### Development Install with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Clones the repository and installs development dependencies using uv.

```bash
git clone https://github.com/qwerty239qwe/scTenifoldpy
cd scTenifoldpy
uv sync --group test --group dev --group docs
```

--------------------------------

### Optional Extras Install with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Installs scTenifoldpy with the 'scanpy' extra using uv.

```bash
uv pip install "scTenifoldpy[scanpy]"
```

--------------------------------

### Fetching remote example datasets

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/1_data.ipynb

Demonstrates how to list and fetch example datasets from a remote repository. Network access is required.

```python
from scTenifold.data import list_data

# Requires network access:
# list_data()
# datasets = fetch_data("AD")
```

--------------------------------

### Build Docs with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Builds the documentation using uv.

```bash
uv run mkdocs build --strict
```

--------------------------------

### Optional Extras Install with pip

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Installs scTenifoldpy with the 'scanpy' extra using pip.

```bash
pip install "scTenifoldpy[scanpy]"
```

--------------------------------

### scTenifoldKnk Initialization and Build

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/quickstart.md

Initializes a scTenifoldKnk object and executes the build() method.

```python
from scTenifold import get_test_df
from scTenifold import scTenifoldKnk

df = get_test_df(n_cells=1000)
sc = scTenifoldKnk(data=df,
                   ko_method="default",
                   ko_genes=["NG-1"],  # the gene you wants to knock out
                   qc_kws={"min_lib_size": 10})
result = sc.build()
```

--------------------------------

### scTenifoldNet Initialization and Build

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/quickstart.md

Initializes a scTenifoldNet object and executes the build() method.

```python
from scTenifold import get_test_df
from scTenifold import scTenifoldNet

df_1, df_2 = get_test_df(n_cells=1000), get_test_df(n_cells=1000)
sc = scTenifoldNet(df_1, df_2, "X", "Y",
                   qc_kws={"min_lib_size": 10})
result = sc.build()
```

--------------------------------

### Hello World Example

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/index.md

A basic example demonstrating how to use the compare_networks function with test data and printing the head of the result.

```python
from scTenifold import compare_networks
from scTenifold.data import get_test_df

x = get_test_df(n_cells=200, n_genes=300, random_state=0)
y = get_test_df(n_cells=200, n_genes=300, random_state=1)

result = compare_networks(
    x, y,
    qc_kws={"min_lib_size": 1},
    network_kws={"n_nets": 3, "n_samp_cells": 100},
)
print(result.head())
```

--------------------------------

### Run Test Suite with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Runs the test suite using uv.

```bash
uv run pytest
```

--------------------------------

### Install scTenifold using pip

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/installation.md

This command installs the scTenifold package using pip.

```console
$ pip install sctenifold
```

--------------------------------

### Parallel Backends example

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Examples of using different parallel backends for network construction.

```python
from scTenifold import make_networks

networks = make_networks(df_1, backend="serial", n_jobs=1)
networks = make_networks(df_1, backend="joblib-loky", n_jobs=4)
```

--------------------------------

### Development Install with pip

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Installs scTenifoldpy in editable mode with development dependencies using pip.

```bash
pip install -e ".[scanpy,parallel-ray,docs]"
pip install pytest pytest-cov ruff build
```

--------------------------------

### Installation with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/index.md

Installs scTenifoldpy using uv for virtual environment and package management.

```bash
uv venv
uv pip install scTenifoldpy
```

--------------------------------

### Example DataFrame creation

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/1_data.ipynb

Demonstrates creating sample expression data as a pandas DataFrame with genes as rows and cells as columns.

```python
import pandas as pd
from scTenifold.data import get_test_df

x = get_test_df(n_cells=80, n_genes=120, random_state=0)
y = get_test_df(n_cells=80, n_genes=120, random_state=1)

x.shape, y.shape
```

--------------------------------

### Build Default Docker Image

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Builds the default Docker image for scTenifoldpy.

```bash
docker build -t sctenifoldpy .
```

--------------------------------

### Build Docker Image with Optional Extras

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Builds a Docker image with specific optional extras included.

```bash
docker build --build-arg EXTRAS=scanpy -t sctenifoldpy:scanpy .
docker build --build-arg EXTRAS=parallel-ray -t sctenifoldpy:ray .
```

--------------------------------

### Installation with pip

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/index.md

Installs scTenifoldpy using pip.

```bash
pip install scTenifoldpy
```

--------------------------------

### High-Level API example

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Example usage of the compare_networks and virtual_knockout high-level APIs.

```python
from scTenifold import compare_networks, virtual_knockout

result = compare_networks(
    df_1,
    df_2,
    qc_kws={"min_lib_size": 10, "plot": False},
    network_kws={"n_nets": 3, "n_samp_cells": 100},
    backend="joblib-threading",
    n_jobs=4,
)

knockout = virtual_knockout(
    df_1,
    ko_genes=["NG-1"],
    qc_kws={"min_lib_size": 10, "min_percent": 0.001},
)
```

--------------------------------

### Step-Wise: ``scTenifoldNet`` / ``scTenifoldKnk``

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/quickstart.md

This code snippet demonstrates the step-wise usage of the `scTenifoldNet` class for pipeline processing. It shows initialization, running individual steps, printing intermediate results, and saving the model.

```python
from scTenifold import scTenifoldNet

model = scTenifoldNet(
    x, y,
    x_label="ctrl", y_label="cond",
    qc_kws={"min_lib_size": 1},
    nc_kws={"n_nets": 3, "n_samp_cells": 100, "backend": "serial"},
)

model.run_step("qc")
model.run_step("nc")
model.run_step("td")
model.run_step("ma")
model.run_step("dr")

print(model.QC_dict["ctrl"].shape)         # genes x cells after QC
print(len(model.network_dict["ctrl"]))     # n_nets PC networks
print(model.tensor_dict["ctrl"].shape)     # genes x genes
print(model.manifold.shape)                # (2 * shared_genes) x d
print(model.d_regulation.head())

model.save("./run-ctrl-vs-cond")
```

--------------------------------

### AnnData Input Examples

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/anndata.md

Examples demonstrating how to use AnnData objects with compare_networks and virtual_knockout functions.

```python
from scTenifold import compare_networks, virtual_knockout

# compare_networks with two AnnData objects
result = compare_networks(adata_x, adata_y, layer="counts")

# virtual_knockout reads adata.X if layer is omitted
result = virtual_knockout(adata, ko_genes=["GeneA"])
```

--------------------------------

### Class API example

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Example usage of the scTenifoldNet class API.

```python
from scTenifold.data import get_test_df
from scTenifold import scTenifoldNet

df_1 = get_test_df(n_cells=1000)
df_2 = get_test_df(n_cells=1000)

sc = scTenifoldNet(
    df_1,
    df_2,
    "X",
    "Y",
    qc_kws={"min_lib_size": 10},
    nc_kws={"backend": "serial", "n_jobs": 1},
)
result = sc.build()
```

--------------------------------

### Compare Two Conditions: ``compare_networks``

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/quickstart.md

This code snippet demonstrates how to compare two conditions using the `compare_networks` function from the scTenifold library. It includes data loading, network comparison, and printing the head of the results.

```python
from scTenifold import compare_networks
from scTenifold.data import get_test_df

x = get_test_df(n_cells=200, n_genes=300, random_state=0)
y = get_test_df(n_cells=200, n_genes=300, random_state=1)

result = compare_networks(
    x, y,
    x_label="ctrl",
    y_label="cond",
    qc_kws={"min_lib_size": 1},
    network_kws={"n_nets": 3, "n_samp_cells": 100},
    backend="serial",
)

print(result.head())
```

--------------------------------

### Optional extras installation with uv

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Install scTenifoldpy with optional extras like scanpy or parallel-ray using uv.

```bash
uv venv
uv add "scTenifoldpy[scanpy]"
uv add "scTenifoldpy[parallel-ray]"
```

--------------------------------

### Run CLI from Docker Container

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Runs the scTenifold CLI from a Docker container, mounting the current directory.

```bash
docker run --rm -v "$PWD:/workspace" sctenifoldpy scTenifold --help
```

--------------------------------

### Virtual Knockout: ``virtual_knockout``

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/quickstart.md

This code snippet shows how to perform a virtual knockout experiment using the `virtual_knockout` function. It involves loading data, specifying genes to knockout, and printing the sorted results by p-value.

```python
from scTenifold import virtual_knockout
from scTenifold.data import get_test_df

data = get_test_df(n_cells=300, n_genes=300, random_state=0)

result = virtual_knockout(
    data,
    ko_genes=["NG-1"],
    qc_kws={"min_lib_size": 1, "min_exp_avg": 0, "min_exp_sum": 0},
    network_kws={"n_nets": 3, "n_samp_cells": 100},
    ko_method="default",
)

print(result.sort_values("p-value").head())
```

--------------------------------

### CLI commands

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Example commands for using the scTenifold Command Line Interface.

```bash
scTenifold config -t 1 -p ./net_config.yml
scTenifold net -c ./net_config.yml -o ./output_folder
scTenifold knk -c ./knk_config.yml -o ./output_folder
```

--------------------------------

### Run CLI from Docker Container (PowerShell)

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/installation.md

Runs the scTenifold CLI from a Docker container using PowerShell, mounting the current directory.

```powershell
docker run --rm -v "${PWD}:/workspace" sctenifoldpy scTenifold --help
```

--------------------------------

### Optional extras installation with pip

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/README.md

Install scTenifoldpy with optional extras like scanpy or parallel-ray using pip.

```bash
pip install "scTenifoldpy[scanpy]"
pip install "scTenifoldpy[parallel-ray]"
```

--------------------------------

### d_regulation example 1

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Example of calling d_regulation with default parameters.

```python
d_reg_df = d_regulation(ma_df)
```

--------------------------------

### compare_networks usage

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/parallel-backends.md

Example of using the compare_networks function, demonstrating how backend and n_jobs are propagated, and how network_kws can be used.

```python
result = compare_networks(
    x, y,
    backend="joblib-loky",
    n_jobs=8,
    network_kws={"n_nets": 10},   # backend/n_jobs propagated automatically
)
```

--------------------------------

### d_regulation example 2

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Example of calling d_regulation with custom boxcox and chi2 parameters.

```python
d_reg_df = d_regulation(ma_df, boxcox_kws={\"lmbda\": 0}, chi2_kws={\"df\": 1})
```

--------------------------------

### Merging overrides

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/pipeline-steps.md

Example of how to merge keyword arguments into the stored configuration for a step.

```python
model.nc_kws["n_jobs"] = 4
model.run_step("nc")
```

--------------------------------

### Running a single step with overrides

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/pipeline-steps.md

Example of how to run a single pipeline step and pass keyword arguments that override default settings for that specific call.

```python
model.run_step("nc", n_nets=5, backend="joblib-loky", n_jobs=4)
```

--------------------------------

### make_networks usage

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/parallel-backends.md

Example of using the make_networks function with the 'joblib-loky' backend and specifying the number of jobs.

```python
from scTenifold import make_networks

nets = make_networks(data, n_nets=10, backend="joblib-loky", n_jobs=4)
```

--------------------------------

### Inspecting state after a step

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/pipeline-steps.md

Examples of inspecting the populated attributes after running specific pipeline steps.

```python
model.run_step("qc")
print(model.QC_dict["ctrl"].shape)

model.run_step("nc")
print([net.shape for net in model.network_dict["ctrl"]])
```

--------------------------------

### AnnData Round-trip Conversion

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/anndata.md

Example showing how to convert an AnnData object to a pandas DataFrame using anndata_to_dataframe and verifying the index and columns.

```python
import anndata as ad
from scTenifold.core._networks import anndata_to_dataframe

adata = ad.read_h5ad("sample.h5ad")
df = anndata_to_dataframe(adata, layer="counts")
assert df.index.equals(adata.var_names)
assert df.columns.equals(adata.obs_names)
```

--------------------------------

### Data Preparation

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/3_knock_out.ipynb

Imports necessary libraries and loads test data.

```python
from scTenifold import scTenifoldKnk, virtual_knockout
from scTenifold.data import get_test_df

data = get_test_df(n_cells=80, n_genes=40, random_state=2)
ko_genes = ["NG-1"]
```

