AI-Driven Drug Repurposing: Network Pharmacology, Biomedical Knowledge Graphs & Predictive Drug Discovery

Aim

Workshop Objectives

Workshop Structure

📅 Day 1 – Network Pharmacology, Drug–Target Identification & Disease Pathway Analysis

• Introduction to drug repurposing and network pharmacology in computational drug discovery.
• Identification of disease-associated genes and therapeutic targets using Open Targets.
• Drug–target interactions, mechanisms of action, and bioactivity analysis using ChEMBL.
• Drug and compound information retrieval using PubChem.
• Protein–protein interaction network construction using STRING.
• Molecular network visualization and identification of highly connected proteins using Cytoscape.
• Biological pathway enrichment and functional interpretation using Reactome.
• Integration of drug–gene–disease relationships for therapeutic hypothesis development.

🛠️ Hands-On Lab: Drug–Target Network Analysis & Pathway Enrichment

• Select a disease and identify associated genes and therapeutic targets.
• Retrieve existing drugs and investigate their molecular targets.
• Construct and visualize protein interaction networks using STRING and Cytoscape.
• Identify relevant biological pathways and potential drug repurposing opportunities.

Hands-On Tools: Open Targets | ChEMBL | PubChem | STRING | Cytoscape | Reactome

📅 Day 2 – Biomedical Knowledge Graphs, Graph Embeddings & AI-Based Drug–Disease Prediction

• Introduction to biomedical knowledge graphs and their applications in drug discovery.
• Representation of drugs, genes, diseases, pathways, and adverse effects through graph entities and relationships.
• Biomedical knowledge graph construction and visualization using NetworkX.
• Understanding graph embeddings and relational learning approaches.
• Introduction to TransE, DistMult, and ComplEx graph embedding models.
• Drug–disease link prediction and computational candidate ranking.
• Interpretation of prediction scores and graph-based biological relationships.
• Model evaluation and limitations of computational therapeutic predictions.

🛠️ Hands-On Lab: Biomedical Knowledge Graph Analysis & Link Prediction

• Import a curated drug–gene–disease dataset into Google Colab.
• Construct and visualize a biomedical knowledge graph using Python and NetworkX.
• Explore graph embeddings through a guided TransE experiment.
• Evaluate predicted drug–disease links and compare candidate scores.

Hands-On Tools: Google Colab | Python | Pandas | NetworkX | PyKEEN | Matplotlib

📅 Day 3 – AI-Driven Drug Repurposing, Therapeutic Candidate Prioritization & Virtual Live-Lab Experimentation

• Integration of network pharmacology and biomedical knowledge graph predictions.
• Evidence-weighted scoring and prioritization of potential drug–disease associations.
• Interpretation of therapeutic targets, molecular pathways, and biological plausibility.
• Drug safety signals and adverse drug effect assessment.
• Literature-based validation of potential therapeutic associations using PubMed.
• Evaluation of available clinical evidence using ClinicalTrials.gov.
• Comparison of graph embedding approaches and prediction results.
• Development of research hypotheses and experimental validation strategies.

🛠️ Hands-On Lab 1: Drug Candidate Prioritization & Biomedical Evidence Analysis

• Investigate predicted drug–disease associations and their molecular targets.
• Evaluate supporting therapeutic evidence using Open Targets and ChEMBL.
• Review relevant literature and clinical trial information.
• Prioritize potential candidates based on biological relevance and supporting evidence.

Hands-On Tools: Open Targets | ChEMBL | PubMed | ClinicalTrials.gov

🧪 Hands-On Lab 2: Repurpose Drug Discovery Lab – Virtual Research Project

Participants will conduct a guided drug repurposing experiment using the Repurpose Drug Discovery Lab at live-labs.org.

• Select a drug–disease case study and define research objectives.
• Validate biomedical data and retrieve supporting evidence.
• Explore drug–gene–disease relationships using knowledge graphs.
• Analyze drug–disease predictions and rank potential candidates.
• Generate a research report with supporting evidence and testable hypotheses.

Hands-On Tools: Repurpose Drug Discovery Lab | Biomedical Knowledge Graphs | Link Prediction | Drug Candidate Ranking

Who Should Enrol?

Important Dates

Workshop Outcomes

Fee Structure