magistrsko delo
Sara Kužnik (Author), Tomaž Curk (Mentor)

Abstract

Interakcije med proteini in RNA igrajo pomembno vlogo pri številnih celičnih procesih. Komplekse 3D proteina in RNA lahko določamo eksperimentalno, kar pa je zahtevno in počasno. S hitrejšimi računskimi metodami, čeprav so te manj natančne, lahko usmerjamo eksperimentalno preverjanje hipotez o mestu interakcij. V magistrskem delu poskusimo najprej napovedati mesta interakcij na ravni aminokislin, ki sestavljajo protein v kompleksu protein-RNA. Za vsako aminokislino smo pridobili dve napovedi: napoved, ali je aminokislina v interakciji z RNA, ter še natančnejšo napoved, katera mesta aminokisline so v interakciji z RNA. Za napovedi na posamezni aminokislini smo uporabili 3D konvolucijsko nevronsko mrežo. Razvili smo tudi metodo, ki napovedi na aminokislinah združi v prostorsko napoved mest interakcij v strukturi 3D proteina in RNA. Uspešnost metode ocenimo s klasifikacijsko točnostjo in ROC AUC, izmerjenim na posameznih 3D kompleksih proteina in RNA. Povprečni ROC AUC, izmerjen na posameznih strukturah protein-RNA v testni množici, je 0.79, povprečni ROC AUC na dodatni, neodvisni testni množici pa je 0.74. Opazimo tudi, da natančnejše napovedi na posameznih aminokislinah privedejo do boljših končnih napovedi.

Keywords

bioinformatika;konvolucijske nevronske mreže;interakcije med proteini in RNA;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [S. Kužnik]
UDC: 004.8:575.112(043.2)
COBISS: 41001731 Link will open in a new window
Views: 804
Downloads: 197
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Prediction of interactions between proteins and RNA with deep 3D convolutional neural networks
Secondary abstract: Protein–RNA interactions play an important role in a wide variety of cellular processes. We can determine protein-RNA complexes experimentally, but that is a difficult and slow process. Even though their accuracy is lower than that of experimental observations, faster computational predictions can be sufficiently accurate to guide experimental validation. In this thesis, we first try to predict the site of interactions on amino acids, which are the building block of proteins in the protein-RNA complex. For every amino acid we infer two predictions, we predict whether the amino acid is in interaction with the RNA and also which parts of the amino acid are in interactions with the RNA. For predictions on amino acids, we implemented a 3D convolutional neural network. We also developed a method to combine these predictions on amino acids into a spacial prediction of interactions in 3D protein and RNA complexes. We estimate the performance of our method with classification accuracy and ROC AUC measured on every 3D protein and RNA complex. The average AUC estimated on Protein-RNA complexes in the test set equals 0.79, whereas the average ROC AUC in an additional, independent test set equals 0.74. We also observe that more specific predictions on amino acids give better final predictions.
Secondary keywords: bioinformatics;convolutional neural networks;protein-RNA interactions;computer science;computer and information science;master's degree;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 75 str.
ID: 12189492