AI-Driven Bioinformatics: From Genomic Data to Intelligent Biological Discovery

Aim

Workshop Objectives

Workshop Structure

📅 Day 1: Integrated Genomic Data Mining and Variant Interpretation

Core Objective: Build an integrated genomic-data workflow for investigating genes, transcripts, proteins, variants, and disease associations.

• Advanced navigation of genomic, transcriptomic, proteomic, and disease databases
• Gene, transcript, isoform, exon, regulatory-region, and protein annotation
• Genome-build awareness, coordinates, identifiers, and cross-database mapping
• Sequence retrieval, similarity searching, and comparative sequence interpretation
• Variant annotation, consequence prediction, and functional-impact assessment
• AI-assisted literature mining with evidence verification and source validation

🧪 Hands-on Session

• Retrieve and integrate gene, transcript, protein, variant, and disease information for a selected biological target.
• Perform sequence-similarity and variant-impact analysis and prepare an evidence-based genomic annotation table.

🧰 Tools Covered

NCBI, Ensembl, UniProt, NCBI BLAST, Ensembl Variant Effect Predictor

📅 Day 2: Transcriptomic Analysis and AI-Assisted Biomarker Discovery

Core Objective: Transform gene-expression data into statistically and biologically meaningful disease-associated signatures.

• Experimental design, metadata assessment, and transcriptomic dataset selection
• Gene-expression normalization, quality assessment, and sample comparison
• Differential-expression analysis and statistical significance interpretation
• Fold change, adjusted p-value, multiple testing, and expression-pattern assessment
• Identification of candidate biomarkers and disease-associated gene signatures
• AI-assisted interpretation of expression results, biological relevance, and research hypotheses

🧪 Hands-on Session

• Analyze a disease-versus-control gene-expression dataset and identify significantly differentially expressed genes.
• Prioritize candidate biomarkers using statistical evidence, biological databases, and AI-assisted interpretation.

🧰 Tools Covered

NCBI GEO, GEO2R, Ensembl, UniProt, Excel or Google Sheets

📅 Day 3: Functional Enrichment, Network Biology and Intelligent Discovery

Core Objective: Convert gene lists into pathways, interaction networks, disease mechanisms, and testable biological hypotheses.

• Gene Ontology, pathway databases, and functional-annotation frameworks
• Over-representation analysis and enrichment-result interpretation
• Biological pathway mapping and disease-mechanism reconstruction
• Protein–protein interaction network construction and confidence assessment
• Hub-gene, functional-module, and candidate-target prioritization
• AI-assisted integration of genomic, expression, pathway, and network findings

🧪 Hands-on Session

• Perform functional enrichment and pathway analysis on a prioritized disease-associated gene list.
• Construct and interpret a protein-interaction network and prepare an AI-supported biological discovery summary.

🧰 Tools Covered

g: Profiler, STRING Database, KEGG, Cytoscape Awareness

Who Should Enrol?

Important Dates

Workshop Outcomes

Meet Your Mentor(s)

Abhimanyu

Deprtment of Biotechnology

more