--------------------------------

### Step-wise workflow using scTenifoldNet class

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/2_build_network.ipynb

Initializes the scTenifoldNet model and runs through the analysis steps sequentially.

```python
model = scTenifoldNet(
    x,
    y,
    x_label="control",
    y_label="condition",
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0},
    nc_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0, "backend": "serial"},
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
)

for step in ["qc", "nc", "td", "ma", "dr"]:
    model.run_step(step)

model.d_regulation.head()
```

--------------------------------

### Build a small result using the class API

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/4_visualization.ipynb

Initializes and builds a scTenifoldNet model with specified parameters for quality control, network construction, tensor decomposition, and manifold alignment.

```python
model = scTenifoldNet(
    x,
    y,
    "control",
    "condition",
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0},
    nc_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0, "backend": "serial"},
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
)
model.build()
```

--------------------------------

### Import necessary libraries and load test data

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/2_build_network.ipynb

Imports scTenifold components and loads sample expression data for two conditions.

```python
from scTenifold import compare_networks, scTenifoldNet
from scTenifold.data import get_test_df

x = get_test_df(n_cells=80, n_genes=40, random_state=0)
y = get_test_df(n_cells=80, n_genes=40, random_state=1)
```

--------------------------------

### Import necessary libraries and load test data

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/4_visualization.ipynb

Imports plotting and data handling functions from scTenifold and loads test dataframes.

```python
%matplotlib inline
from scTenifold import compare_networks, scTenifoldNet
from scTenifold.data import get_test_df
from scTenifold.plotting import plot_hist, plot_network_heatmap, plot_qqplot

x = get_test_df(n_cells=80, n_genes=40, random_state=0)
y = get_test_df(n_cells=80, n_genes=40, random_state=1)
```

--------------------------------

### Displaying gene and cell names

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/1_data.ipynb

Shows how to inspect the first few gene and cell names from the DataFrame.

```python
x.index[:5].tolist(), x.columns[:5].tolist()
```

--------------------------------

### build() Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Runs the entire scTenifoldKnk pipeline.

```python
build() -> DataFrame
```

--------------------------------

### One-call workflow using compare_networks()

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/2_build_network.ipynb

Compares two networks using the `compare_networks` function with specified parameters for a quick analysis.

```python
result = compare_networks(
    x,
    y,
    x_label="control",
    y_label="condition",
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0},
    network_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0},
    backend="serial",
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
)

result.head()
```

--------------------------------

### Run scTenifoldKnk

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/cli.md

Command to run scTenifoldKnk using a specified configuration file.

```shell
python -m scTenifold knk -c ./knk_config.yml -o ./outputs
```

--------------------------------

### load_config() Class Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Constructs a scTenifoldKnk instance from a configuration dictionary, loading data from disk as specified.

```python
load_config(config: Dict[str, object]) -> [scTenifoldKnk](#scTenifold.scTenifoldKnk)
```

--------------------------------

### AnnData to DataFrame conversion

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/1_data.ipynb

Illustrates converting a custom AnnData-like object to a pandas DataFrame using scTenifoldpy's utility function.

```python
from scTenifold.core._networks import anndata_to_dataframe

class MiniAnnData:
    def __init__(self, matrix, obs_names, var_names):
        self.X = matrix
        self.obs_names = obs_names
        self.var_names = var_names
        self.layers = {}

adata = MiniAnnData(x.T.to_numpy(), obs_names=x.columns, var_names=x.index)
converted = anndata_to_dataframe(adata)
converted.equals(x)
```

--------------------------------

### Run scTenifoldNet

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/cli.md

Command to run scTenifoldNet using a specified configuration file.

```shell
python -m scTenifold net -c ./net_config.yml -o ./outputs
```

--------------------------------

### Step-wise workflow

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/3_knock_out.ipynb

Utilizes the class API for a step-by-step workflow, exposing intermediate results.

```python
knk = scTenifoldKnk(
    data=data,
    ko_genes=ko_genes,
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0, "min_exp_avg": 0, "min_exp_sum": 0},
    nc_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0, "backend": "serial"},
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
    ko_method="default",
)

for step in ["qc", "nc", "td", "ko", "ma", "dr"]:
    knk.run_step(step)

knk.d_regulation.head()
```

