Iterativno traženje fraza i statistika semantičkog indeksiranja

master's thesis

• Author: Silvestar Mavrek
• Mentor: Pavle Goldstein (mentor)
• Committee member: Eduard Marušić-Paloka (predsjednik povjerenstva)
• Committee member: Pavle Goldstein (član povjerenstva)
• Committee member: Nela Bosner (član povjerenstva)
• Committee member: Marko Vrdoljak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Mathematics); Zagreb
• Defense date and country: 2019-03-01, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

Potreba za točnim, automatiziranim metodama klasifikacije nastavlja se povećavati kako napredak biotehnologije otkriva nove proteine. U radu je provedeno nekoliko analiza klasifikacije proteina u proteinske familije, koristeći vrlo jednostavan pristup preuzet iz semantičkog indeksiranja. Naglasak je bio na metodama identifikacije diskriminativnih uređenih četvorki aminokiselina s ciljem što boljeg razlikovanja familija proteina. Uz vrlo malu razinu prethodno iskorištenog biološkog znanja dobiveni su iznenađujuće dobri rezultati.

Abstract (english)

The need for accurate, automated protein classification methods continues to increase as advances in biotechnology uncover new proteins. We carried out protein classification by several methods, using a very simple approach taken from semantic indexing. The emphasis was on identifying discriminating blocks of amino acids to distinguish between various protein families. Our classification results are surprisingly good, especially considering no expert knowledge was used in the process.

• Keywords: automatizirane metode klasifikacije; klasifikacija proteina
• Keywords (english): automated classification methods; protein classification
• Language: croatian
• URN:NBN: urn:nbn:hr:217:392336
• Study programme: Title: Mathematical Statistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2019-08-29 12:50:20