Bc. Filip Jozefov

Bachelor's thesis

Machine learning techniques of mass spectra prediction

Machine learning techniques of mass spectra prediction
Abstract:
Táto bakalárska práca predstavuje komplexnú štúdiu uplatňovania hlbokých neuronových sieti na predpovedanie hmotnostnej spektrometrie z molekulárnych štruktúr. Navrhujeme a vyhodnocujeme tri modely hlbokého učenia založené na grafoch: Graph Convolutional Neural Networks (GCN), Graph Attention Networks (GAT) a TransformerConv s obojsmernou vrstvou. Tieto modely využívajú podobnosť grafov ú štruktúru …more
Abstract:
This thesis presents a comprehensive study of applying deep learning models for predicting mass spectrometry from molecular structures. We propose and evaluate three graph-based deep learning models: Graph Convolutional Neural Networks (GCN), Graph Attention Networks (GAT), and Graph Convolutional Transformers (TransformerConv) with a bidirectional layer. These models exploit the inherent graph structure …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 18. 5. 2023

Thesis defence

  • Date of defence: 29. 6. 2023
  • Supervisor: Mgr. Aleš Křenek, Ph.D.
  • Reader: RNDr. Tomáš Rebok, Ph.D.

Citation record

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky