Artificial Intelligence for Drug Discovery
Artificial Intelligence (AI) and Machine Learning (ML) are transforming pharmacology by enabling faster drug discovery, repurposing of FDA-approved medicines, and identification of therapeutic targets.
This fully online course trains health professionals, students, and researchers to build QSAR models, ML pipelines, and predictive applications using real datasets of African natural products and FDA-approved drugs.
Course Content
Module 1 – Introduction and Context
- Global challenges in drug discovery: antimicrobial resistance, neglected diseases, costs and timelines
- Why AI is a game-changer in pharmacology and drug repurposing
- Success stories of AI-driven drug discovery
- Core concepts: QSAR, polypharmacology, molecular targets
Module 2 – Python and Data Science Fundamentals
- Python for pharmacology: variables, functions, control structures
- Data manipulation with Pandas and NumPy
- Data visualization with Matplotlib and Seaborn; simple dashboards
- ML basics: Random Forest, XGBoost, evaluation metrics, training/testing models
Module 3 – Hands-On Projects with Real Data
Project 1 – Drug Discovery for Neglected Diseases
- Dataset: curated African natural products database
- Goal: identify molecules with biological potential
- Methods: QSAR, Random Forest, XGBoost
- Output: predictive model for compound screening
Project 2 – Repurposing FDA-Approved Drugs
- Dataset: FDA-approved drugs
- Goal: find candidates for new therapeutic targets
- Methods: supervised ML, multi-target analysis
- Output: predictive pipeline for drug repurposing
Project 3 – Polypharmacology and Multi-Target Drug Design
- Goal: design strategies for compounds acting on multiple targets
- Methods: multi-target ML, protein–ligand interaction analysis
- Output: predictive model prioritizing compounds with polypharmacological effects
Module 4 – Tools and Applications for Pharmacology
- Building QSAR and ML pipelines
- Developing interactive drug prediction apps in Python
- Integrating natural products, FDA-approved drugs, and molecular target data
Module 5 – Application and Communication
- Presenting results to researchers and lab managers
- Visualizing promising compounds and prioritizing experimental testing
- Strategies for publishing predictive data and reports
Module 6 – Preparing for the International Market (Premium Plan)
- Crafting a competitive CV and cover letter for international roles in AI applied to pharmacology
- Optimizing professional profiles (LinkedIn, GitHub)
- Preparation for technical and behavioral interviews
- Strategies to seek opportunities in pharmaceutical companies, biotech startups, UK, Europe, Canada, and Australia
- Strategic support for up to 5 job applications
- Personalized recommendation letter signed by Prof. Dr. Alexandre Cobre
Note: Module 6 provides career support but does not guarantee job placement or visa approval.
Instructor
The course is led by Prof. Dr. Alexandre de Fátima Cobre, a Mozambican scientist affiliated with The University of Manchester (UK), specialist in AI applied to drug discovery, collaborator of the WHO, and founder of MozBioMed.AI.
- Ranked among the Top 3 Pharmaceutical Scientists in Brazil (2025)
- Author of over 50 international publications
- Recognized for pioneering AI-based discoveries in COVID-19
Basic Plan – £175 (15,000 MZN)
- Complete course + practical projects + international certificate
- Discounted price (one-time payment): £165 (14,000 MZN)
- Installments: 3x £60 (total £180 / 15,000 MZN)
Premium Plan – £580 (50,000 MZN)
- Everything in the Basic Plan + full Module 6
- Strategic support for the international job market: CV, GitHub, recommendation letter, guidance on job applications and visa
- Discounted price (one-time payment): £550 (47,000 MZN)
- Installments: 5x £120 (total £600 / 50,000 MZN)
Key Differentiators
- 100% online, with pre-recorded lessons
- Hands-on projects with real datasets of natural products and FDA-approved drugs
- Development of AI apps for compound screening and efficacy prediction
- Flexible pace: complete in 3–6 weeks for dedicated learners
- International certificate of completion
- Career-oriented preparation for the global AI-driven drug discovery market
