Primjena metoda grupiranja u otkrivanju genetičke rekombinacije

master's thesis

• Title (english): Clustering methods for genetic recombination detection
• Author: Robert Tušek
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Ivica Botički (član povjerenstva)
• Committee member: Tomislav Jagušt (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-25, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Genetička rekombinacija je česta pojava koja se može uočiti kod prokariota, eukariota i virusa. Kod bakterija i virusa ona je često mehanizam kojim prenose gene poput gena za rezistenciju na antibiotike i antiviralne lijekove, pa detekcija takvih pojava može biti od presudne važnosti. Postojeća računalna rješenja često imaju velike memorijske i prostorne složenosti pa postoji potreba za optimalnijim metodama. U ovom radu testiram metode grupiranja uparene s akumuliranim prirodnim vektorima kao sredstvo otkrivanja genetičke rekombinacije. Dobiveni rezultati varirali su od metode do metode, ali su neki postupcima ostvareni bolji rezultate od drugih. Na temelju rezultata izvodim zaključke o korištenju pojedinih metoda grupiranja kao sredstva otkrivanja genetičke rekombinacije.

Abstract (english)

Genetic recombination is a common occurrence observable in procaryotes, eukaryotes and viruses. Bacteria and viruses often use it as a mechanism of transferring genes such as genes resistant to antibiotics and antivirals, which in turn makes the detection of such phenomena very important. Existing computational solutions often have large time and space complexities, so there is a need for more optimal methods. In this paper, I test clustering algorithms paired with accumulated natural vectors as a means of discovering genetic recombination. The results varied from a method to method, but some of them achieved better results than others. Based on the results, I attempt to reach conclusions about using certain clustering algorithms as a means for detecting genetic recombination.

• Keywords: Bioinformatika; genomika; strojno učenje; grupiranje; genetička rekombinacija
• Keywords (english): Bioinformatics; genomics; machine learning; clustering; genetic recombination
• Language: croatian
• URN:NBN: urn:nbn:hr:168:064128
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 14:06:36