AI-Powered Systems Biology & Nanomedicine: Python-Based Biomarker Discovery for Lifestyle Diseases

Aim

Workshop Objectives

Workshop Structure

🗓️ Day 1 — Python-Based Disease Genomics, Molecular Pathways & Systems Biology

• Molecular mechanisms of type 2 diabetes, obesity, and cardiovascular disorders
• Insulin resistance, metabolic dysfunction, oxidative stress, and inflammatory signaling
• Disease-associated gene identification using GeneCards, DisGeNET, and NCBI Gene
• Protein function and disease association analysis using UniProt
• PI3K–AKT, AMPK, insulin signaling, and NF-κB pathway analysis using KEGG and Reactome
• Gene Ontology and pathway enrichment analysis using ShinyGO
• Python-based processing and visualization of disease-associated molecular data

🛠️ Hands-On: Retrieve type 2 diabetes-associated genes, perform pathway enrichment analysis using ShinyGO, and         generate pathway visualization plots in Python.

Bioinformatics Tools: GeneCards | DisGeNET | NCBI Gene | UniProt | KEGG | Reactome | ShinyGO

Python Tools: Google Colab | Pandas | Matplotlib

🗓️ Day 2 — AI-Driven Molecular Network Analysis, Hub Genes & Biomarker Discovery

• Protein–protein interaction networks and their biological significance
• Construction of disease-associated molecular interaction networks using STRING
• Network visualization using Cytoscape and Python NetworkX
• Hub gene identification through degree and betweenness centrality analysis
• Network cluster and functional module detection using cytoHubba or MCODE
• Retrieval and analysis of diabetes-related gene-expression datasets from NCBI GEO
• Random Forest-based candidate biomarker prioritization using gene-expression data
• Integration of network topology and machine-learning feature rankings for molecular target prioritization

🛠️ Hands-On: Build a diabetes-associated protein interaction network using STRING and Cytoscape, identify hub genes, and apply Random Forest to a prepared gene-expression dataset for candidate biomarker ranking.

Bioinformatics Tools: STRING | Cytoscape | cytoHubba | NCBI GEO | GEO2R

Python Tools: Google Colab | NetworkX | Scikit-learn | Pandas

🗓️ Day 3 — AI-Assisted Nanomedicine, Protein Targets & Predictive Nano–Bio Analysis

• Nanomedicine applications in diabetes and metabolic disease research
• Lipid nanoparticles, polymeric nanocarriers, and functionalized drug-delivery systems
• Retrieval of disease-associated protein structures using RCSB PDB
• Three-dimensional visualization of therapeutic protein targets using ChimeraX
• Nanoparticle–protein interactions and protein corona formation
• Effects of particle size, zeta potential, and surface properties on nano–bio interactions
• Machine-learning analysis of nanocarrier properties and experimentally measured biological responses
• Predictive modeling of cellular uptake or cytotoxicity and interpretation of model limitations

🛠️ Hands-On: Visualize a selected diabetes-associated protein structure and use Python with a curated nanoparticle dataset to build an exploratory Random Forest model for cellular uptake or cytotoxicity prediction.

Bioinformatics Tools: UniProt | RCSB PDB | ChimeraX

Python Tools: Google Colab | Pandas | NumPy | Scikit-learn | Matplotlib

Who Should Enrol?

Important Dates

Workshop Outcomes