AI-Powered Rare Disease Therapeutics: Bioinformatics, Cytoscape Network Analysis, ADMET & Drug Discovery
From Real Huntington Disease Datasets to DEG Analysis, Biomarker Identification, Protein Networks, Molecular Docking & ADMET Using NCBI GEO, GEO2R, Google Colab, Cytoscape and AI Tools.
About This Course
Rare disease research increasingly leverages public genomic datasets, bioinformatics, artificial intelligence and computational drug discovery.
This three-day international hands-on workshop focuses on Huntington Disease Genomics, covering public dataset extraction, differential gene expression analysis, biomarker discovery, PPI network construction, hub-gene identification and pathway enrichment using NCBI GEO, GEO2R, Google Colab, STRING, Cytoscape, Reactome and Enrichr.
Participants will also explore therapeutic target identification, drug repurposing, molecular docking, and computational ADMET and toxicity prediction using Open Targets, ChEMBL, PubChem, AutoDock Vina, SwissADME, pkCSM and ProTox.
Using Huntington disease as a case study, participants will follow an integrated workflow from gene expression analysis to preliminary drug candidate prioritization.
The workshop is designed for PhD scholars, research scientists, faculty members, bioinformatics and neuroscience researchers, biotechnology professionals, and pharmaceutical scientists.
Aim
To provide participants with a practical understanding of how bioinformatics, network biology, and Artificial Intelligence can be integrated to identify, analyze, and prioritize disease-associated genes for rare disease research and precision genomics.
Workshop Objectives
-
-
Extract and organize Huntington disease gene expression datasets from NCBI GEO.
-
Identify significant differentially expressed genes using GEO2R and Google Colab.
-
Generate research visualizations, including volcano plots and gene expression heatmaps.
-
Identify and prioritize candidate disease-associated biomarkers.
-
Construct protein interaction networks and identify hub genes using STRING and Cytoscape.
-
Perform functional enrichment and pathway analysis.
-
Identify potential therapeutic targets and retrieve compounds for drug repurposing.
-
Perform molecular docking and analyze protein–ligand interactions.
-
Evaluate drug-likeness, pharmacokinetic properties and predicted toxicity.
- Integrate computational findings into a structured research report.
-
Workshop Structure
📅 Day 0: Software Installation & Mentor Setup
Day 0 prepares your computing environment by guiding you through installing Cytoscape (with cytoHubba), BIOVIA Discovery Studio Visualizer, AutoDock Vina, and configuring Google Colab with required Python packages (pandas, scikit-learn, seaborn).
Dedicated technical mentors will provide live, 1-on-1 troubleshooting for OS/Java conflicts and offer pre-configured cloud fallbacks so every participant can run codes and hands-on tools seamlessly from Day 1.
📅 Day 1: Huntington Disease Genomics, Biomarker Discovery & PPI Networks
-
Introduction to Huntington disease, HTT gene mutations, molecular pathology, and disease-associated genes.
-
Explore and download public gene expression datasets from NCBI GEO.
-
Perform differential gene expression analysis using GEO2R and filter significant genes with Google Colab and Python.
-
Generate volcano plots, heatmaps, and gene expression visualizations.
-
Investigate candidate biomarkers using NCBI Gene, ClinVar, and UniProt.
-
Construct protein–protein interaction (PPI) networks using STRING and Cytoscape.
-
Identify hub genes using cytoHubba and perform pathway enrichment using Reactome and Enrichr.
-
Prioritize potential therapeutic targets using Open Targets.
🛠️ Hands-on Activity: Huntington Disease Gene Expression & Network Analysis
Participants will analyse a public Huntington disease dataset, identify differentially expressed genes, visualize expression patterns, shortlist candidate biomarkers, construct PPI networks, and explore disease-associated pathways and therapeutic targets.
Practical Output: DEG results, volcano plot, heatmap, candidate biomarker list, PPI network, hub genes, enriched pathways, and prioritized targets.
📅 Day 2: Drug Repurposing, Compound Screening & Molecular Docking
-
Explore computational drug repurposing for Huntington disease.
