20.500.12556/RUL-72036 Napovedovanje mesta na RNA v interakciji s proteinom Predicting protein-RNA interaction sites on RNA V magistrskem delu smo razvili modele za napovedovanje mest na RNA v interakciji s proteini, pri čemer smo uporabili metodo skritih Markovih modelov. Določili smo reprezentativne atribute in motive, na podlagi katerih smo nato zgradili modele za vsak posamezen eksperiment. Ugotovili smo, da različni proteini uporabljajo veliko skupnih atributov in motivov za prepoznavo mest interakcije z RNA. Modeli z dvema stanjema (prisotnost interakcije) boljše napovedujejo kot pa modeli s tremi stanji (prisotnost in intenziteta interakcije). Združevanje napovedi modelov posameznih eksperimentov ne izboljša zmogljivosti napovedovanja. Združeni modeli imajo dovolj dobro zmogljivost, da nam lahko služijo za sklepanje o relacijah med posameznimi proteini, in sicer njihovem sodelovanju, tekmovanju ali neodvisnosti. Skriti Markovi modeli predstavljajo primerno metodo za napovedovanje mest interakcij. The main goal of the master's thesis has been to develop prediction models for interactions between RNA and proteins. We have chosen hidden Markov models as our method for modelling and predicting interactions. From our initial data we have extracted representative features and motifs, which we used for building separate models for each experiment. Majority of proteins bind to the same or very similar features and motifs. We have compared the predictive accuracy of models build with two (presence of interaction) and three states (presence and intensity of interaction). Results show that models with two states perform better than models with three states. Merging predictions of multiple single experiment models in combined models, does not improve prediction accuracy. However, combined models perform with high accuracy, and can be used to determine the relations between proteins, such as competition, cooperation and independence with other proteins when interacting with RNA. We have presented hidden Markov models as viable method for predicting interactions between RNA and proteins. skriti Markov model Markove verige Viterbijev algoritem algoritem naprej algoritem nazaj aposteriorno dekodiranje transkripcija RNA protein gen hidden Markov model Markov chain Viterbi algorithm forward algorithm backward algorithm posterior decoding transcription RNA protein gene true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2015-08-17 15:05:06 2015-08-17 15:05:08 2022-08-01 15:16:33 0000-00-00 00:00:00 2015 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 14090 Huc_Aleks_-_Napovedovanje_mesta_na_RNA_v_interakciji_s_proteinom.pdf Huc_Aleks_-_Napovedovanje_mesta_na_RNA_v_interakciji_s_proteinom.pdf 1 DC51423987A169D8880829F0938D7064 6d39378e8ddc857543ed4fec484b1358e31c329e13a95ee54c57b07794a36fa1 5684277a-a1ad-11eb-a523-00155dcfd717 20.500.12556/rul/64bfa091-43be-4f19-b0d4-9e2a4d0e5d16 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=72047 Fakulteta za računalništvo in informatiko 0 0 0