AI in Bioinformatics & Multi-Omics: Hands-On Genomics, Biomarker Discovery and Drug Discovery

To equip participants with practical knowledge of AI-assisted biological research by integrating bioinformatics databases, computational analysis, and intelligent discovery workflows for data interpretation, biomarker exploration, protein analysis, and early-stage drug discovery.

• To explain the shift from traditional biology to data-driven and AI-assisted discovery.
• To familiarize participants with key biological data types such as genomics, transcriptomics, proteomics, imaging data, and electronic health records.
• To introduce basic machine learning concepts relevant to biologists and life science researchers.
• To demonstrate how AI can support biological data preprocessing, visualization, and interpretation.
• To explain the structure of a digital discovery pipeline, including data acquisition, integration, knowledge extraction, hypothesis generation, validation, and iteration.
• To explore real-world applications such as drug discovery, protein structure prediction, biomarker identification, and precision medicine.
• To introduce AI tools such as scientific LLMs, bioinformatics AI platforms, protein-design tools, single-cell analysis tools, and knowledge graph systems.
• To guide participants in building a basic AI-assisted biological workflow.
• To create awareness about ethical considerations and responsible AI use in biomedical and life science research.

📅 Day 1: Vision of the Digital Biologist

• Core Objective: Understand the evolution of biology from traditional research approaches to AI-enabled discovery.
• Digital Biologist: evolution from traditional biology to AI-enabled discovery
• Current challenges in biological research: data overload and multi-omics integration
• Hypothesis generation and experimental scalability
• Machine learning fundamentals for biologists
• Biological data types: genomics, transcriptomics, proteomics, imaging, and electronic health records

🛠️ Hands-on:

• Hands-on Lab: Explore biological datasets for AI-driven research applications.
• Hands-on Lab: Perform biological data preprocessing and visualization.
  • Gene Expression Analysis: Identify differentially expressed genes using NCBI GEO2R.
  • Cancer Biomarker Exploration: Analyze gene expression patterns and genomic alterations using UCSC Xena and cBioPortal.
  • Data Visualization: Explore and visualize biological datasets using Python in Google Colab.

   

🧰 Tools Covered: Biological datasets, data preprocessing tools, visualization workflows. NCBI GEO2R, UCSC Xena, cBioPortal, Google Colab, Python.

📅 Day 2: Digital Discovery Pipeline

• Core Objective: Learn how AI-driven discovery pipelines support biological data integration, knowledge extraction, hypothesis generation, and validation.
• Biological data acquisition and data integration
• Knowledge extraction from datasets and scientific literature
• AI-assisted hypothesis generation
• Experimental design, validation, and iterative discovery
• Applications in drug discovery, protein structure prediction, biomarker identification, and precision medicine

🛠️ Hands-on & Case Studies:

• Case Study: AI-driven drug discovery workflow
• Case Study: Protein structure prediction for biological research
• Case Study: Biomarker identification using biological datasets
• Case Study: Precision medicine and personalized biological insights
• • Protein Structure Analysis: Visualize AI-predicted protein structures using AlphaFold DB and Mol*.
  • Molecular Network Analysis: Explore protein interactions and biological pathways using STRING.
  • Drug-Likeness & ADMET: Evaluate selected compounds using SwissADME or ADMETlab.
  • Biomarker Analysis: Investigate disease-associated genomic evidence using cBioPortal or UCSC Xena.
  • Integrated Data Analysis: Organize and visualize research findings using Google Colab.

🧰 Tools Covered: AI discovery pipelines, biological data integration tools, knowledge extraction workflows.  AlphaFold DB, Mol*, STRING, SwissADME, ADMETlab, cBioPortal, UCSC Xena, Google Colab.

📅 Day 3: AI Tools for the Digital Biologist

• Core Objective: Explore AI tools and platforms used to build AI-assisted biological workflows.
• Scientific LLMs for biological research and literature understanding
• Bioinformatics AI platforms for biological data interpretation
• Protein-design tools for structure and function exploration
• Single-cell analysis tools for cellular-level biological insights
• Knowledge graph systems for biological relationship mapping
• Ethical considerations and responsible AI in biomedicine

🛠️ Hands-on:

• Hands-on Lab: Select a biological problem for AI-assisted analysis.
• Hands-on Lab: Analyze a biological dataset using AI tools.
• Hands-on Lab: Apply AI platforms to support biological interpretation.
• Hands-on Lab: Build an AI-assisted biological discovery workflow.

🧰 Tools Covered: Scientific LLMs, bioinformatics AI platforms, protein-design tools, single-cell analysis tools, knowledge graph systems

Application Themes: Cancer genomics, drug repurposing, microbiome analysis, and protein function prediction.

• Undergraduate and postgraduate students from biotechnology, bioinformatics, life sciences, biomedical sciences, microbiology, biochemistry, genetics, pharmacy, and related fields
• PhD scholars and research scholars working in biological, biomedical, pharmaceutical, or computational biology research
• Faculty members, academicians, and research mentors interested in AI-enabled life science research
• Bioinformatics professionals and data analysts working with biological datasets
• Biotechnology, pharmaceutical, healthcare, and life science industry professionals
• Beginners with basic knowledge of biology and an interest in AI-driven biological discovery

• Understand the concept of the Digital Biologist and its importance in modern life science research.
• Explain how AI can support biological discovery, data analysis, and research automation.
• Identify different biological data types, including genomics, transcriptomics, proteomics, imaging data, and clinical health records.
• Perform basic exploration, preprocessing, and visualization of biological datasets.
• Understand the structure of an AI-driven digital discovery pipeline.
• Apply AI-assisted thinking to biological problems such as drug discovery, biomarker identification, protein structure prediction, and precision medicine.
• Explore scientific LLMs, bioinformatics AI platforms, protein-design tools, single-cell analysis tools, and knowledge graph systems.
• Build a basic AI-assisted biological workflow for a selected biological problem.
• Understand how AI can help in hypothesis generation and experimental planning.
• Recognize ethical issues related to responsible AI use in biomedical and life science research.
• Gain foundational skills for future learning in AI-driven biotechnology, computational biology, bioinformatics, and digital biology research.