Institutional Repository of Vilnius University
Baltymų sąveikai svarbių aminorūgščių prognozavimas naudojant baltymų kalbų modelius /
Abstract
dc:descriptionAlmost all cellular processes are closely linked to the properties of proteins and their ability to recognise a variety of different interaction partners. Disruption of these interactions by mutations in binding residues, conformational changes or the absence of binding partners can lead to cellular dysfunctions in a wide range of diseases, making the analysis of protein interaction sites crucial for the identification of amino acids important for protein interactions. In this work, computationals models to predict protein interaction hot spot residues were developed, using protein language model ProtTrans and different modelling methods. The best models were obtained using linear methods and K-nearest neighbour classifier, but all models exhibited strong overfitting, their prediction accuracy is low and therfore, further application for prediction of protein interaction hot spots is not advisable.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Toločkaitė, Ieva,
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:ELABAETD210639790&prefLang=en_US