Odabir najinformativnijih genomskih regija za određivanje ishodišnih stanica melanoma metodama strojnog učenja

master's thesis

• Title (english): Selection of the most informative genomic regions for the determination of melanoma cell-of-origin using machine learning methods
• Author: Marin Volarić
• Mentor: Rosa Karlić (mentor)
• Committee member: Rosa Karlić (predsjednik povjerenstva)
• Committee member: Sven Jelaska (član povjerenstva)
• Committee member: Tomislav Ivanković (član povjerenstva)
• Committee member: Kristian Vlahoviček (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Biology); Zagreb
• Defense date and country: 2020-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Biology

Abstract

Iako najmanje uobičajeni oblik karcinoma kože melanom je njegov najsmrtonosniji oblik karakteriziran
visokom invazivnošću i velikim metastatskim potencijalom. Metastatski potencijal melanoma pokazao se
problemom u djelu bolesnika koji nemaju očito mjesto porijekla primarnog tumora, pokazano najjačeg
prediktora ponašanja tumora. Novi pristupi temeljeni na metodama strojnog učenja bili su uspješni u
identificiranju stanice porijekla u različitih vrsta karcinoma isključivo korištenjem karakterističnih profila
putničkih mutacija i somatskih epigenomskih profila. Cilj ovog istraživanja bio je istražiti može li se stanica
podrijetla melanoma odrediti s djelom genomskih regija koji su korišteni u prethodnim studijama. Istražili
smo može li upotreba analize glavnih komponenti smanjiti broj regija koje modeli strojnog učenja trebaju
koristiti da bi se uspješno predvidjelo stanično podrijetlo melanoma. Ovdje pokazujemo da je čak 10%
veličine profila korištene u prethodnim istraživanjima dovoljno za predviđanje melanomne stanice
podrijetla s velikom točnošću. Nadalje, otkrili smo da najinformativnije regije imaju veći proporcionalni
udio prepisane sekvence i imaju relativno malo otkrivenih poznatih mutacija koje su povezane s razvojem
melanoma. Ti nalazi otkrivaju potencijalni put do novih istraživanja dijagnostičkog potencijala metoda
strojnog učenja ne samo za melanom, već i za druge vrste raka.

Abstract (english)

Although being the least common form of skin cancer melanoma is by far its deadliest form characterized
by high invasiveness and a large metastatic potential. The metastatic potential of melanoma proves to be
a problem in a fraction of patients who have no obvious site of primary tumor which is the strongest
predictor of tumor behavior. Novel approaches based on machine learning methods have been successful
in identifying different cancer types cells-of-origin solely by using cancer passenger mutation and somatic
cell epigenomic regional profiles. The aim of this research was to investigate whether melanoma cell-oforigin can be determined with a fraction of genomic regions used in previous studies. We investigated
whether the use of principal component analysis can reduce the number of regions that machine learning
models need to use to successfully predict melanoma cell-of-origin. Here we show that with even 10% of
the profile size used in previous research is enough to predict melanoma cell-of-origin with high accuracy.
Moreover, we also found that the best regions have a larger proportional fraction of transcribed sequence
and have relatively few of discovered known mutations which are connected with melanoma
development. Those findings reveal a potential path to new research into the diagnostic potential of
machine learning methods not only for melanoma but for other cancer types.

• Keywords: melanom; strojno učenje; epigenetika; bioinformatika; PCAWG
• Keywords (english): melanoma; machine learning; epigenetics; bioinformatics; PCAWG
• Language: croatian
• URN:NBN: urn:nbn:hr:217:444505
• Study programme: Title: Molecular Biology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra molekularne biologije (magistar/magistra molekularne biologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access; Embargo expiration date: 2021-07-16
• Created on: 2020-07-20 12:13:21