Prediction of ADME properties using curriculum learning

Entity: Universitat Rovira i Virgili (URV)

Confidenciality: No

Education area(s): Ciència de Dades Biomèdiques

APS: No

Title in different languages: Prediction of ADME properties using curriculum learning

Abstract: This thesis will study the effect that such a curriculum sampler has when trying to predict a variety of molecular properties, using datasets describing absorption, distribution, metabolism and excretion of various samples. Making a quantitative analysis of how models trained in different configurations compare. The results show that the ordering of samples during training is a relevant factor in how well a model learns to generalize, although the type of molecular complexity measures depends on the application.

Subject: Farmacocinètica

Academic year: 2023-2024

Language: en

Work's public defense date: 2024-09-12

Subject areas: Health sciences

Student: Lagemann, Jens Alexander

Work's codirector: Vellido, Alfredo

Department: Enginyeria Informàtica i Matemàtiques

Creation date in repository: 2025-03-03

Keywords: ADME, MPNN, Curriculum Learning

Title in original language: Prediction of ADME properties using curriculum learning

Access Rights: info:eu-repo/semantics/openAccess

Project director: König, Caroline