Računalna metoda za predviđanje mjesta proteinske interakcije

doctoral thesis

• Title (english): Computational method for prediction of protein-protein interaction sites
• Author: Mile Šikić
• Mentor: Branko Jeren (mentor)
• Mentor: Kristian Vlahoviček (komentor)
• Committee member: Sven Lončarić (član povjerenstva)
• Committee member: Branko Jeren (član povjerenstva)
• Committee member: Kristian Vlahoviček (član povjerenstva)
• Committee member: Bojana Dalbelo-Bašić (član povjerenstva)
• Committee member: Mladen Kos (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronic Systems and Information Processing); Zagreb
• Granter: Ruđer Bošković Institute; Zagreb
• Defense date and country: 2008-09-29, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Electronics
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Data Processing
• Scientific / art field, discipline and subdiscipline: INTERDISCIPLINARY AREAS OF KNOWLEDGE; Biotechnology in Biomedicine (natural science, biomedicine and healthcare, bioethics area
• Universal decimal classification (UDC): 621.3 - Electrical engineering ; 60 - Biotechnology. Genetic engineering. Products of cloning ; 004 - Computer science and technology. Computing. Data processing

Abstract

Predmet je disertacije predviđanje mjesta proteinske interakcije na osnovi informacija iz slijeda i strukture proteina koji sudjeluju u interakciji. U radu se mjesto interakcije definira kao pomični prozor od 9 ostataka, u kome je barem središnji ostatak mjesto dodira. Ostatak se definira da je u dodiru ako se njegov najbliži atom nalazi na manje od 6 A od najbližeg atoma ostatka koji pripada susjednom lancu. Na osnovi postojećeg skupa za učenje klasifikacija i provjera rezultata provedena je koristeći metodu slučajnih šuma i OR metode. OR metode, razvijene u ovom radu se temelje na kombiniranju klasifikatora i poboljšanju F-mjere pri radu s neuravnoteženim podacima. Za predviđanje mjesta interakcije iz prostorne strukture proteina uz slijed upotrijebljena su i ova svojstva: nepolarna ASA, maksimalna ukopanost, srednja ukopanost, minimalna izbočenost i hidrofobnost. Rezultati dobiveni u ovome radu za predviđanje na osnovi samo slijeda su bolji od dosadašnjih, a rezultati na osnovi podataka iz slijeda i prostorne strukture u rangu su rezultata najboljih metoda u ovom području. Kroz analizu na 9 UCI skupova podataka primjena OR metode pokazala je poboljšanje rezultata. Na kraju rada, primjenom metode predviđanja na osnovi slijeda i prostorne strukture, predviđena su mjesta interakcije na Ras i C-Raf proteinima te je metodama prianjanja i molekularne dinamike dobivena struktura Ras-Raf kompleksa.

Abstract (english)

Prediction of protein-protein interaction sites using information from protein sequence and 3D structure is purposed in this thesis. The protein interaction site is defined as a slide window of 9 residues in which at least central residue is in contact with other chains. The aminoacid is in contact if its distance to the nearest heavy atom of a neighbour chain is less then 6 A. In this work it is used an existing non-redundant dataset which is classified using Random Forest and OR method. OR method, purposed in this thesis, is a method based on combining classifiers and improvement of F-measure in cases when data is imbalanced. The predictions are based on sequence alone or combination of sequence and 3D structure features. The following 3D features are used: sequence, non-polar ASA, maximal depth index, average depth index, minimal protrusion and hydrophobicity. The results obtained using prediction based only on sequence information are better for other in the field, while the results based on both sequence and 3D structure information is the rank of results of other authors. In addition OR method was tested on 9 UCI datasets, where it achieves improvement of the results comparing with methods based only on individual classifiers. Furthermore, using the information about the potential binding site determined by above mentioned methods the wild type Ras and the RBD (Ras Binding Domain) of C-RAF1 were docked (by specifying the predicted binding site as a centre). Finally the obtained complex was energy minimised and subjected to molecular dynamics.

• Keywords: proteinska međudjelovanja; slijed aminokiselinskih ostataka; prostorna struktura; metoda slučajnih šuma; klasifikacija; F-mjera; neuravnoteženi podaci; prianjanje
• Keywords (english): protein – protein interactions; sequence; 3D protein structure; Radnom Forest; Classification; F-measure; imbalanced data; protein docking
• Language: croatian
• URN:NBN: urn:nbn:hr:168:631838
• Study programme: Title: Electrical Engineering and Computing; Study programme type: university; Study level: postgraduate; Academic / professional title: Doktor znanosti elektrotehnike i računarstva (Doktor znanosti elektrotehnike i računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-05-26 06:37:43