Machine Learning voor Geavanceerde Chemische Analyse en Structuurherkenning in de Ontdekking van Geneesmiddelen

The essence of successful Quantitative Structure-Activity Relationship (QSAR) modeling for drug discovery lies in the availability of diverse and high-quality data. However, acquiring such data in the pharmaceutical industry is not only challenging and expensive but also constrained by its proprietary nature, limiting sharing opportunities. To overcome these challenges, this dissertation introduces innovative methods aimed at accessing literature and cross-pharma data, thereby enabling the utilization of larger datasets for the training of machine learning models. An integral component of this research involves the introduction of the Optical Chemical Structure Recognition (OCSR) technique, known as ChemGrapher. While showcasing its potential, a notable limitation comes to light, emphasizing the indispensability of atom-level entity labels. These labels, providing precise details about the localization of individual elements within chemical compounds, prove essential for effective training. The treatment of atom-level entities as discrete objects highlights the convergence of OCSR with object detection methodologies, underlining the significance of identifying and categorizing individual atomic elements within chemical depictions. The subsequent sections of this dissertation delve into the continual progress and enhancement of object detection methods, directly contributing to the refinement and advancement of ChemGrapher.