Grupiranje proteina korištenjem MCL algoritma

undergraduate thesis

• Title (english): Protein clustering using MCL algorithm
• Author: Jana Martinović
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Krešimir Fertalj (član povjerenstva)
• Committee member: Vedran Mornar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Grupiranje je postupak nenadziranog strojnog učenja čiji je cilj objekte podijeliti u grupe na temelju njihovih sličnosti. Radi se o problemu kojega je teško formalno opisati te je sukladno tome teško ocijeniti koliko su ponuđena rješenja dobra.
Ipak, grupiranje je vrlo prirodan način raspolaganja podacima i primjenjivo je u najširem skupu područja pa je potreba za algoritmima koji nude kvalitetno rješenje na ovaj problem velika. Jedan od tih algoritama je MCL algoritam. On se snažno oslanja na koncept nasumične šetnje i njenu intrinzičnu povezanost s postojanjem prirodnih grupa čvorova u grafu.
Koristila sam MCL algoritam u svrhu grupiranja proteina HIV-a što se pokazalo vrlo uspješnim. 4298 proteina razvrstano je u 10 grupa i dobiveni rezultati su smisleni. Proteini u istim grupama imaju istu funkciju i za njih kodira isti gen. Stršećih vrijednosti bilo je malo, a njihovo postojanje je opravdano.

Abstract (english)

Clustering is an unsupervised machine learning method in which the objective is to separate objects into distinct groups based on their similarity. It is difficult to formalize and provide a satisfactory description of clustering or to evaluate proposed solutions.
However, clustering is a natural way of dealing with data and therefore useful for a wide range of applications. Any progress in this field is highly appreciated. MCL algorithm is based on the concept of random walks and its connection with the existence of clusters in a graph.
I applied the MCL algorithm for the detection of clusters of HIV proteins which was shown to be very successful. 4298 proteins were divided into 10 clusters and the results were accurate. The proteins that were put in the same cluster have the same function and are encoded by the same gene. There were only a few outliers, but their presence is justified.

• Keywords: grupiranje; MCL algoritam; proteini; HIV
• Keywords (english): clustering; cluster analysis; MCL algorithm; proteins; HIV
• Language: croatian
• URN:NBN: urn:nbn:hr:168:162537
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 21:07:02