Deep learning applications in anti-aging drug discovery

Μπαλούγιας, Θεόδωρος; Balougias, Theodoros

dc.contributor.author	Μπαλούγιας, Θεόδωρος	el
dc.contributor.author	Balougias, Theodoros	en
dc.date.accessioned	2022-09-28T10:00:08Z
dc.date.available	2022-09-28T10:00:08Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/55800
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.23498
dc.rights	Default License
dc.subject	Deep Learning	en
dc.subject	Βαθειά μάθηση	el
dc.subject	Aging	en
dc.subject	Drug discovery	en
dc.subject	Systems biology	en
dc.subject	Statistics	en
dc.subject	Γήρανση	el
dc.subject	Ανακάλυψη φαρμάκων	el
dc.subject	Βιολογία συστημάτων	el
dc.subject	Στατιστική	el
dc.title	Deep learning applications in anti-aging drug discovery	en
heal.type	bachelorThesis
heal.classification	Deep Learning in drug discovery	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2022-03-30
heal.abstract	Aging is considered nowadays by the scientific community as a disease that needs to be treated. Cellular senescence is one of the key characteristics of aging, as it leads to the apoptosis of cells and their abnormal reproduction. It is therefore of value to identify drugs that combat the biological effects of cellular senescence in the human organism. In this direction, we developed a deep learning model which can predict the biological footprint of compounds given their chemical structure. In particular, the model learns and predicts a biological distance between a pair of compounds, as well as some biological pathways that are activated due to the perturbations caused by the compounds in specific cell lines. In addition, we are utilizing data from in-vitro senescence induction experiments to identify relations between the compounds used in these experiments and the ones from our web database with the goal of selecting those that most probably express senolytic activity and using them then as inputs to our model in order to screen for more similar compounds with such activity in other databases.	en
heal.advisorName	Αλεξόπουλος, Λεωνίδας	el
heal.committeeMemberName	Αλεξόπουλος, Λεωνίδας	el
heal.committeeMemberName	Σπιτάς, Βασίλειος	el
heal.committeeMemberName	Προβατίδης, Χριστόφορος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Μηχανολόγων Μηχανικών. Τομέας Ρευστών. Εργαστήριο Βιορευστομηχανικής και Βιοϊατρικής Τεχνολογίας	el
heal.academicPublisherID	ntua
heal.numberOfPages	54 σ.	el
heal.fullTextAvailability	false