User API

Import OmicVerse as:

import omicverse as ov

Data IO

read	Read common omics file formats into AnnData or pandas DataFrame.
io.read_h5ad	Read an .h5ad file.
io.read_h5ad	Read an .h5ad file.
io.read_10x_h5	Read a 10x Genomics HDF5 matrix file.
io.read_10x_mtx	Read a 10x Genomics Matrix Market directory.
io.read_nanostring	Read Nanostring formatted dataset.
io.read_visium_hd	Read 10x Visium HD outputs with a single entry point.

Preprocessing (pp)

Quality control & filtering

pp.qc	Perform quality control on a dictionary of AnnData objects.
pp.filter_cells	Filter cell outliers based on counts and numbers of genes expressed.
pp.filter_genes	Filter genes based on number of cells or counts.
pp.scrublet	Predict cell doublets using Scrublet with optional GPU acceleration.

Normalisation & feature selection

pp.normalize_total	Normalize counts per cell.
pp.log1p	Log-transform expression values with log(1 + x).
pp.highly_variable_genes	Run HVG detection and write flags/statistics into adata.var.
pp.highly_variable_features	Select highly variable features (HVF/HVG) for downstream modeling.
pp.normalize_pearson_residuals	Normalize count matrix using Pearson residuals.
pp.recover_counts	Given log-normalized gene expression data, recover the raw read/UMI counts by inferring the unknown size factors.

Dimensionality reduction & graph

pp.pca	Performs Principal Component Analysis (PCA) on the data stored in a scanpy AnnData object.
pp.neighbors	Compute a neighborhood graph of observations [McInnes18].
pp.umap	Run UMAP on AnnData, choosing implementation based on settings.mode, The argument could be found in scanpy.pp.umap
pp.tsne	Compute t-SNE coordinates for cells.
pp.mde	Run MDE (Minimum Distortion Embedding) from a latent representation.

Clustering

pp.leiden	leiden clustering
pp.louvain	Run Louvain clustering on the precomputed kNN graph.

Batch correction & scaling

pp.scale	Scale the input AnnData object.
pp.regress	Regress out technical covariates from each gene.
pp.regress_and_scale	Scale the regressed layer and store it as a new analysis layer.
pp.remove_cc_genes	Remove cell-cycle-correlated genes from highly_variable_features.
pp.score_genes_cell_cycle	Score cell cycle phases using predefined or custom gene sets.

Single-cell (single)

Annotation

single.pySCSA	Automated cell-type annotation using SCSA marker-enrichment scoring.
single.MetaTiME	MetaTiME wrapper for tumor microenvironment cell-state annotation.
single.CellVote	Ensemble cell-type annotation manager with multiple backends.
single.gptcelltype	Annotate cluster cell types with a remote LLM service.
single.gptcelltype_local	Annotate cell types with a local instruction-tuned LLM.
single.CellOntologyMapper	🧬 Cell ontology mapping class using NLP
single.Annotation	Unified single-cell annotation manager for cell-type labeling.
single.AnnotationRef	Reference-based label transfer helper for single-cell annotation.

Trajectory & cell fate

single.TrajInfer	Trajectory inference class for single-cell data analysis.
single.Velo	RNA velocity analysis wrapper for directional cell-state transition inference.
single.Fate	Adaptive ridge-regression framework for pseudotime-associated gene discovery.
single.cytotrace2	Predict developmental potency with CytoTRACE2.

Cell structure

single.MetaCell	SEACells-based metacell construction workflow.
single.DEG	Differential gene-expression testing wrapper for single-cell datasets.
single.SCENIC
single.aucell	Calculate gene signature enrichment scores using AUCell algorithm.
single.geneset_aucell	Calculate the AUC-ell score for a given gene set.
single.cellphonedb_v5	Run CellPhoneDB statistical analysis with proper file handling
single.Drug_Response	Predict drug sensitivity from single-cell transcriptomes using CaDRReS models.

Batch correction & integration

single.Batch	Run MultiMAP to correct batch effect within a single AnnData object.
single.pySIMBA	SIMBA wrapper for single-cell batch integration and graph-embedding construction.
single.Integration	Run MultiMAP to integrate a number of AnnData objects from various multi-omics experiments into a single joint dimensionally reduced space.

Multi-omics

single.pyMOFA	Train MOFA models for latent factor discovery across multiple omics layers.
single.pyMOFAART	Load pretrained MOFA models for downstream factor interpretation.
single.GLUE_pair	Pair RNA and ATAC cells using GLUE latent embeddings and neighbor matching.
single.pyTOSICA	TOSICA wrapper for pathway-informed transformer-based cell-type annotation.

Topic modelling

single.cNMF

Consensus NMF workflow wrapper for robust gene-program discovery.

Bulk RNA-seq (bulk)

bulk.pyDEG	Differential-expression analysis helper for bulk RNA-seq count tables.
bulk.pyGSEA	Gene Set Enrichment Analysis (GSEA) wrapper for ranked gene lists.
bulk.pyPPI	Protein-protein interaction (PPI) analysis wrapper based on STRING.
bulk.pyTCGA	TCGA (The Cancer Genome Atlas) data analysis module.
bulk.Deconvolution	Bulk RNA-seq deconvolution class for inferring cell-type fractions from single-cell references.
bulk.Matrix_ID_mapping	Map gene IDs in the input data to gene symbols using a reference table.
bulk.batch_correction	Perform batch effect correction using ComBat algorithm.
bulk.geneset_enrichment	Perform pathway enrichment analysis using Enrichr-compatible gene-set libraries.

