AI-Powered Nanopore Sequencing & Multi-Omics Analysis

To equip participants with the knowledge and hands-on experience to apply AI-driven workflows for Nanopore sequencing, generating actionable insights in genomics, metagenomics, and epigenetic research.

• Understand the fundamentals of Nanopore sequencing and data formats (POD5/FAST5).
• Apply AI and deep learning for basecalling, quality control, and methylation-aware signal interpretation.
• Conduct genome assembly, polishing, and metagenomic classification using AI-assisted tools.
• Perform variant calling and epigenetic analysis including DNA methylation and RNA modifications.
• Build interactive dashboards for visualization of sequencing metrics, assembly, and genomic insights.
• Complete an end-to-end mini-project integrating all steps of the Nanopore-AI workflow.

📅 Day 1: Foundations of Nanopore Sequencing and AI-Based Basecalling

• Overview of Nanopore sequencing: technology, raw signal generation, and sequencing chemistry (R10.4)
• Understanding POD5/FAST5 files and conversion to FASTQ reads
• AI and deep learning in basecalling: transformers, hybrid models, and methylation-aware basecallers (Bonito, Dorado, Remora)
• Adaptive sampling for targeted sequencing and dynamic read enrichment
• Quality control of Nanopore reads: read length, N50, quality scores, signal-level QC, and reproducibility

🛠️ Hands-on:

• AI-based basecalling using Dorado/Bonito
• Real-time QC dashboard creation (Python + Streamlit)
• Interpretation of sequencing metrics and error profiles
• Targeted read enrichment simulation using adaptive sampling

🧰 Tools Covered:

• Dorado, Bonito, NanoPlot, PycoQC, Python (Pandas, Plotly, Streamlit), Google Colab

📅 Day 2: AI-Assisted Genome Assembly, Polishing, and Real-Time Metagenomics

• Long-read genome assembly and error characteristics of Nanopore data
• AI-assisted polishing and consensus correction (Medaka, DeepConsensus)
• Hybrid assembly integration: Nanopore + Illumina reads for high-quality genomes
• Metagenomic classification: strain-level resolution, pathogen detection, and microbial community profiling
• Real-time data pipelines for adaptive microbiome analysis
• Visualization of assembly quality and taxonomic composition using interactive dashboards

🛠️ Hands-on:

• Genome assembly and AI-based polishing using Medaka
• Comparative metagenomic classification using Kraken2 + Bracken
• Taxonomic visualization using Krona
• Assembly quality scoring and dashboard visualization

🧰 Tools Covered:

• Medaka, Kraken2, Bracken, Krona, Python (Scikit-learn, Pandas, Plotly), Google Colab

📅 Day 3: AI-Based Variant Calling, Epigenetic Profiling, and Multi-Omics Integration

• Detection of genomic variants: SNVs, indels, structural variants using deep learning (Clair3, DeepVariant adaptation)
• AI-based DNA methylation analysis and phasing (Dorado methylation models, Modkit)
• Multi-modal variant detection integrating basecall signals, methylation, and coverage
• RNA modifications (m6A) detection from direct RNA sequencing (emerging trend)
• Population genomics and disease association applications using Nanopore-derived variants
• Explainable AI approaches for variant and epigenetic prediction
• Reproducibility, FAIR data practices, and pipeline standardization

🛠️ Hands-on:

• Variant calling using Clair3 and DeepVariant
• DNA methylation detection and allele-specific analysis
• Multi-sample methylation comparison for differential analysis
• Mini-project: End-to-end AI pipeline — raw signals → basecalling → assembly → variant & methylation analysis → interactive dashboard

🧰 Tools Covered:

• Clair3, Dorado methylation models, Modkit, IGV, Python (Pandas, Plotly, Streamlit), Google Colab

• PhD scholars, researchers, and academicians in genomics, bioinformatics, or molecular biology.
• Industry professionals in precision medicine, microbiome research, and AI-assisted biotechnology.
• Bioinformatics enthusiasts seeking hands-on AI applications in sequencing and multi-omics analysis.
• Participants with basic familiarity in Python/data analysis (helpful but not mandatory).

• Perform AI-based basecalling, QC, and methylation-aware analysis.
• Execute AI-assisted genome assembly, polishing, and metagenomic classification.
• Conduct variant calling and epigenetic profiling including methylation and RNA modifications.
• Integrate sequencing data into interactive dashboards for analysis and reporting.
• Apply knowledge to research projects and real-world datasets, generating reproducible and FAIR-compliant results.
• Gain practical experience with state-of-the-art AI and bioinformatics tools.