Tutorials

The easiest way to get familiar with OmicVerse is to follow along with our tutorials. Most notebooks are designed to work in Google Colab with minimal setup.

• Bulk RNA-seq
  • Upstream
  • Preprocessing
  • Downstream
  • Deconvolution
  • Others
• Metabolomics
  • Metabolomics preprocessing and univariate statistics
  • Multivariate discrimination with PLS-DA and OPLS-DA
  • Metabolite-set enrichment analysis (MSEA)
  • Untargeted LC-MS and mummichog pathway inference
  • Lipidomics with LIPID MAPS and LION
  • Batch effect and drift correction for LC-MS
  • Multi-factor designs — ASCA and linear mixed models
  • Biomarker discovery — univariate AUC + multivariate panel
  • Differential correlation — DGCA
  • Multi-omics integration — metabolomics + RNA-seq with MOFA
  • Real-data case study — MTBLS1 (urine NMR, Type 2 Diabetes)
• Microbiome
  • 16S rRNA amplicon analysis with OmicVerse
  • 16S phylogeny: MAFFT → FastTree → Faith PD + UniFrac
  • DADA2 backend: pure-Python ASV inference
  • Differential abundance: Wilcoxon vs DESeq2 vs ANCOM-BC
  • Cross-cohort 16S meta-analysis
• Single-Cell RNA-seq
  • Alignment
  • Preprocessing
  • Annotation
  • MetaCell
  • Trajectory
  • Cell-Cell Communication
  • Cell Structure
  • Copy-Number Variation
  • Enrichment
  • Velocity
  • Multi-omics
• Multi-Omics
  • Bulk RNA-seq generate ‘interrupted’ cells to interpolate scRNA-seq
  • Bulk RNA-seq to Single RNA-seq
  • Single RNA-seq to Spatial RNA-seq
  • Paired microbe ↔ metabolite integration (Franzosa 2019 IBD)
• Spatial Transcriptomics
  • Preprocessing
  • Clustering
  • Deconvolution
  • Downstream
• Foundation Models
  • Overview
  • Skill-Ready Models
  • Core Models
  • Specialized Models
  • Domain-Specific Models
• Visualization & Plotting
  • Visualization of single cell RNA-seq
  • Visualization of Bulk RNA-seq
  • Palette optimization for publication-quality single-cell & spatial plots
  • Scientific plotting for publication with OmicVerse
  • Color system
  • Circular UMAP with plot1cell