Simulacija de-novo sekvenciranja kratkih proteina pomoću masenog spektrometra, koristeći tehnike dubokog učenja

undergraduate thesis

• Title (english): Simulating Short Protein De-novo Sequencing by Mass Spectrometry Using Deep Learning
• Author: Andrija Arbanasić
• Mentor: Krešimir Križanović (mentor)
• Committee member: Krešimir Križanović (predsjednik povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Filip Bosnić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sekvenciranje proteina je jedan od glavnih problema kojima se bioinformatika bavi. Ovaj rad se bavi eksperimentiranjem sa dubokim neuronskim mrežama u svrhu rješavanja tog problema. Sekvenciranje smo pokušali ostvariti pomoću konvolucijskih modela. Modeli su implementirani u Python-ovoj biblioteci PyTorch te su trenirani na podacima generiranim pomoću simulatora masenog spektrometra. Simulator je također implementiran u Pythonu. U radu su prikazani teorijska pozadina sekvenciranja proteina i dubokih neuronskih mreža te je opisana implementacija simulatora i modela.

Abstract (english)

Protein sequencing is one of Bioinformatic's main issues. This paper tries to tackle the issue by experimenting with deep neural networks. More precisely, we were experimenting with convolutional neural network models. Models were trained on data which was generated using mass spectrometry simulator. Models and simulator were both implemented in Python. Additionally, models were implemented with the help of open source Python library, PyTorch. Paper showcases theory of protein sequencing and deep neural networks. Furthermore it describes implementation of convolutional models and mass spectrometry simulator.

• Keywords: sekvenciranje proteina; masena spektrometrija; duboko učenje; klasifikacija; PyTorch
• Keywords (english): protein sequencing; mass spectrometry; deep learning; classification; PyTorch
• Language: croatian
• URN:NBN: urn:nbn:hr:168:029089
• 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 20:00:28