Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Machine Learning in Drug Discovery and Cheminformatics
Rating: 4.6 out of 5(30 ratings)
135 students

Machine Learning in Drug Discovery and Cheminformatics

Apply Python, AI, and Machine Learning in Cheminformatics for Drug Discovery
Created byKhalid Mostafa
Last updated 5/2026
English
English [Auto],

What you'll learn

  • Apply Python programming techniques in drug design and chemistry.
  • Apply Machine learning techniques to real drug discovery problems : Learn how to predict pIC50, toxicity, ADMET, and other molecular properties.
  • Master Chemical Data Preparation and Featurization : Extract, manipulate, and generate chemically relevant molecular representations (e.g, SMILES, fingerprints)
  • Build complete QSAR and prediction models from scratch : Learn to preprocess chemical data, generate descriptors and fingerprints, train ML models.
  • Create and deploy your own end-to-end cheminformatics project : Build a complete project (data → model → predictions → deployment).

Course content

9 sections • 65 lectures • 3h 3m total length

  • Course Objectives1:01

    Explore chemi-informatics and drug discovery by learning molecular representations, mastering Python for computational projects, and applying machine learning, culminating in a practical project to kickstart your own drug discovery work.

  • Introduction2:54
  • Basics of Molecular Representations2:51

Requirements

  • No-Preq Knowledge Required: We start from absolute basics—no programming or chemistry background needed.

Description

Welcome to Machine Learning for Drug Discovery & Cheminformatics


This course is designed for all levels, from beginners who are new to programming and machine learning, to intermediate learners who want to apply AI in real drug discovery workflows.

You will learn how to combine Python, Machine Learning, AI, and Cheminformatics to build practical solutions used in modern computational drug discovery.


What You Will Learn

  • Python fundamentals for scientific computing

  • Data handling and preprocessing

  • Molecular representations (SMILES, molecular fingerprints)

  • Building and evaluating Machine Learning models

  • Understanding R², RMSE, and model performance

  • Virtual screening workflows

  • ADMET filtering concepts

  • How to build real-world drug discovery projects

Practical, Project-Based Approach

This is not a theory-only course.

You will:

  • Build real Machine Learning Project in Cheminformatics models

  • Build real QSAR models

  • Generate molecular fingerprints using RDKit

  • Perform virtual screening on compound libraries

  • Apply AI to predict biological activity

    By the end of the course, you will understand how machine learning is applied in real computational drug discovery pipelines.

Who This Course Is For

  • Pharmacy students and Pharmacists

  • Chemistry and life science students

  • Bioinformatics and cheminformatics learners

  • Data science students interested in healthcare

  • Anyone who wants to apply AI in drug discovery


After This Course

You will be able to:

  • Start your own drug discovery ML projects

  • Understand published AI drug discovery papers

  • Apply machine learning to molecular datasets

  • Build a strong foundation for advanced research

Who this course is for:

  • This course is designed for: Programmers & Data Scientists curious about applying their skills to drug discovery and chemistry .
  • Chemists , Bioinformaticians & Pharmacists wanting to integrate machine learning into their research.
  • Students & Researchers in life sciences looking to leverage AI in their work.
  • Complete Beginners interested in the intersection of AI and healthcare
  • No prior experience in programming, chemistry, or machine learning is required. We start from absolute fundamentals and build up step-by-step.

Report abuse