Multi-Omics Network Integration & Data Fusion — Hands-on

Learn how to combine multiple omics layers into coherent, network driven views of biology. This module focuses on aligning heterogeneous data types, choosing appropriate integration strategies, and building multi layer networks and latent factor models that connect genes, proteins, metabolites and phenotypes using practical workflows in R, Python and Cytoscape.

Multi-Omics Network Integration & Data Fusion

Help Desk · WhatsApp

Session Index

Session 1 — Multi-Omics Data Types & Alignment Session 2 — Normalisation & Integration Strategies Session 3 — Network Based & Latent Factor Data Fusion Session 4 — Mini Capstone: Integrated Multi-Omics Network

Session 1

Fee: Rs 8800

Multi-Omics Data Types & Alignment

Multi omics study design and data layers

transcriptomics proteomics metabolomics and more

Feature identifiers and sample alignment across omics

gene, protein and metabolite IDs mapping tables and lookups paired samples and timepoints

Data structures and toolchain for multi omics matrices

R / tidyverse matrix and list formats Python / pandas and xarray style use meta data and design tables

Session 2

Fee: Rs 11800

Normalisation & Integration Strategies

Preprocessing and normalisation across omics layers

scaling and transformation choices batch and platform effects filtering and feature selection

Main integration paradigms for multi omics data

early integration (feature concatenation) intermediate latent factor style late integration at model level

Implementation toolkit for normalisation and inspection

R based multi omics utilities Python / scikit learn pipelines QC plots and summary statistics

Session 3

Fee: Rs 14800

Network Based & Latent Factor Data Fusion

Correlation and association networks across omics layers

cross layer correlation matrices co expression and metabolite links edge thresholding and filtering

Latent factor and multi block methods (concept level)

PLS and PLS DA style approaches factor models similar to MOFA ideas canonical correlation preview

Implementation toolkit for data fusion and network views

R style mixOmics like workflows Python notebooks for data fusion Cytoscape multi layer network visualisation

Session 4

Fee: Rs 18800

Mini Capstone: Integrated Multi-Omics Network

Build an integrated multi omics network for a case study dataset

Theory + Practical

Identify key modules, pathways and phenotype associations

joint clusters across omics layers pathway annotation overlays links to clinical or trait variables

Deliverables: integration notebook, network files & report

R or Python integration notebook network exports (SIF / GraphML) PDF/HTML multi omics summary

PDF

Multi-Omics Network Integration & Data Fusion Training | Multi-Layer Networks & Data Fusion Workflows

Multi-Omics Network Integration & Data Fusion — Hands-on