Klasifikacija mikroba uporabom dubokog učenja

master's thesis

• Title (english): Microbe Classification Using Deep Learning
• Author: Kristijan Pongračić
• Mentor: Mile Šikić (mentor)
• Committee member: Mile Šikić (predsjednik povjerenstva)
• Committee member: Ivica Botički (član povjerenstva)
• Committee member: Krešimir Križanović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Mikrobi su sveprisutni, golim okom nevidljivi organizmi. Oni utječu i međudjeluju s ljudima na više načina. Stoga je važno moći prepoznati i klasificirati mikrobe kako bi otkrili bolesti, propisali liječenje i zadržali zdrav način života. Cilj ovog rada bio je razviti klasifikator koji bi mogao odrediti kojoj klasi pripada sekvencionirano očitanje nekog mikroba. Arhitektura modela temelji se na modelu transformera. Za poboljšanje performansi koriste se dvije različite metode ekstrakcije značajki i četiri tehnike povečanja podataka. Model je testiran na Zymo mock community skupu podataka.

Abstract (english)

Microbes are omnipresent organisms invisible to the naked eye. They affect and interact with humans in multiple ways. The ability to detect and classify microbes is essential to discover diseases, prescribe medication, and keep a healthy lifestyle. The goal of this thesis was to develop a classifier that could predict the class membership of an individual sequenced read that corresponds to some microbe. Model architecture is based on the transformer model. Two different feature extraction methods and four data augmentation techniques are used to improve performance. The model was tested on Zymo mock community dataset.

• Keywords: bionformatika; mikrobi; klasifikacija; duboko učenje; transformer
• Keywords (english): bioinformatics; microbes; classification; deep learning; transformers
• Language: english
• URN:NBN: urn:nbn:hr:168:983166
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 15:55:18