How to develop a QSAR model using Python

Learn how to develop your own QSAR models using Python scripts. Understand the theoretical background of the modelling workflow and explore tools to implement them with customized Python scripts.

Machine learning methods for drug discovery and toxicology: How to develop a QSAR model using Python

This course will provide you with the tools and knowledge necessary to develop your own QSAR models for bioactivity or toxicology prediction. You will learn to use open libraries to create your customized Python scripts, enabling you to construct these models effectively. You will learn the theoretical background about QSAR modelling and the general workflow to develop the model: including the rationale of the different steps and the tools to implement them. Covering data management and curation, calculation and selection of molecular descriptors, different machine-learning algorithms, the statistical evaluation of the models and the evaluation of the applicability domain.

This online course allows you to learn at your own pace. The course remains accessible at all times, giving you the flexibility to register whenever you choose. Once enrolled, you’ll have a four-month window to complete the course. In our platform, you will have access to recorded lessons, text explanations, interactive Python exercises, and other resources. This is a practical course with several practical exercises that will finish with a project when you will develop a whole QSAR model by yourself. But you are not alone; a tutor from ProtoQSAR will follow your advance on the platform, give you feedback on your assignments and will be available by e-mail. Additionally, you will be able to interact with your colleagues and instructors through internal forums and chats, and it will be a series of live videoconferences to clarify doubts.

For more details, please download the course content.

Hands-on course of QSAR with Python

A very practical course were you will develop your own models following

Course summary

Introduction of basic concepts

  • Overview of different computational approaches
  • QSAR model workflow
  • Regression versus classification
  • Statistical analysis of models

Basic chemoinformatics techniques in Python

  • Import and analysis of data frames
  • Characterization of molecules
  • Preservation of chemical and biological data

QSAR model development

  • Data collection and preservation
  • Molecular descriptor calculation
  • Training/test division
  • Feature reduction and scaling
  • Algorithm selection
  • Hyperparameter optimization
  • Metrics and model validation
  • Domain applicability
  • External prediction

Prerequisites

Practical information

Mode: Online

When: Always open (4 months to complete)

Estimated hours: 60

Pre-registration: Fill in this form

Contact: training@protoqsar.com

Language: English

Price: 600€ (VAT included)*

* 300€ for students (requisites in form)