20.500.12556/RUL-185099 Vložitev genomov na podlagi nabora aminokislinskih zaporedij proteinov Embedding genomes from a repertoire of protein amino acid sequences Bakteriofagi so tip virusov, ki napadajo bakterijske celice, pri čemer je uspešnost okužbe odvisna od značilnosti proteinov tako bakteriofaga kot njegovega gostitelja. V magistrskem delu obravnavamo problem vložitve genomov parov bak\-te\-rija-bakteriofag, z namenom napovedovanja interakcije med bakterijo in bakteriofagom, to je, ali bakteriofag vstopi v bakterijo in vpliva na njene celične procese. Ker so genomi zelo različnih dolžin, par genomov bakterija-bakteriofag v interakciji predstavimo z reprezentativnimi pari proteinov, ki so udeleženi v interakciji. Glavno orodje, ki ga pri tem uporabljamo, so proteinski jezikovni modeli, ki so iz aminokislinskega zaporedja proteina sposobni napovedati njegove značilnosti. Vložitev tako dobljenih parov lahko uporabljamo za napovedovanje, ali dana vrsta bakterije in bakteriofaga vstopata v interakcijo ali ne. Najboljši model doseže ROC AUC 0,709. Za izboljšanje uspešnosti modela bi potrebovali več učnih podatkov. Bacteriophages are a type of virus that infect bacterial cells. Their ability to do so depends on both the characteristics of their own proteins and those of the potential host. In this master's thesis, we address the problem of embedding the genomes of bacterium-bacteriophage pairs to predict whether a phage can interact with a bacterial cell by entering and manipulating its functions. As the genomes may be of considerably varying lengths, we represent the host-phage pair interaction with the protein pairs that characterise the interaction with their involvement. To accomplish this, we mainly rely on protein language models, which are capable of predicting properties of a given protein from its amino acid sequence. The embedding of pairs obtained with this method may be used to predict whether a species of bacterium may be vulnerable to a specific bacteriophage infection. Our best model achieves an ROC AUC of 0.709. The model would require more training data to increase its reliability. bioinformatika vložitev genomskih zaporedij bakteriofagi bakterije bioinformatics genome sequence embeddings bacteriophages bacteria true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2026-07-22 14:45:03 2026-07-22 14:45:15 2026-07-31 11:59:45 0000-00-00 00:00:00 2026 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 38452 286578947 Zgonik_Timotej_-_Vlozitev_genomov_na_podlagi_nabora_aminokislinskih_zaporedij_proteinov.pdf Zgonik_Timotej_-_Vlozitev_genomov_na_podlagi_nabora_aminokislinskih_zaporedij_proteinov.pdf 1 3BE3C30540BC2F1EF29BDC2725CF759C 20dfcece3111dd001a13a1d8951329bb00fddd6efbb3168e94624815d4481300 f20be3fe-85ca-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=243289 Fakulteta za računalništvo in informatiko 0 0 0