Machine learning methods for drug discovery and toxicology

This course will help you to build your own QSAR models for bioactivity or toxicology prediction by the implementation of free python scripts. You will learn how to implement the different steps of the general QSAR workflow: data management and curation, descriptors calculation and selection, different model algorithms and model evaluation metrics and applicability domain.

Where? Valencia (Parque Tecnológico) Registration: Please fill in this form
When? 25 May 2023 from 9-17h and 26 May from 9-15h Information:
Price: 480 €* *Discounts up to 50% for students available

Course overview:

Introduction of basic concepts
  • Regression vs Classification
  • Statistical analysis
  • Overview of different computational approaches: QSAR, SAR, Docking
Data management and curation
  • Dataframe importation and analysis
  • Molecule characterization
  • Chemical and biological data curation
QSAR model development
  • General workflow
  • Calculation of molecular descriptors
  • Train/test splitting
  • Feature reduction and scaling
  • Algorithm selection
  • Hyperparameter optimization
  • Model metrics and validation
  • Applicability domain
  • External prediction