BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Untangling genome assembly graphs with graph neural networks - Lov
 ro Vrcek\, Genome Institute of Singapore\, A*STAR
DTSTART:20230607T150000Z
DTEND:20230607T160000Z
UID:TALK202234@talks.cam.ac.uk
CONTACT:Chaitanya's Talks List
DESCRIPTION:With the emergence of PacBio HiFi and ultra-long ONT reads\, t
 he efforts to assemble genomes of various species in a de novo manner have
  significantly increased. This is manifested in projects including the T2T
  consortium project\, the Human Pangenome Project and the Vertebrate Genom
 e Project\, which strive to assemble a large number of genomes with contem
 porary tools and data. However\, even with all the recent advances in sequ
 encing technologies\, manual curation of the assembly genomes is still nec
 essary. At the same time\, most de novo assembly tools rely on graph-simpl
 ification heuristics\, which have remained largely unchanged in recent yea
 rs. Moreover\, heuristics parameters have been hand-crafted using several 
 genomes for which a high-quality reference was available during the time o
 f development.\n\n \n\nWe implemented an entirely novel approach for resol
 ving assembly graphs into genomes\, one based on graph neural networks. We
  evaluated our method on different types of reads and with initial assembl
 y graphs produced in a different way\, comparing it against state-of-the-a
 rt de novo assemblers used in the field. Moreover\, the preliminary result
 s indicate the modularity and the adaptability of our approach\, which sho
 uld generalize better with every new genome assembly released\, requiring 
 minimal adjustments to the existing pipeline.\n\nhybrid talk:\nhttps://cl-
 cam-ac-uk.zoom.us/j/93934749405?pwd=M0ZERUZleklON01vZlpXbzhqTld0Zz09\n\nID
  riunione: 939 3474 9405\nPasscode: 374750
LOCATION:Seminar Room FW26\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR