prikaz prve stranice dokumenta Grupiranje proteinskih sljedova korištenjem modela dubokog učenja
No public access
master's thesis
Grupiranje proteinskih sljedova korištenjem modela dubokog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:124863
Šarić, Ivona
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Šarić, I. (2023). Grupiranje proteinskih sljedova korištenjem modela dubokog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:124863

Šarić, Ivona. "Grupiranje proteinskih sljedova korištenjem modela dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:124863

Šarić, Ivona. "Grupiranje proteinskih sljedova korištenjem modela dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:124863

Šarić, I. (2023). 'Grupiranje proteinskih sljedova korištenjem modela dubokog učenja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:124863

Šarić I. Grupiranje proteinskih sljedova korištenjem modela dubokog učenja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 July 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:124863

I. Šarić, "Grupiranje proteinskih sljedova korištenjem modela dubokog učenja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:124863

Metadata
TitleGrupiranje proteinskih sljedova korištenjem modela dubokog učenja
Title (english)Deep learning-based protein sequence clustering
AuthorIvona Šarić
MentorMirjana Domazet-Lošo (mentor)
Committee memberMirjana Domazet-Lošo (predsjednik povjerenstva)
Committee memberTomislav Jagušt (član povjerenstva)
Committee memberDanijel Mlinarić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-03, Croatia
Abstract
U radu je objašnjena tehnologija transformera i razrađena je motivacija za njeno korištenje u području bioinformatike. Opisana je ostvarena arhitektura transformera pomoću Keras i TensorFlow radnih okvira u programskom jeziku Python. Model grupira proteinske sljedove HIV-1 prema vrsti proteina i prema podtipu (soju) virusa. Objašnjena je potreba za provođenjem mutacija nad dohvaćenim podacima uslijed nedostataka istih. Performanse modela uspoređene su s rezultatima koje su ostvarili predtrenirani model ProteinBERT i alat MMseqs2 na istom skupu podataka.
Abstract (english)
In this paper, the transformer technology and the motivation for its use in the field of bioinformatics is explained. The implemented architecture of the transformer is described using the Keras and TensorFlow frameworks in the Python programming language. The model clusters HIV-1 protein sequences based on protein type and subtype (viral strain). The performance of the model is compared with the results achieved by the pretrained ProteinBERT model and the MMseqs2 tool on the same dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:124863
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-07-13 10:35:12