API reference

Most users only need the scverse API (ecotyper.recovery(), ecotyper.discovery(), ecotyper.EcoTyperModel). ecotyper.workflows mirrors the R wrapper scripts on pandas objects and files, and ecotyper.io reads the R pipeline’s input files. The other modules expose each step of the R pipeline as a function, for custom pipelines and for checking intermediate results against R.

scverse API

recovery	Recover cell states and ecotypes defined by model in new data.
discovery	Discover cell states and ecotypes; returns an in-memory EcoTyperModel.
infer_data_type	Guess the data type of adata.
EcoTyperModel	A discovery result: chosen ranks, per-cell-type states and ecotypes.

File-based and pandas workflows

Recovery

recover_bulk	Recover cell states and ecotypes in bulk samples (adata: samples x genes).
recover_bulk_frame	Bulk recovery on a genes x samples DataFrame (values as read by R).
recover_bulk_files	File-based equivalent of Rscript EcoTyper_recovery_bulk.R -m matrix -a annotation.
recover_scrna	Recover cell states in single cells (adata: cells x genes, raw-scale expression; obs must have CellType and, for ecotypes, Sample).
recover_scrna_frame	scRNA-seq recovery on a genes x cells DataFrame (fread semantics) and a cell annotation with ID, CellType and optionally Sample.
recover_scrna_files	File-based equivalent of Rscript EcoTyper_recovery_scRNA.R.
read_visium	spatial_load_visium_data.R: 10x Visium folder → (genes x spots counts, spot annotation with ID, X (array row), Y (array col)).
recover_visium_frame	Returns (state_results, state_abundances_long, state_abundances, ecotype_abundances).
recover_visium_files	File-based equivalent of Rscript EcoTyper_recovery_visium.R -c config.yml with precomputed fractions.
ecotype_abundances_long	melt(ecotype_data, id.vars = c("ID", "X", "Y", "Sample", "Malignant")).

Discovery

discover_from_profiles	Cell state + ecotype discovery from per-cell-type expression profiles (EcoTyper_discovery_bulk.R steps 3–6 and 8 with CSx HiRes profiles as input, or EcoTyper_discovery_presorted.R with "no filter").
discover_files	File-based discovery from a folder of per-cell-type profiles (CSx HiRes output or presorted profiles) and a sample annotation file.
read_profiles	Per-cell-type profiles <input_dir>/<cell type>.txt (read.delim(row.names = 1)).
write_discovery	Write the R layout <out_dir>/EcoTyper/<name>/<fractions>/....
discover_scrna	scRNA-seq discovery on AnnData (cells x genes, raw-scale expression; obs with CellType and Sample).
discover_scrna_frame	EcoTyper_discovery_scRNA.R on a genes x cells matrix (fread semantics) and a cell annotation with ID, CellType and Sample.
write_discovery_scrna	Write the R layout of a scRNA discovery run.
DiscoveryResult	Results of a discovery run (attribute access to the dict keys).

Modules

ecotyper.api	scverse-style entry points: recovery(), discovery(), infer_data_type().
ecotyper.workflows	High-level workflows mirroring the R wrapper scripts.
ecotyper.io	Readers for EcoTyper's user-facing inputs and conversion to AnnData.
ecotyper.builtin	The prebuilt EcoTyper models (Carcinoma, Lymphoma) by name.
ecotyper.model	EcoTyper discovery results ("models") in the R directory layout.
ecotyper.recovery_steps	Cell state and ecotype recovery (pipeline/state_recovery_*.R, ecotypes_recovery*.R, spatial_states.R, spatial_ecotypes.R).
ecotyper.discovery_steps	Cell state and ecotype discovery from purified (CIBERSORTx HiRes) or presorted profiles: state_discovery_*.R, ecotypes.R, ecotypes_assign_samples.R (bulk and presorted discovery wrappers).
ecotyper.discovery_scrna	scRNA-seq discovery (EcoTyper_discovery_scRNA.R):
ecotyper.nmf	Port of the parts of the R package NMF (v0.28) that EcoTyper uses.
ecotyper.rlayout	Write results in the R pipeline's directory layout and file formats (write.table(x, sep = "\t")), so outputs can be diffed with R's.
ecotyper.validate	Compare output trees of the Python port with the R pipeline's.
ecotyper.cli	ecotyper-py command line, mirroring the R wrapper scripts.
ecotyper.rcompat	R semantics needed for exact parity: RNG and sample, number parsing and formatting, hclust/cutree/dist/silhouette, cor/var/mean with R's long-double accumulation, quantiles, BH, t-test, Wilcoxon, string collation, merge/order.