AI-Guided RNA Epitranscriptomics: m6A Modification Profiling, RNA Regulatory Networks & Disease Biomarkers

Aim

Workshop Objectives

Workshop Structure

Workshop Structure

Day 1: RNA Epitranscriptomics, m6A Profiling & Python-Based Analysis

Session Focus: Explore m6A RNA modifications, regulatory mechanisms and computational approaches for RNA modification profiling.

Topics Covered

• RNA epitranscriptomics: Biological significance and research applications.
• m6A regulatory machinery: Writers (METTL3/METTL14), erasers (FTO/ALKBH5) and readers (YTH proteins).
• m6A detection technologies: MeRIP-seq, miCLIP and nanopore sequencing.
• RNA modification databases: m6A-Atlas and RMBase.
• Computational m6A profiling, DRACH motif identification and transcript-level analysis.
• Python-based RNA sequence analysis and visualization.

Hands-On: m6A Modification Profiling & Sequence Motif Analysis

Analyze a curated m6A dataset, identify DRACH motifs, examine transcript-region distributions and generate modification profiling visualizations using Python.

Tools: Google Colab, Python, Biopython, Pandas, Matplotlib, m6A-Atlas.

Practical Outcome: Annotated m6A dataset, motif analysis and RNA modification visualizations.

Day 2: AI-Based m6A Prediction & RNA Regulatory Network Analysis

Session Focus: Apply machine learning to predict m6A-associated sites and investigate RNA regulatory interactions.

Topics Covered

• AI-assisted m6A prediction and RNA sequence feature extraction.
• k-mer encoding and Random Forest classification.
• Model evaluation: Confusion matrix, precision, recall, F1-score and ROC-AUC.
• m6A-mediated regulation of RNA stability, splicing and translation.
• RNA regulatory interactions involving m6A regulators, RNA-binding proteins, miRNAs and target genes.
• Regulatory network construction and visualization.

Hands-On: Machine Learning-Based m6A Prediction & Network Visualization

Train a Random Forest classifier using curated RNA sequence data, evaluate prediction performance and visualize an m6A-associated regulatory network.

Tools: Google Colab, Python, Scikit-learn, Pandas, NetworkX, Matplotlib.

Practical Outcome: Introductory m6A prediction model, performance plots and RNA regulatory network.

Day 3: AI-Driven Disease Biomarker Screening & Epitranscriptomic Data Integration

Session Focus: Integrate RNA modification and gene expression data with machine learning to explore disease-associated biomarkers.

Topics Covered

• m6A dysregulation in cancer, neurological, metabolic and inflammatory diseases.
• Disease-associated RNA modification signatures and gene expression analysis.
• Integration of epitranscriptomic and transcriptomic datasets.
• AI-based biomarker screening using feature selection and Random Forest.
• ROC-AUC analysis, feature importance and candidate biomarker prioritization.
• Emerging trends: Single-cell epitranscriptomics, nanopore sequencing and explainable AI.

Hands-On: AI-Based Disease Biomarker Screening & Classification

Analyze curated disease-associated molecular datasets, train a classification model, evaluate ROC-AUC and visualize candidate biomarker rankings.

Tools: Google Colab, Python, Pandas, Scikit-learn, Matplotlib, Seaborn.

Practical Outcome: Exploratory disease classification model, ROC curve and prioritized candidate biomarker list requiring further validation.

Who Should Enrol?

Important Dates

Workshop Outcomes

Fee Structure