Explainable AI (XAI) for Single-Cell Multi-Omics Integration
Integrating Multi-Omics Data with Transparent AI—For Better Understanding and Targeted Therapies.
Skills you will gain:
About Workshop:
Multi-omics data integration at the single-cell level is revolutionizing our understanding of cellular heterogeneity, disease mechanisms, and therapeutic response. However, integrating high-dimensional datasets from different omics layers (e.g., genomics, transcriptomics, proteomics, epigenomics) presents significant challenges, particularly in terms of model interpretability and biological relevance. Explainable AI (XAI) methods are essential in providing transparency into the complex AI models used to analyze such data, ensuring that results are not only accurate but also biologically interpretable.
This workshop explores how XAI techniques can be employed in single-cell multi-omics studies to integrate data from various omics layers. Participants will learn how to apply machine learning models like random forests, neural networks, and attention mechanisms to multi-omics datasets while ensuring model transparency through feature importance and local explainability. The program also emphasizes how XAI methods can help identify key biomarkers, uncover cellular mechanisms, and facilitate precision medicine applications in oncology, immunology, and other fields.
Aim:
This workshop aims to provide participants with a comprehensive understanding of Explainable AI (XAI) techniques applied to single-cell multi-omics integration. It focuses on how AI can be used to combine genomic, transcriptomic, proteomic, and epigenomic data at the single-cell level while ensuring the interpretability and transparency of the models. Participants will learn to integrate multi-omics datasets and generate biologically meaningful insights using XAI-driven approaches, empowering data-driven decisions in systems biology.
Workshop Objectives:
- Understand XAI techniques for ensuring model transparency and interpretability.
- Learn how to integrate multi-omics datasets (genomic, transcriptomic, proteomic, and epigenomic) at the single-cell level.
- Apply machine learning models for multi-omics data analysis while maintaining biological interpretability.
- Use XAI methods to identify key biomarkers and mechanisms from multi-omics data.
- Explore applications of XAI in precision medicine, oncology, and immune system research.
What you will learn?
Day 1 Data Prep (Make Multiome Data Analysis-Ready)
- What multiome data is (RNA + ATAC from the same cells)
- Load PBMC multiome dataset into AnnData
- Basic QC + filtering (remove low-quality cells/features)
- Normalize RNA, prepare ATAC features
- Create a clean dataset + baseline UMAP (RNA-only)
- Hands-on: Scanpy + AnnData workflow
Day 2 Integration with scVI / TotalVI (Build a Joint Latent Space)
- Quick concept: what a VAE does in single-cell analysis
- Train scVI/TotalVI on the prepared multiome dataset
- Extract latent embedding
- UMAP + clustering on the latent space
- Quick marker check to validate clusters
- Hands-on: scVI-tools + Scanpy (UMAP, clustering)
Day 3 Explainability with SHAP + Paper-Ready Figures
- What “explainability” means in multiome deep learning
- Run SHAP to find key genes driving cluster separation
- Top gene list per cluster (interpretable outputs)
- Export: publication-ready UMAP, violin plots for top genes, ranked feature table (CSV)
Hands-on: SHAP + Scanpy plotting
Mentor Profile
Fee Plan
Important Dates
05 Mar 2026 Indian Standard Timing 7:00 PM
05 Mar 2026 to 07 Mar 2026 Indian Standard Timing 8:00 PM
Get an e-Certificate of Participation!
Intended For :
- Doctoral Scholars & Researchers: PhD candidates seeking to integrate computational workflows into their molecular research.
- Postdoctoral Fellows: Early-career scientists aiming to enhance their data-driven publication profile.
- University Faculty: Professors and HODs interested in modern bioinformatics pedagogy and tool mastery.
- Industry Scientists: R&D professionals from the Biotechnology and Pharmaceutical sectors transitioning to genomic-driven discovery.
- Postgraduate Students: Final-year PG students looking for specialized research-grade exposure beyond standard curricula.
Career Supporting Skills
Workshop Outcomes
Participants will be able to:
- Apply XAI techniques to integrate multi-omics datasets.
- Use machine learning models to interpret complex biological data while ensuring model transparency.
- Gain insights into key biomarkers and cellular mechanisms from multi-omics data.
- Understand how to interpret results in a biologically meaningful way for precision medicine applications.
- Propose AI-driven pipelines for integrating omics layers in systems biology research.