-
Identify potential therapeutic targets using Open Targets and ChEMBL.
-
Retrieve protein sequences and structures from UniProt and RCSB PDB.
-
Obtain candidate compounds from PubChem and ChEMBL.
-
Prepare protein and ligand files for molecular docking.
-
Perform docking using AutoDock Vina.
-
Visualize protein–ligand interactions using BIOVIA Discovery Studio Visualizer.
-
Compare docking scores and binding interactions to shortlist candidate compounds.
🛠️ Hands-on Activity: Compound Screening & Molecular Docking
Participants will select a disease-relevant protein target, retrieve candidate compounds, prepare molecular structures, and perform docking. They will analyse predicted binding interactions and compare docking results to prioritize compounds for further evaluation.
Practical Output: Prepared protein and ligand files, candidate compound library, docking scores, interaction visualizations, and shortlisted drug-repurposing candidates.
📅 Day 3: ADMET Analysis, AI-Assisted Drug Ranking & Research Reporting
-
Evaluate drug-likeness and molecular properties using SwissADME.
-
Predict ADMET characteristics using pkCSM and toxicity profiles using ProTox 3.0.
-
Assess predicted blood–brain barrier permeability and CNS-relevant properties.
-
Integrate docking scores, molecular descriptors, and ADMET results using Google Colab and Python.
-
Explore AI-assisted compound ranking using a prepared dataset and basic machine-learning methods.
-
Compare candidates based on target relevance, docking results, drug-likeness, predicted ADMET, and toxicity.
-
Generate comparative charts, screening tables, and research visualizations.
-
Integrate findings into a structured computational research report.
🛠️ Hands-on Activity: ADMET Screening & AI-Assisted Drug Candidate Prioritization
Participants will evaluate shortlisted compounds, compare predicted pharmacokinetic and toxicity properties, and assess their potential CNS suitability. They will integrate docking and ADMET results, explore a basic AI-assisted ranking workflow, and prepare a consolidated research report.
Practical Output: ADMET comparison table, toxicity predictions, BBB assessment, ranked candidate compounds, research figures, and a structured computational research report.
Who Should Enrol?
This workshop is designed for undergraduate and postgraduate students, Ph.D. scholars and research fellows, faculty members and academicians, bioinformatics and computational biology researchers, genomics and molecular biology scientists, biotechnology and pharmaceutical professionals, data scientists working in life sciences, healthcare researchers, AI and machine learning enthusiasts, and industry professionals interested in genomics, precision medicine, and computational biology.
Important Dates
Registration Ends
November 1, 2026
IST 8:00 PM
Workshop Dates
November 1, 2026 – November 4, 2026
IST 8:00 PM
Workshop Outcomes
- Understand the role of bioinformatics in rare disease genomics and gene discovery.
- Retrieve and interpret disease-associated genomic information from public biological databases.
- Perform functional annotation, network biology analysis, and pathway enrichment of candidate genes.
- Construct and analyze protein–protein interaction networks using Cytoscape and related bioinformatics tools.
- Apply AI and machine learning techniques for disease gene prioritization and biomarker identification.
- Integrate genomic, functional, and network-based information to support rare disease research.
- Gain practical experience with widely used bioinformatics databases, network analysis platforms, and AI-enabled computational workflows for precision genomics.
Fee Structure
Frequently asked questions
Will I get the recording?
Yes. Paid participants get the session recordings and study material in their NanoSchool dashboard (My registrations → Recorded Lectures / Study Material).
What if I miss a live session?
Watch the recording in your dashboard and send your questions to the mentor through the support desk.
Do I get a certificate?
Yes, an e-certificate of participation after the workshop, with a QR code anyone can verify and an "Add to LinkedIn" button.
Which fee category applies to me?
Choose the category that matches your current role: Student, Ph.D. Scholar / Researcher, Academician / Faculty or Industry Professional.
How can I pay?
By card, UPI or PayPal on the payment page; international bank transfer is also available there.
What is the refund policy?
See our Returns, Refunds & Cancellation policy: Returns, Refunds & Cancellation policy