prikaz prve stranice dokumenta Klasifikacija proteinskih fragmenata
  Download
PDF 2.12 MB
master's thesis
Klasifikacija proteinskih fragmenata
Zagreb: University of Zagreb, Faculty of Science, 2023. urn:nbn:hr:217:583785
Radnić, Josipa
University of Zagreb
Faculty of Science
Department of Mathematics

Institutional repository: Repository of the Faculty of Science

Cite this document

Radnić, J. (2023). Klasifikacija proteinskih fragmenata (Master's thesis). Zagreb: University of Zagreb, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:217:583785

Radnić, Josipa. "Klasifikacija proteinskih fragmenata." Master's thesis, University of Zagreb, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:217:583785

Radnić, Josipa. "Klasifikacija proteinskih fragmenata." Master's thesis, University of Zagreb, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:217:583785

Radnić, J. (2023). 'Klasifikacija proteinskih fragmenata', Master's thesis, University of Zagreb, Faculty of Science, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:217:583785

Radnić J. Klasifikacija proteinskih fragmenata [Master's thesis]. Zagreb: University of Zagreb, Faculty of Science; 2023 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:217:583785

J. Radnić, "Klasifikacija proteinskih fragmenata", Master's thesis, University of Zagreb, Faculty of Science, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:217:583785

Metadata
TitleKlasifikacija proteinskih fragmenata
Title (english)Classification of protein fragments
AuthorJosipa Radnić
MentorPavle Goldstein (mentor)
Committee memberPavle Goldstein (predsjednik povjerenstva)
Committee memberMiljenko Huzak (član povjerenstva)
Committee memberMladen Jurak (član povjerenstva)
Committee memberVedran Čačić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Science
(Department of Mathematics)
Zagreb
Defense date and country2023-03-02, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Abstract
U ovom diplomskom radu promatra se problem klasifikacije proteina određenog proteoma u proteinske familije. Uz pomoć opisivanja aminokiselina numeričkim vektorima želi se povećati točnost standardnog modela pretraživanja. Nakon uvedenih pojmova, matematičkih i bioloških, nužnih za razumijevanje ovog rada, navode se metode pomoću kojih se pronalazi kugla u vektorskom prostoru. Nadziranim i nenadziranim načinom nalazi se kugla koja sadržava motive koji su biološki dokazani da pripadaju određenoj proteinskoj familiji. Istraživanje se provodi na pet različitih proteoma i promatra se uspješnost na različitim veličinima skupova podataka. Glavna mjera za uspješnost modela je F1-score. U radu su potvrđene pretpostavke o grupiranju pravih pozitivaca oko upita i postojanju kugle koja sadrži te prave pozitivce. Model se pokazao robustan na promjene broja podataka i nenadzirana klasifikacija se pokazala vrlo brzim rješenjem.
Abstract (english)
This thesis is concerned with classification of proteins into protein families. In particular, the aim is to increase the accuracy of a motif scanning procedure by using a description of amino acids as vectors. After describing the mathematical and some biological background we present our Euclidean ball searching techniques. With supervised and unsupervised classification we found a sphere that contains motifs that have been shown to belong to the designated protein family. This study was carried out on five different proteomes and for different sizes of data sets. F1-score was the primary metric used for measuring success of a model. Finally, we confirmed the hypothesis regarding clustering of true positive hits and the existence of sphere that contains them.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:217:583785
Study programmeTitle: Mathematical Statistics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-08-18 09:17:29