Interpretability of Neural Networks in Drug Design

dc.contributor.advisor	Hochreiter, Sepp
dc.contributor.author	Aljeiroudi, Abd Alkareem
dc.date.accessioned	2024-03-12T08:13:19Z
dc.date.available	2024-03-12T08:13:19Z
dc.date.issued	2020
dc.date.submitted	2020-04-28
dc.identifier.uri	https://dspace.jcu.cz/handle/20.500.14390/42802
dc.format	52 p.
dc.format	52 p.
dc.language.iso	eng
dc.publisher	Jihočeská univerzita	cze
dc.rights	Bez omezení
dc.title	Interpretability of Neural Networks in Drug Design	cze
dc.title.alternative	INTERPRETABILITY OF NEURAL NETWORKS IN DRUG DESIGN	eng
dc.type	bakalářská práce	cze
dc.identifier.stag	61007
dc.description.abstract-translated	Several artificial neural networks were implemented and evaluated. Best network's architecture was selected on the basis of the AUC analysis. Later on, Integrated Gradients (IG) was used to attribute the network's decisions to the learned input. The performance of IG using different baselines was evaluated. IG identifies a number of already known toxicophores listed in the literature.	eng
dc.date.accepted	2020-06-15
dc.description.department	Přírodovědecká fakulta	cze
dc.thesis.degree-discipline	Bioinformatics	cze
dc.thesis.degree-grantor	Jihočeská univerzita. Přírodovědecká fakulta	cze
dc.thesis.degree-name	Bc.
dc.thesis.degree-program	Applied Informatics	cze
dc.description.grade	Dokončená práce s úspěšnou obhajobou	cze
dc.contributor.referee	Renz, Philipp