bio-workflows-multi-omics-pipeline

name	bio-workflows-multi-omics-pipeline
description	End-to-end multi-omics integration workflow. Orchestrates data harmonization, MOFA/mixOmics integration, factor interpretation, and downstream analysis across transcriptomics, proteomics, metabolomics, and other modalities. Use when integrating multiple omics datasets.
tool_type	r
primary_tool	MOFA2
workflow	true
depends_on	["multi-omics-integration/data-harmonization","multi-omics-integration/mofa-integration","multi-omics-integration/mixomics-analysis","multi-omics-integration/similarity-network"]

Multi-omics Integration Pipeline

Pipeline Overview

RNA-seq Data ─────┐
                  │
Proteomics Data ──┼──> Data Harmonization ──> Integration ──> Factors/Components
                  │                                                    │
Metabolomics ─────┘                                                    ▼
                        ┌─────────────────────────────────────────────────────┐
                        │           multi-omics-pipeline                      │
                        ├─────────────────────────────────────────────────────┤
                        │  1. Data Preprocessing per Modality                 │
                        │  2. Sample Harmonization (matching samples)         │
                        │  3. Feature Selection/Filtering                     │
                        │  4. Integration (MOFA2 / mixOmics / SNF)            │
                        │  5. Factor/Component Interpretation                 │
                        │  6. Downstream Analysis                             │
                        └─────────────────────────────────────────────────────┘
                                                                       │
                                                                       ▼
                              Integrated Factors + Biomarker Signatures

Complete MOFA2 Workflow

library(MOFA2)
library(MOFAdata)
library(ggplot2)
library(tidyverse)

# === 1. LOAD AND HARMONIZE DATA ===
# RNA-seq data (samples x genes)
rna <- read.csv('rnaseq_normalized.csv', row.names = 1)
cat('RNA:', nrow(rna), 'samples,', ncol(rna), 'genes\n')

# Proteomics data (samples x proteins)
protein <- read.csv('proteomics_normalized.csv', row.names = 1)
cat('Protein:', nrow(protein), 'samples,', ncol(protein), 'proteins\n')

# Metabolomics data (samples x metabolites)
metab <- read.csv( row.names  
cat nrowmetab  ncolmetab 


common_samples  Reduceintersect rownamesrna rownamesprotein rownamesmetab
cat common_samples 


rna  rnacommon_samples 
protein  proteincommon_samples 
metab  metabcommon_samples 



select_variable  data n   
    vars  applydata  var na.rm  
    top_features  sortvars decreasing  n ncoldata
    data top_features


rna_var  select_variablerna n  
protein_var  select_variableprotein n  
metab_var  select_variablemetab n  



data_list  
    RNA  tas.matrixrna_var
    Protein  tas.matrixprotein_var
    Metabolome  tas.matrixmetab_var



mofa  create_mofadata_list


sample_metadata  read.csv
rownamessample_metadata  sample_metadatasample_id
samples_metadatamofa  sample_metadatacommon_samples 



data_opts  get_default_data_optionsmofa
data_optsscale_views    


model_opts  get_default_model_optionsmofa
model_optsnum_factors  15  


train_opts  get_default_training_optionsmofa
train_optsmaxiter  1000
train_optsconvergence_mode  
train_optsseed  42


mofa  prepare_mofamofa data_options  data_opts
                      model_options  model_opts
                      training_options  train_opts

cat
mofa  run_mofamofa outfile   use_basilisk  



plot_variance_explainedmofa max_r2  
ggsave width   height  


factor_values  get_factorsmofa


plot_factor_cormofa color_by  
ggsave width   height  


plot_factormofa factors   color_by   dot_size  
ggsave width   height  



 f   
    cat f 
    weights  get_weightsmofa factors  f as.data.frame  

     view  uniqueweightsview 
        view_weights  weightsweightsview  view 
        view_weights  view_weightsorderview_weightsvalue decreasing   
        cat view  pasteheadview_weightsfeature  collapse   
    



plot_top_weightsmofa view   factors   nfeatures  
ggsave width   height  


libraryclusterProfiler
libraryorg.Hs.eg.db


rna_weights  get_weightsmofa views   factors   
top_genes  sortrna_weights decreasing  


ego  enrichGOgene  top_genes
                OrgDb  org.Hs.eg.db
                keyType  
                ont  
                pvalueCutoff  

dotplotego showCategory  
ggsave width   height  


librarysurvival
librarysurvminer


surv_data  data.frame
    sample  rownamesfactor_values
    factor1  factor_values 
    time  sample_metadatarownamesfactor_values 
    status  sample_metadatarownamesfactor_values 



surv_datafactor1_group  ifelsesurv_datafactor1  mediansurv_datafactor1  


fit  survfitSurvtime status  factor1_group data  surv_data
ggsurvplotfit data  surv_data pval   risk.table  
ggsave width   height  



write.csvfactor_values 


all_weights  get_weightsmofa as.data.frame  
write.csvall_weights  row.names  

cat

mixOmics DIABLO Workflow

library(mixOmics)

