Open-source tools for single-cell biology
Analyse large datasets and reuse public studies to answer new biological questions. Nygen tools help you trace how results were produced and examine the evidence for biological interpretations.
-
Analyse single cell data across modalities, scaling to 100 million cells with fast, memory efficient CPU processing. Combine remote atlases into virtual datasets without copying data, with full provenance tracking.
pip install cytearc -
Analyse bulk and pseudobulk omics data with over 20 statistical methods in Python. Test gene expression, cell proportions and gene sets, or perform meta analysis across studies.
pip install cytepool -
Queryable catalogue covering ~180 million cells. Connect to any dataset directly from CyteArc for reanalysis, mapping or visualisation, without downloading it in full.
pip install cytebase -
Identify cell types and states in AnnData, with supporting biological evidence. Outperformed SingleR, CellTypist and GPTCellType in benchmarks, with ~5× GPTCellType’s annotation agreement score.
pip install cytetype -
Trace cell identities from broad lineages to specific types across 24 species. Over 3,000 cell type entries provide the hierarchies, markers and biological descriptions used by CyteType.
-
Compare cell type labels in an embedding space anchored to the Cell Ontology. Quantify agreement across methods and studies, accounting for differences in names, specificity and mixed cell identities.
https://cyteonto.nygen.io/compare -
Identify cell types and states in Seurat with CyteType. Keep labels, confidence assessments and supporting biological evidence in your Seurat object.
devtools::install_github("NygenAnalytics/CyteTypeR") -
CyteLM
A fast, locally deployable language model, fine tuned for single cell knowledge work. Currently in development.
-
CyteTarget
Discover and prioritise drug targets by combining single cell data, genetics and literature to assess disease relevance, tractability and safety. Currently in development.
Using an AI assistant? Point it at docs.nygen.io/llms.txt.