Određivanje varijanti gena u populaciji više jedinki pomoću stojnog učenja

undergraduate thesis

• Title (english): Discovering gene variants in populations using machine learning
• Author: Ema Vlainić
• 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: 2023-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Određivanje i poznavanje alela ključno je za razumijevanje nasljednih osobina organizama,
u području medicinske genetike, poljoprivrede i stočarstva. U našem radu
smo implementirali algoritam koji će pronaći sve različite varijante alela u uzorku
genetskog materijala. Bavimo se određivanjem varijanti gena grupiranjem, koristeći
algoritam hijerarhijskog grupiranja te cilj istraživanja je identificirati različite varijante
gena. Uzorci gena dobiveni su sekvenciranjem, a algoritam grupiranja temelji se na
grupiranju sličnih sekvenci i analizi većeg broja uzoraka. U radu je provedena detaljna
priprema podataka i poravnanje sekvenci kako bi se osigurala kvalitetna analiza.
Različite parametre, poput troška za otvaranje i proširenje praznine, prilikom stvaranja
višestrukog poravnanja sekvenci, prilagođavali smo kako bi se postigla što bolja
kvaliteta grupiranja. Korišten je algoritam hijerarhijskog grupiranja (Agglomerative
clustering) za grupiranje varijanti gena. Uspješno detektiramo više zastupljene gene te
iznosimo problematiku detektiranja manje zastupljenih gena i odbacivanja nevažećih
podataka.

Abstract (english)

Discovering and knowing alleles is key to understanding the hereditary traits of
organism, also in the field of medical genetics, agriculture and cattle breeding. In our
work we have implemented an algorithm that will find all the different allele variants
in the sample of genetic material. We did discovering of gene variants by grouping,
using hierarchical grouping algorithm and the goal of the research is to identify different
variants of genes. The gene samples were obtained by sequencing, and the
clustering algorithm was based on grouping similar sequences and analyzing a large
number of samples. Detailed data preparation and sequence alignment was needed to
ensure quality analysis. We adjusted different parameters, such as the cost to open and
widen the gap, when creating multiple sequence alignment, in order to achieve the best
possible result quality by grouping. Hierarchical grouping algorithm (Aglomerative
clustering) was used for grouping gene variants. We successfully detected genes that
are more represented and we presented the problem of detecting less represented genes
and rejecting invalid data.

• Keywords: gen; alel; strojno učenje; grupiranje; višestruko poravnanje sekvenci; Jupyter; MAFFT; Python
• Keywords (english): gene; allele; machine learning; clustering; multiple sequence alignment; Jupyter; MAFFT; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:310991
• 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: 2023-07-13 10:39:43