Primjena algoritma k-sredina na problem grupiranja gena

undergraduate thesis

• Title (english): Application of k-means clustering algorithm to gene clustering
• Author: Adela Prebeg
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Ivica Botički (član povjerenstva)
• Committee member: Fran Tonković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu istražila sam što su mikročipovi, kako grupirati podatke iz mikročipova pomoću algoritma k-sredina i kako na rezultate grupiranja utječu mjere udaljenosti. U programskom jeziku Python implementirala sam algoritam k-sredina i tri mjere udaljenosti: Pearsonovu, Eisenovu i Spearmanovu. Algoritam sam testirala na skupu razina ekspresije gena koji su dobiveni iz mikročipa. Razine ekspresije gena iz mikročipa dobivene su iz genetskog materijala pacijenata koji boluju od akutne limfocitne leukemije "ALL" i akutne mijelocitne leukemije "AML". Algoritam je trebao prepoznati da se u uzorcima kriju dvije grupe, da su to grupe pacijenata koji boluju od ALL i AML leukemije, te ispravno grupirati nove podatke. Algoritam je bio dosta uspješan u prepoznavanju te dvije vrste leukemije, ali ima mjesta za poboljšanje. Između tri mjere udaljenosti koje su implementirane najbolje rezultate dale su mjere Pearsonova i Spearmanova udaljenost.

Abstract (english)

The aim of this paper was to study DNA microarrays, k-means clustering algorithm, and the way distance functions used in clustering effect clustering results. I implemented the k-means clustering algorithm and Pearsons, Eisens and Spearmans distance functions in the Python programming language. I tested the implementation of the algorithm on gene expression levels collected from a microarray that contains genetic materials collected from patients suffering from acute lymphocytic leukemia "ALL" and acute myelocytic leukemia "AML". The algorithm identified that there are two clusters in the data provided, that those two cluster are distinguished by the le- ukemia the patient is suffering from and it assigned new samples to the correct cluster. The algorithm was pretty good at distinguishing those two types of leukemia, but there is room for improvements. From the three distance functions I implemented the best preforming ones were Pearsons and Spearmans distance function.

• Keywords: Python; k-sredine; Pearsonova mjera; Spearmanova mjera; Eisenova mjera; grupiranje; mikročip
• Keywords (english): Python; k-means; Pearson’s rank correlation coefficient; Spearman’s rank correlation coefficient; Eisen’s rank correlation coefficient; clustering; microarray
• Language: croatian
• URN:NBN: urn:nbn:hr:168:073060
• 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: 2023-01-13 13:33:30