Institutional Repository of Vilnius University
Baltymų molekulinių struktūrų sąveikų regionų nusakymas naudojant giliojo mokymosi metodus /
Abstract
dc:descriptionIn this study a deep learning method was developed using graph convolution networks to determine the binding sites in protein molecular structures. To achieve this, the graph deep learning algorithm was modelled using graph attention networks in PyTorch Geometric library. Data used for training, validation and testing of this model was taken from “Protein Data Bank” data base and was converted to graphs. Model uses weighted cross entropy loss function, as well as Adam optimization algorithm. Matthews correlation coefficient (MCC) was employed as scoring algorithm. Optimized version of this model was based on graph convolution network with three layers which inputs’ sizes were: number of graph vertices, 256 and 64, respectively. Model was trained using PyTorch Geometric advanced mini batching, where batch size was 10 graphs. This training was done 1000 times. Model was tested with a new data set from “Protein Data Bank” data base and the results of testing where F1 = 0.82 and MCC = 0.72. These results show that model is good enough to be used to determine binding sites in protein molecular structures.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pažarauskas, Justas,
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:ELABAETD146241885&prefLang=en_US