# === 1. PREPARE DATA ===
# Same preprocessing as above
X <- list(
    RNA = as.matrix(rna_var),
    Protein = as.matrix(protein_var),
    Metabolome = as.matrix(metab_var)
)

# Outcome variable
Y <- factor(sample_metadata[common_samples, 'condition'])

# === 2. DESIGN MATRIX ===
# Define connections between blocks
design <- matrix(0.1, ncol = length(X), nrow = length(X),
                 dimnames = list(names(X), names(X))
diagdesign  



perf.diablo  perfblock.splsdaX Y ncomp   design  design
                    validation   folds   nrepeat  

ncomp  perf.diablochoice.ncompWeightedVote 
cat ncomp 


test.keepX  
    RNA     
    Protein     
    Metabolome    


tune.diablo  tune.block.splsdaX Y ncomp  ncomp test.keepX  test.keepX
                                  design  design validation   folds  

optimal.keepX  tune.diablochoice.keepX


diablo.model  block.splsdaX Y ncomp  ncomp
                              keepX  optimal.keepX design  design



plotIndivdiablo.model ind.names   legend   title  


plotVardiablo.model var.names   style   legend  


circosPlotdiablo.model cutoff   line  
           color.blocks    


cimDiablodiablo.model color.blocks    
          margins   


perf.final  perfdiablo.model validation   folds   nrepeat  
cat perf.finalWeightedVote.error.rate 


auc.diablo  aurocdiablo.model roc.block   roc.comp  

Similarity Network Fusion (SNF)

library(SNFtool)

# === 1. CREATE SIMILARITY MATRICES ===
# Distance matrices per modality
dist_rna <- dist2(as.matrix(rna_var), as.matrix(rna_var))
dist_protein <- dist2(as.matrix(protein_var), as.matrix(protein_var))
dist_metab <- dist2(as.matrix(metab_var), as.matrix(metab_var))

# Affinity matrices
K <- 20  # Number of neighbors
alpha <- 0.5  # Hyperparameter

aff_rna <- affinityMatrix(dist_rna, K = K, sigma = alpha)
aff_protein <- affinityMatrix(dist_protein, K = K, sigma = alpha)
aff_metab <- affinityMatrix(dist_metab, K = K, sigma  alpha


W  SNFaff_rna aff_protein aff_metab K  K t  


clusters  spectralClusteringW K    
cat tableclusters 



displayClustersWithHeatmapW clusters

QC Checkpoints

Stage	Check	Action if Failed
Sample matching	>80% samples shared	Check sample IDs
Missing values	<20% per modality	Impute or remove
Feature variance	Features vary	Filter low variance
Model convergence	ELBO plateau	Increase iterations
Factor variance	>5% per factor	Keep fewer factors

Workflow Variants

With Missing Samples

# MOFA2 handles missing views gracefully
# Use create_mofa_from_df for unbalanced data
data_long <- rbind(
    data.frame(sample = rownames(rna), view = 'RNA',
               feature = colnames(rna), value = unlist(rna)),
    data.frame(sample = rownames(protein), view = 'Protein',
               feature = colnames(protein), value = unlist(protein))
)
mofa <- create_mofa_from_df(data_long)

Single-cell Multi-omics

# MOFA+ for single-cell
library(MOFA2)
mofa <- create_mofa_from_Seurat(seurat_obj, groups = 'cell_type',
                                 assays = c('RNA', 'ATAC'))

Related Skills

• multi-omics-integration/mofa-integration - MOFA2 details
• multi-omics-integration/mixomics-analysis - mixOmics methods
• multi-omics-integration/similarity-network - SNF method
• multi-omics-integration/data-harmonization - Preprocessing
• pathway-analysis/go-enrichment - Factor interpretation
• differential-expression/batch-correction - Batch effects