starlitnightly/omicverse
Overview
This skill provides OmicVerse-focused data I/O helpers for loading bulk, single-cell, and spatial RNA-seq formats. It replaces common Scanpy and pandas reads with ov.read() and ov.io.* readers that handle h5ad, 10x H5/MTX, Visium, Visium HD, Nanostring, and CSV/TSV robustly. Use these readers in OmicVerse projects to avoid format edge cases and gain spatial geometry and Rust-backend options.
How this skill works
The skill exposes a universal ov.read(path, backend='python') that auto-detects files and routes to specialized readers under ov.io and ov.io.spatial. Readers include read_h5ad, read_10x_h5, read_10x_mtx, spatial.read_visium, read_visium_hd (bin/seg variants), read_nanostring, and read_csv. Many readers auto-detect variants (10x v2/v3, Visium parquet/csv, Nanostring column variants) and provide options for images, scalefactors, segmentation polygons, and Rust-backed h5ad loading.
When to use it
- Loading any .h5ad, .csv, .tsv, or gzipped table into an OmicVerse workflow
- Importing 10x Genomics outputs (H5 or Matrix Market) with correct format detection
- Loading Visium spatial experiments with images, tissue positions, and scalefactors
- Working with Visium HD (binned outputs or cell-segmentation polygons)
- Reading Nanostring/CosMx SMI outputs that require column-name auto-detection
Best practices
- Always call ov.read(path) instead of sc.read or pandas.read_csv in OmicVerse projects
- Validate input paths before calling readers (file/directory existence, expected files in Space Ranger outputs)
- Use ov.io.read_h5ad(..., backed='r') or ov.read(..., backend='rust') for very large h5ad files and remember to close backed objects
- Prefer gex_only=False when you need antibody or guide features from 10x H5 files
- Install optional dependencies (geopandas, shapely) to enable polygon geometry support for Visium HD segmentation
Example use cases
- Load a small h5ad for analysis: adata = ov.read('dataset.h5ad')
- Import 10x HDF5 counts with antibody features: adata = ov.io.read_10x_h5('filtered_feature_bc_matrix.h5', gex_only=False)
- Read Space Ranger Visium with images: adata = ov.io.spatial.read_visium('outs/', load_images=True)
- Open Visium HD segmentation to get WKT polygons: adata = ov.io.read_visium_hd_seg('outs/segmented_outputs/')
- Read Nanostring CosMx outputs with counts and metadata: ov.io.read_nanostring(path, counts_file, meta_file, fov_file=None)
FAQ
ov.read auto-detects by extension: .h5ad returns AnnData, .csv/.tsv/.txt (and gzipped variants) return pandas DataFrame; use format-specific readers for 10x/Visium/Nanostring when needed.
How do I avoid out-of-memory errors on large h5ad files?
Use backed mode via ov.io.read_h5ad(..., backed='r') or the Rust backend ov.read(..., backend='rust') and close backed objects when finished.
I get missing polygons for Visium HD segmentation—what's required?
Install geopandas and shapely (pip install geopandas shapely). Visium HD segmentation requires those libraries to parse GeoJSON polygons into WKT.
19 skills
This skill streamlines OmicVerse data loading by replacing scanpy with ov.io readers for h5ad, 10x, Visium, Nanostring, and CSV formats.
This skill infers gene regulatory networks from scRNA-seq, prunes regulons, and scores regulon activity for cell-type resolution.
This skill helps you run foundation model workflows for single-cell analysis, from embedding to annotation and integration across 22 models with a unified API.
This skill helps you annotate gene results and explore pathways, literature, and drug associations using BioContext's unified Python API.
This skill identifies pseudotime-associated genes driving lineage decisions by adaptive ridge regression and Mellon-based density scoring.
This skill guides end-to-end FASTQ-to-count analysis in OmicVerse, automating download, QC, alignment, quantification, and single-cell workflows.
This skill guides you through proper dictionary-based gene set enrichment in OmicVerse, ensuring correct data formats and error-free analysis.
This skill helps you generate publication-quality matplotlib and seaborn visualizations for bioinformatics data, supporting multi-panel layouts and
This skill exports bioinformatics results and tables to formatted Excel files using openpyxl, running locally for compatibility with all LLM providers.
This skill reconstructs single-cell profiles from bulk RNA-seq using Bulk2Single, trains a beta-VAE, and benchmarks against reference scRNA-seq.
This skill harmonises bulk RNA-seq data across batches using ComBat, exports corrected matrices, and benchmarks pre/post correction visually.
This skill creates professional PDF reports with text, tables, and embedded images using reportlab, enabling local, provider-agnostic analysis documentation.
This skill maps single-cell references to spatial transcriptomics profiles, enabling spot-level reconstruction, marker visualization, and downstream reporting.
This skill guides you through loading TCGA data, initializing metadata, and exporting annotated AnnData while enabling survival analyses.
This skill provides quick, actionable guidance to integrate and visualize single-cell multi-omics data across MOFA, GLUE, SIMBA, TOSICA, and StaVIA.
This skill guides you through bulk RNA-seq differential expression analysis in omicverse, from gene ID mapping to visualization and pathway enrichment.
This skill guides you through single-cell annotation workflows from SCSA to GPTAnno and weighted transfer, enabling accurate cell type labeling.
This skill quantifies ligand-receptor communication in annotated single-cell data using CellPhoneDB v5 and generates CellChat-style visualizations for
This skill helps you query STRING for protein interactions, build PPI networks with pyPPI, and render styled network figures from gene lists.
