omicverse

Two adjacent LC-MS workflows on AnnData — (1) untargeted metabolomics with m/z-based peak annotation, mummichog pathway inference and adduct-ppm matching, and (2) lipidomics with LIPID MAPS shorthand parsing, lipid-class aggregation, and LION term enrichment. Use when converting `t_metabol_04_untargeted` or `t_metabol_05_lipidomics` into a reusable skill, when the input feature IDs encode `m/z`/`RT`, or when the var_names look like `PC 34:1` / `Cer d18:1/24:0` / `TAG 54:3`.

Bulk RNA-seq DEG pipeline: gene ID mapping, DESeq2 normalization, statistical testing, volcano plots, and pathway enrichment in OmicVerse.

End-to-end bulk RNA-seq quantification with omicverse's alignment module — SRA download, fastp QC, two interchangeable quantification paths (STAR + featureCount, OR alignment-free kb-python with technology='BULK'), and wiring into `ov.bulk.pyDEG` DESeq2. Single-cell kb-python (10XV2/10XV3) is out of scope — use the `single-cell-kb-alignment` skill instead.

CellRank fate maps from RNA velocity. Combine VelocityKernel + ConnectivityKernel into a transition matrix, fit a GPCCA estimator, predict terminal states, and produce per-cell fate probabilities. Visualise with `ov.pl.branch_streamplot` and feed branch-resolved gene-trends into `ov.single.dynamic_features` / `ov.pl.dynamic_trends` / `ov.pl.dynamic_heatmap`. Use after RNA velocity is computed (scvelo / dynamo / latentvelo / graphvelo) and before reporting fate probabilities or marker dynamics.

Run OmicVerse single-cell NMF program discovery as a reusable, triggerable skill — both the classical Python `ov.single.cNMF` (consensus NMF with CPU/GPU factorization, K-selection, RFC labelling) and the Rust-backed `ov.single.NMF` (fast `nmf-rs` backend: dnmf default, Brunet-style K-selection with stability-drop auto-K, cNMF-style consensus heatmap, RFC labels). Use when fitting consensus NMF gene programs on single-cell AnnData, choosing K, building consensus, or converting normalized usage programs into hard cluster labels.

Monocle2-style single-cell trajectory analysis on AnnData via the `ov.single.Monocle` class - DDRTree pseudotime + branch detection + per-gene differential test + BEAM branch-dependent gene discovery, plus the unified `ov.pl.trajectory` / `ov.pl.trajectory_overlay` / `ov.pl.trajectory_tree` plotters and the shared pseudotime visualisations (`branch_streamplot`, `dynamic_heatmap`, `dynamic_trends`). Use when fitting a Monocle2 trajectory on an annotated AnnData, when deriving branch-aware gene trends with `dynamic_features`, or when reproducing `t_traj_monocle2`.

Run the OmicVerse sctour trajectory branch on raw-count single-cell AnnData. Use when adapting the scTour part of an OmicVerse trajectory notebook, or when you need sctour pseudotime, latent space, or vector-field outputs instead of the diffusion_map, slingshot, or palantir branches.

Run or adapt OmicVerse single-cell trajectory inference on cluster-ready AnnData. Use when converting OmicVerse trajectory notebooks into a reusable skill, or when choosing the diffusion_map, slingshot, palantir, PAGA, or Palantir branch-selection branches for developmental ordering and lineage summaries.

OmicVerse plotting: volcano, venn, boxplot, embedding, density, heatmap families, dotplot, convex hull, stacked bar, and Forbidden City color palettes.

CellPhoneDB v5 ligand-receptor analysis, CellChatViz plots, and the newer ccc_heatmap / ccc_network_plot / ccc_stat_plot communication visualizations in OmicVerse.

Cell type annotation: SCSA, MetaTiME, CellVote consensus, CellMatch, GPTAnno, weighted KNN label transfer in OmicVerse.

Bulk RNA-seq batch correction with pyComBat: remove batch effects from merged cohorts, export corrected matrices, and benchmark visualizations.

PyDESeq2 differential expression: ID mapping, DE testing, fold-change thresholding, and GSEA enrichment visualization in OmicVerse.

STRING protein-protein interaction network analysis with pyPPI: query STRING database, build PPI graphs, expand with add_nodes, and visualize styled networks for bulk gene lists.

Turn bulk RNA-seq cohorts into synthetic single-cell datasets using omicverse's Bulk2Single workflow for cell fraction estimation, beta-VAE generation, and quality control comparisons against reference scRNA-seq.

Extend scRNA-seq developmental trajectories with BulkTrajBlend by generating intermediate cells from bulk RNA-seq, training beta-VAE and GNN models, and interpolating missing states.

Bulk RNA-seq batch correction with pyComBat: remove batch effects from merged cohorts, export corrected matrices, and benchmark visualizations.

Bulk RNA-seq DEG pipeline: gene ID mapping, DESeq2 normalization, statistical testing, volcano plots, and pathway enrichment in OmicVerse.

PyDESeq2 differential expression: ID mapping, DE testing, fold-change thresholding, and GSEA enrichment visualization in OmicVerse.

Turn bulk RNA-seq cohorts into synthetic single-cell datasets using omicverse's Bulk2Single workflow for cell fraction estimation, beta-VAE generation, and quality control comparisons against reference scRNA-seq.

Extend scRNA-seq developmental trajectories with BulkTrajBlend by generating intermediate cells from bulk RNA-seq, training beta-VAE and GNN models, and interpolating missing states.

WGCNA co-expression network: soft-threshold, module detection, eigengenes, hub genes, and trait correlation in OmicVerse.

Gene set enrichment analysis with correct geneset format handling. Critical guidance for loading pathway databases and running enrichment in OmicVerse.

OmicVerse plotting: volcano, venn, boxplot, embedding, density, dotplot, convex hull, stacked bar, and Forbidden City color palettes.