Deep Learning for Drug Discovery, Property Prediction with Neural Networks on Raw Molecular Graphs

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/256629
Download file(s):
File Description SizeFormat 
256629.pdfFulltext1.15 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: Deep Learning for Drug Discovery, Property Prediction with Neural Networks on Raw Molecular Graphs
Authors: Lindelöf, Edvard
Abstract: The lengthy and expensive process of developing new medicines is a driving force in the development of machine learning on molecules. Classical approaches involve extensive work to select the right chemical descriptors to use as input data. The scope of this thesis is neural network architectures learning directly on raw molecular graphs, thereby eliminating the feature engineering step. The starting point of experimentation is a reimplementation of the previously proposed message passing neural networks framework for learning on graphs, analogous to convolutional neural networks in how it updates node hidden states through aggregation of neighbourhoods. Three modifications of models in this framework are proposed and evaluated: employment of a recently introduced activation function, a neighbourhood aggregation step involving weighted averaging and a message passing model incorporating hidden states in the graph’s directed edges instead of its nodes. The resulting models are hyperparameter optimized using a parallelized variant of Bayesian optimization. Comparison to literature benchmarks for machine learning on molecules shows that the new models are competitive with state-of-the-art, outperforming it on some datasets.
Keywords: Livsvetenskaper;Datavetenskap (datalogi);Bioinformatik (beräkningsbiologi);Datorsystem;Life Science;Computer Science;Bioinformatics (Computational Biology);Computer Systems
Issue Date: 2019
Publisher: Chalmers tekniska högskola / Institutionen för biologi och bioteknik
Chalmers University of Technology / Department of Biology and Biological Engineering
URI: https://hdl.handle.net/20.500.12380/256629
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.