Dijagnostika bolesti na temelju podataka o ekspresiji gena

undergraduate thesis

• Title (english): Diagnostics Based on Gene Expression Data
• Author: Marija Perković
• Mentor: Krešimir Križanović (mentor)
• Committee member: Krešimir Križanović (predsjednik povjerenstva)
• Committee member: Josipa Lipovac (član povjerenstva)
• Committee member: Rafael Josip Penić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Analiza ekspresije gena ključna je za razumijevanje molekularnih mehanizama koji stoje iza različitih tipova karcinoma. Ona omogućava identifikaciju specifičnih gena čija je aktivnost povezana s nastankom i razvojem bolesti, što je od presudne važnosti za dijagnozu, prognozu i terapiju. U ovom radu, istražili smo primjenu različitih tehnika nadziranog i nenadziranog strojnog učenja na skupovima podataka za klasifikaciju leukemije i raka dojke koristeći podatke dobivene analizom ekspresije gena. Kroz analizu, implementaciju i evaluaciju algoritama logističke regresije, stroja potpornih vektora (SVM), dubokog učenja i grupiranja, istražili smo njihov doprinos u klasifikaciji karcinoma koristeći programske biblioteke sklearn i keras. Uspješno smo klasificirali različite oblike karcinoma te su naši rezultati bili u skladu s očekivanim. Ovaj rad pruža uvid u primjenu strojnog učenja u medicini te otvara nova područja za daljnja istraživanja.

Abstract (english)

Gene expression analysis is crucial for understanding the molecular mechanisms underlying various types of cancer. It enables the identification of specific genes whose activity is associated with the onset and development of the disease, which is essential for diagnosis, prognosis, and therapy. In this study, we explored the application of different supervised and unsupervised machine learning techniques on datasets for the classification of leukemia and breast cancer using data obtained from gene expression analysis. Through the analysis, implementation, and evaluation of algorithms such as logistic regression, support vector machines (SVM), deep learning, and clustering, we investigated their contribution to cancer classification using the sklearn and keras libraries. We successfully classified different forms of cancer, and our results were consistent with expectations. This paper provides insight into the application of machine learning in medicine and opens new areas for further research.

• Keywords: ekspresija gena; logistička regresija; stroj potpornih vektora; duboko učenje; grupiranje
• Keywords (english): gene expression; logistic regression; support vector machine; deep learning; clustering
• Language: croatian
• URN:NBN: urn:nbn:hr:168:555223
• 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: 2024-10-12 21:49:13