ecotyper.model

EcoTyper discovery results (“models”) in the R directory layout.

A model is the folder EcoTyper/<discovery>/<fractions>/ written by the R discovery wrappers (the prebuilt Carcinoma and Lymphoma models ship in this layout) or by ecotyper.workflows. Only the files used by recovery are loaded; numbers are parsed with R’s own read.delim number parser so that recovery starts from exactly the values R sees.

Functions

ecotype_levels(values)	Levels of ecotype_to_factor(values) (lib/misc.R).
load_cell_type(d, cell_type, n_states)
model_ecotypes_table(result)	ecotypes.txt as written by the discovery workflow (the scRNA variant has R's extra Cell type column, ecotypes_scRNA.R:152).
read_W(path)	read.delim("W.txt") with R's number parser.
write_model_files(result, base, *[, heatmap])	Write the files recovery reads from a discovery result into base (<discovery>/<fractions>), byte-identical to the corresponding files of ecotyper.workflows.write_discovery() / write_discovery_scrna.

Classes

CellTypeModel(cell_type, n_states, W, ...[, ...])	Cell states of one cell type (Cell_States/discovery/<ct>/<rank>).
EcoTyperModel(name, fractions, rank_data[, ...])	A discovery result: chosen ranks, per-cell-type states and ecotypes.

class ecotyper.model.CellTypeModel(cell_type, n_states, W, mapping, initial_gene_info, gene_info=None, heatmap_genes=None, path=None)

Bases: object

Cell states of one cell type (Cell_States/discovery/<ct>/<rank>).

Parameters:

• cell_type (str)

• n_states (int)

• W (DataFrame)

• mapping (DataFrame)

• initial_gene_info (DataFrame)

• gene_info (DataFrame | None)

• heatmap_genes (list | None)

• path (Path | None)

cell_type: str

n_states: int

W: DataFrame

mapping: DataFrame

initial_gene_info: DataFrame

gene_info: DataFrame | None = None

heatmap_genes: list | None = None

path: Path | None = None

class ecotyper.model.EcoTyperModel(name, fractions, rank_data, cell_types=<factory>, ecotypes=None, path=None, discovery_result=None)

Bases: object

A discovery result: chosen ranks, per-cell-type states and ecotypes.

Get one from ecotyper.discovery(), load() (a saved model, an R discovery folder, or a built-in model by name: "Carcinoma", "Lymphoma") and pass it to ecotyper.recovery(). save() writes the files recovery needs in the R layout, so a saved model can be used by both this package and the R scripts.

Parameters:

• name (str)

• fractions (str)

• rank_data (DataFrame)

• cell_types (dict)

• ecotypes (DataFrame | None)

• path (Path | None)

• discovery_result (object | None)

name: str

fractions: str

rank_data: DataFrame

cell_types: dict

ecotypes: DataFrame | None = None

path: Path | None = None

discovery_result: object | None = None

full in-memory discovery result (ecotyper.workflows.DiscoveryResult) when the model comes from ecotyper.discovery(); not saved

property cell_type_order: list[str]

property n_states: dict

Cell type → number of cell states.

property ecotype_names: list[str]

classmethod from_discovery(result, name='custom', fractions=None)

Model from an in-memory discovery result (discover_from_profiles / discover_scrna_frame).

The R pipeline hands discovery results to recovery through text files (15 significant digits). To stay exact, the model tables take the same text round trip here (through a temporary folder that is removed again), so recovery with this model equals recovery with the model written by the file-based workflow.

Parameters:

• name (str)

• fractions (str | None)

Return type:

EcoTyperModel

save(path, *, heatmap=True)

Write the model to path (the R <discovery>/<fractions> folder layout).

Load it back with EcoTyperModel.load(path). With heatmap the (large) heatmap_data.txt/heatmap_top_ann.txt files that the R recovery scripts use for their heatmap plots are written too, when available.

Parameters:

heatmap (bool)

Return type:

Path

classmethod load(root, discovery=None, fractions=None)

Load a model.

• load("Carcinoma") / load("Lymphoma"): a built-in model (see ecotyper.builtin; downloaded and cached on first use);

• load(path): a folder written by save() or an R EcoTyper/<discovery>/<fractions> folder (contains Analysis/);

• load(root, discovery, fractions): <root>/<discovery>/<fractions> (fractions defaults to <discovery>_Fractions).

Parameters:

• discovery (str | None)

• fractions (str | None)

Return type:

EcoTyperModel

ecotyper.model.read_W(path)

read.delim("W.txt") with R’s number parser.

Return type:

DataFrame

ecotyper.model.load_cell_type(d, cell_type, n_states)

Parameters:

• d (Path)

• cell_type (str)

• n_states (int)

Return type:

CellTypeModel

ecotyper.model.ecotype_levels(values)

Levels of ecotype_to_factor(values) (lib/misc.R).

Return type:

list[str]

ecotyper.model.model_ecotypes_table(result)

ecotypes.txt as written by the discovery workflow (the scRNA variant has R’s extra Cell type column, ecotypes_scRNA.R:152).

Return type:

DataFrame

ecotyper.model.write_model_files(result, base, *, heatmap=True)

Write the files recovery reads from a discovery result into base (<discovery>/<fractions>), byte-identical to the corresponding files of ecotyper.workflows.write_discovery() / write_discovery_scrna.

Parameters:

heatmap (bool)

Return type:

Path