prikaz prve stranice dokumenta Predviđanje strukture proteina modelom AlphaFold 2
  Download
PDF 8.49 MB
undergraduate thesis
Predviđanje strukture proteina modelom AlphaFold 2
2022. urn:nbn:hr:190:457607
Jelušić, Darijan
University of Rijeka
Faculty of Engineering
Department of Computer Engineering

Cite this document

Jelušić, D. (2022). Predviđanje strukture proteina modelom AlphaFold 2 (Undergraduate thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:457607

Jelušić, Darijan. "Predviđanje strukture proteina modelom AlphaFold 2." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:457607

Jelušić, Darijan. "Predviđanje strukture proteina modelom AlphaFold 2." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:457607

Jelušić, D. (2022). 'Predviđanje strukture proteina modelom AlphaFold 2', Undergraduate thesis, University of Rijeka, Faculty of Engineering, accessed 30 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:457607

Jelušić D. Predviđanje strukture proteina modelom AlphaFold 2 [Undergraduate thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2022 [cited 2024 November 30] Available at: https://urn.nsk.hr/urn:nbn:hr:190:457607

D. Jelušić, "Predviđanje strukture proteina modelom AlphaFold 2", Undergraduate thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:190:457607

Please login to the repository to save this object to your list.
Metadata
TitlePredviđanje strukture proteina modelom AlphaFold 2
Title (english)Protein structure prediction using AlphaFold 2 model
AuthorDarijan Jelušić
MentorGoran Mauša (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
Rijeka
Defense date and country2022-09-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom radu predstavljen je princip rada programskog alata AlphaFold 2, s objašnjenjima primjene genetskog i strukturnog pretraživanja proteina, Evoformer transformatora koji izvlači znanje iz reprezentacija MSA i parovima te strukturnog modula koji predviđa trodimenzionalne koordinate svih atoma strukture na temelju reprezentacija iz Evoformera. Objašnjene su i metrike RMSD, GDT i lDDT koje služe za evaluiranje sličnosti struktura. Dodatno, praktično je istražena mogućnost predviđanja tercijarne strukture za odabrani skup sekvenci duljina između 36 i 223 aminokiseline korištenjem računalnog klastera Isabella. Dobivene strukture imale su pouzdanost između 19,21 i 99,61 GDT, s vremenima izvršavanja između 35 i 53 minute.
Abstract (english)
This paper presents the core principles of the AlphaFold 2 model, with explanations of genetic and structural protein search, the Evoformer transformer used for extracting knowledge from MSA and pair representations, and the Structure module which predicts 3D coordinates of all atoms based on the Evoformer’s representations. Structure similarity metrics RMSD, GDT and lDDT are also explained. Additionally, the viability of tertiary structure prediction for a select set of sequences between 36 and 223 amino acids is explored using the Isabella computer cluster. The GDT scores of the resulting structures range between 19.21 and 99.61, with computing times between 35 and 53 minutes.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:457607
Study programmeTitle: Computer Engineering
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 resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2022-09-20 20:07:49