Spatial transcriptomics (space)

space.clusters	Perform clustering analysis on spatial transcriptomics data using multiple methods.
space.Deconvolution	Spatial deconvolution pipeline that aligns scRNA-seq references with spatial transcriptomics.
space.pySTAGATE	A class representing the PyTorch implementation of STAGATE (Spatial Transcriptomics Analysis using Graph Attention autoEncoder).
space.pySTAligner	STAligner for spatial transcriptomics data integration.
space.pySpaceFlow	SpaceFlow spatial flow analysis class.
space.Tangram	Tangram spatial deconvolution class for cell type mapping.
space.STT	Spatial Transition Tensor (STT) analysis class.
space.GASTON	GASTON spatial depth estimation and clustering.
space.Cal_Spatial_Net	Construct spatial neighbor networks for spatial integration.
space.spatial_neighbors	Build a spatial neighborhood graph from coordinates stored in adata.obsm.
space.moranI	Compute Moran's I spatial autocorrelation for gene expression.

Bulk-to-Single (bulk2single)

bulk2single.BulkTrajBlend	Integrate bulk and single-cell information to infer transitional cell-state trajectories.
bulk2single.Bulk2Single	VAE-based bulk-to-single framework for reconstructing pseudo single cells from bulk RNA-seq.
bulk2single.Single2Spatial	Deep-learning mapper that projects single-cell profiles onto spatial coordinates.

Foundation Models (fm)

fm.run	Execute a foundation model task.
fm.list_models	List available single-cell foundation models.
fm.get_registry	Get the global model registry singleton.
fm.describe_model	Get detailed specification for a foundation model.
fm.select_model	Select the best foundation model for a task and dataset.
fm.preprocess_validate	Validate data compatibility with a model and suggest preprocessing.
fm.profile_data	Profile an AnnData file to detect species, gene scheme, and modality.
fm.interpret_results	Generate QA metrics and visualizations for model results.
fm.ModelSpec	Complete specification for a foundation model.
fm.ModelRegistry	Registry of available single-cell foundation models.

Plotting (pl)

Embedding & dimensionality

pl.embedding	Scatter plot for user specified embedding basis (e.g. umap, pca, etc).
pl.embedding_celltype	Plot embedding with celltype color by omicverse.
pl.embedding_density	Plot cluster-specific density on an existing embedding.
pl.embedding_multi	Create embedding scatter plots for multi-modal data (MuData) or single-cell data.
pl.embedding_atlas	Render large-scale embeddings with Datashader.
pl.pca	Plot PCA embedding.
pl.umap	Plot UMAP embedding.
pl.tsne	Plot t-SNE embedding.

Differential expression

pl.volcano	Create a volcano plot for differential expression analysis.
pl.marker_heatmap	Create a dot plot heatmap showing marker gene expression using PyComplexHeatmap.
pl.rank_genes_groups_dotplot	Create a dot plot from rank_genes_groups results.
pl.dotplot	Make a dot plot of the expression values of var_names.
pl.markers_dotplot	Dot plot of marker genes — clean drop-in for rank_genes_groups_dotplot().

Cell proportion & composition

pl.cellproportion	Plot cell proportion of each cell type in each visual cluster.
pl.cellstackarea	Plot the cell type percentage in each groupby category
pl.venn	Create a Venn diagram to visualize set overlaps.
pl.bardotplot	Create a combined bar-and-dot summary plot by groups.

Distribution

pl.violin	Enhanced violin plot compatible with omicverse's interface.
pl.violin_box
pl.boxplot	Create a boxplot with jittered points to visualize data distribution across categories.
pl.plot_boxplots	Grouped boxplot visualization.

Spatial

pl.spatial	Scatter plot in spatial coordinates, aligned with scanpy.pl.spatial behavior.
pl.plot_spatial	Create spatial plot from Visium data with color gradient and interpolation.
pl.highlight_spatial_region	Mark a rectangular region on a spatial plot.

Cell communication

pl.cpdb_heatmap	Create a dot heatmap of CellPhoneDB interaction counts between cell types.
pl.cpdb_network	Create a circular network plot of CellPhoneDB cell-cell interactions.
pl.cpdb_chord	Create a chord diagram visualization of CellPhoneDB interactions.
pl.CellChatViz	Visualization helper for CellPhoneDB cell-cell communication outputs.

Colours & palettes

pl.palette_112	Built-in mutable sequence.
pl.palette_28	Built-in mutable sequence.
pl.sc_color	Built-in mutable sequence.
pl.ForbiddenCity	Forbidden City traditional-color palette utility.
pl.optim_palette	Optimized palette for plotting
pl.colormaps_palette	Returns a colormap palette.

Datasets

datasets.pbmc3k	Load PBMC 3k dataset from URL.
datasets.zebrafish	The zebrafish is from Saunders, et al (2019).
datasets.pancreatic_endocrinogenesis	Pancreatic endocrinogenesis.
datasets.dentate_gyrus	The Dentate Gyrus dataset used in https://github.com/velocyto-team/velocyto-notebooks/blob/master/python/DentateGyrus.ipynb.
datasets.create_mock_dataset	Create a mock single-cell dataset for testing statistical functions.
datasets.predefined_signatures	dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2).