. To address these
  challenges\, we present HYFA (Hypergraph Factorisation)\, a parameter-eff
 icient graph representation learning approach for joint imputation of mult
 i-tissue and cell-type gene expression. HYFA represents multi-tissue gene 
 expression in a hypergraph of individuals\, metagenes\, and tissues\, and 
 learns factorised representations via a custom message passing neural netw
 ork operating on the hypergraph. HYFA supports a variable number of refere
 nce tissues\, increasing the statistical power over single-tissue approach
 es\, and incorporates inductive biases to exploit the shared regulatory ar
 chitecture of tissues and genes. In performance comparison\, HYFA attains 
 improved performance over TEEBoT and standard imputation methods across a 
 broad range of tissues from the Genotype-Tissue Expression (GTEx) project.
  In post-imputation analysis\, application of expression Quantitative Trai
 t Loci (eQTL) mapping on the fully-imputed GTEx data yields a substantial 
 increase in number of detected replicable eQTLs.\n\n!https://figshare.com/
 ndownloader/files/40384511/preview/40384511/preview.jpg!\n\n"You can also 
 join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVEkvNmw3Q0dqNDV
 RalZvdz09
LOCATION:Lecture Theatre 1\, Computer Laboratory\, William Gates Building 
 and Zoom
END:VEVENT
END:VCALENDAR