Probabilistic Generative Models for Automatic Guided Drug Discovery

Research output: Book/ReportPh.D. thesis

9 Downloads (Pure)

Abstract

This thesis encompasses five distinct contributions presented as manuscripts, accompanied by two novel pieces of work detailed in Chapters 3 and 4. The latter has not been previously disseminated in any publications. The first chapter serves as an introduction to the field of computational drug discovery, offering an overarching perspective on the problem we aim to address and laying the groundwork for subsequent chapters.

In the second chapter, we provide a brief overview of Bayesian optimization, Gaussian Processes, and the concept of Pareto optimality. The third chapter introduces a novel concept: Distance aligning in latent spaces of Variational Autoencoders. Bringing together insights from the initial three chapters, Chapter 4 unveils the comprehensive model for automatic guided drug discovery, complemented by simulated experimental results.
Original languageEnglish
PublisherTechnical University of Denmark
Number of pages142
Publication statusPublished - 2024

Fingerprint

Dive into the research topics of 'Probabilistic Generative Models for Automatic Guided Drug Discovery'. Together they form a unique fingerprint.

Cite this