Institutional Repository of Vilnius University
Baltymo sūkio kampų prognozavimas iš aminorūgščių sekos naudojant neuroninius tinklus /
Abstract
dc:descriptionArtificial neural network is a mathematical model that imitates low level intellect in naturally occurring organisms and has a quality of forming non-linear relationships between input and output data. In this study, artificial neural networks that predict protein torsion angles phi and psi from their amino acid residue chain are formed. Usually it is quite difficult to obtain this kind of information therefore an accurate model would be a priceless tool for protein related research. In order to achieve this goal data about proteins is collected and additional information about their amino acid residue chains is generated. Resulting data is prepared for use with artificial neural networks which are formed and trained using artificial neural network framework „Keras“. Results are compared with results achieved in another scientific study.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2018
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Valiukėnas, Grantas Jonas,
- Contributors dc:contributor
-
- Grinis, Irus
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD29420132&prefLang=en_US