Overview

ABOUT THE COURSE:This 12-week course, Artificial Intelligence in Drug Discovery and Development, is designed to equipparticipants with the knowledge and skills to leverage AI in the realm of drug discovery anddevelopment which itself is a daunting, expensive, time-consuming, and resource intensive task. Theprogram starts with foundational concepts, including the drug discovery pipeline and core AI/MLtechniques, progressing to cutting-edge topics like predictive modeling, generative AI-based drugdesign, and drug repurposing. Alongside theoretical lectures, participants will gain practical experiencewith widely used AI tools and software through hands-on tutorials. The course culminates in a miniproject, offering hands-on experience and enabling participants to apply AI-driven methodologies toreal-world challenges in drug discovery.INTENDED AUDIENCE: Pharmacy professional, computational biologists,computational chemists, BiotechnologistsPREREQUISITES: The participants should have basic knowledge of biology, chemistry, and pharmacology. The keen interest in the domain of drug discovery and a basic introduction to Python programming language is desirable.INDUSTRY SUPPORT: Pharmaceutical industry such as TCS Life Science, Dr.Reddy's Laboratories, Reliance Life Science, Suven Life Sciences Ltd

Syllabus

Week 1: Basics of drug discovery pipeline
1. Drug discovery and development
2. Overview of drug discovery workflows
3. Drug design strategies
4. Conventional methods for drug discovery
5. Riddles in drug discovery
Week 2:Introduction to AI in drug discovery and development
1. History and evolution of AI in drug discovery
2. Overview of AI technologies
3. Key applications of AI across the pipeline
4. Available AI tools and platforms
5. Advantages of AI integration in drug discovery
Week 3:Fundamentals of AI and ML techniques
1. Introduction to machine learning concepts
2. Overview of neural networks
3. Feature engineering and data preprocessing
4. Evaluation metrics for AI models
5. Introduction to Python libraries for AI in drugdiscovery
Week 4:AI in target identification, prediction and validation
1. Introduction to biological targets
2. Basics of target identification and validation
3.Omics data integration for target discovery
4. Binding site and protein structure prediction with AI
5. Hands-on tutorial
Week 5:AI in high throughput virtual screening and leadidentification
1. Introduction and approaches to virtual screening
2. AI tools for virtual screening
3. AI Assisted Molecular Docking
4. Workflow of high-throughput virtual screening
5. Hands-on tutorial
Week 6:AI in lead optimization and drug-target interaction
1. Basics of lead optimization
2. AI for drug-target interaction studies
3. QSAR modelling
4. Molecular dynamics simulations
5. Hands-on tutorial
Week 7:ADMET predictive modelling in drug discovery
1. Introduction to ADMET Properties
2. Importance in lead optimization
3. Conventional methods for ADMET prediction
4. Open available resources for ADMET prediction
5. Hands-on tutorial
Week 8:AI in clinical phase
1. Overview of clinical trials
2. Patient recruitment, stratification, and retention
3. Clinical trial protocol design and optimization
4. Predicting outcomes of clinical trials with AI
5. Data collection and monitoring for regulatorysubmissions
Week 9:De Novo Drug Design using Generative AI
1. Introduction to Generative AI in Drug Design
2. Deep Generative Models for drug design (GAN,GNN, RNN, VAE etc.)
3. Benchmarking Generative Models for Drug Design
4. Molecule Optimization with Generative AI
5. Hands-on tutorial
Week 10:Advanced concepts: Precision medicine, Networkpharmacology and Drug repurposing
1. AI in genomics for personalized treatments
2. AI in real-time monitoring and feedback
3. Overview and data sources for AI in drugrepurposing
4. Integrating multi-target drug discovery
5. Network pharmacology with AI
Week 11:Case studies, challenges, future directions, andresources
1. Public AI resources for drug discovery
2. Examples of notable successful case studies
3. Challenges in modern drug discovery realm
4. Regulatory considerations for AI implementation indrug development
5. Future outlook: Explainable artificial intelligence(XAI) and other emerging technologies in drugdiscovery
Week 12:Mini project
(Implementing an advanced workflow combining datacollection, target prediction, virtual screening, lead optimization, and ADMET prediction)