--------------------------------

### One-call workflow

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/3_knock_out.ipynb

Uses the `virtual_knockout` function for a simplified workflow.

```python
result = virtual_knockout(
    data,
    ko_genes=ko_genes,
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0, "min_exp_avg": 0, "min_exp_sum": 0},
    network_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0},
    ko_method="default",
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
)

result.sort_values("p-value").head()
```

--------------------------------

### Run Workflows

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/cli.md

Commands to execute the scTenifoldNet and scTenifoldKnk workflows using generated configuration files.

```bash
scTenifold net --config net_config.yml --output ./saved_net
scTenifold knk --config knk_config.yml --output ./saved_knk
```

--------------------------------

### get_empty_config() Class Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Returns a blank configuration dictionary for scTenifoldKnk, pre-populated with default values for each step.

```python
get_empty_config() -> Dict[str, object]
```

--------------------------------

### scTenifoldKnk Constructor

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Initializes the scTenifoldKnk class for single-sample virtual knockout analysis. It outlines the pipeline order and parameters for various steps.

```python
class scTenifold.scTenifoldKnk(data: DataFrame | AnnDataLike, strict_lambda: float = 0, ko_method: Literal['default', 'propagation'] = 'default', ko_genes: str | Iterable[str] | None = None, qc_kws: Dict[str, object] | None = None, nc_kws: Dict[str, object] | None = None, td_kws: Dict[str, object] | None = None, ma_kws: Dict[str, object] | None = None, dr_kws: Dict[str, object] | None = None, ko_kws: Dict[str, object] | None = None)
```

--------------------------------

### Generate Config File Template

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/cli.md

Command to generate a configuration file template for scTenifold.

```shell
python -m scTenifold config -t 1 -p ./net_config.yml
```

--------------------------------

### Intermediate model outputs

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/2_build_network.ipynb

Displays shapes of intermediate data structures within the scTenifoldNet model after running the steps.

```python
{
    "qc_shape": model.QC_dict["control"].shape,
    "n_networks": len(model.network_dict["control"]),
    "tensor_shape": model.tensor_dict["control"].shape,
    "manifold_shape": model.manifold.shape,
}
```

--------------------------------

### Generate Configuration Files

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/cli.md

Commands to generate YAML configuration files for scTenifoldNet and scTenifoldKnk.

```bash
scTenifold config --type 1 --path net_config.yml   # scTenifoldNet
scTenifold config --type 2 --path knk_config.yml   # scTenifoldKnk
```

--------------------------------

### scTenifoldNet.load_config() Class Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Constructs a scTenifoldNet object from a configuration dictionary, loading data from specified paths.

```python
load_config(config: Dict[str, object]) -> [scTenifoldNet](#scTenifold.scTenifoldNet)
```

--------------------------------

### scTenifoldNet Class Constructor

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Initializes a two-sample scTenifoldNet workflow. The pipeline includes QC, network construction, tensor decomposition, manifold alignment, and differential regulation.

```python
scTenifoldNet(x_data: DataFrame | AnnDataLike, y_data: DataFrame | AnnDataLike, x_label: str, y_label: str, qc_kws: Dict[str, object] | None = None, nc_kws: Dict[str, object] | None = None, td_kws: Dict[str, object] | None = None, ma_kws: Dict[str, object] | None = None, dr_kws: Dict[str, object] | None = None)
```

--------------------------------

### scTenifoldKnk Pipeline

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/pipeline-steps.md

The sequence of steps in the scTenifoldKnk pipeline, highlighting differences from scTenifoldNet.

```text
data_dict -> qc -> QC_dict -> nc -> network_dict["WT"] -> td -> tensor_dict["WT"] -> ko -> tensor_dict["KO"] -> ma -> manifold -> dr -> d_regulation
```

--------------------------------

### run_step() Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Executes a single step within the scTenifoldKnk pipeline. Steps must be run sequentially.

```python
run_step(step_name: Literal['qc', 'nc', 'td', 'ko', 'ma', 'dr'], **kwargs: object) -> None
```

--------------------------------

### Plot histogram of control data

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/4_visualization.ipynb

Generates and displays a histogram for the control dataset.

```python
plot_hist(x, "control")
```

--------------------------------

### Intermediate Tensor Shapes

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/3_knock_out.ipynb

Displays the shapes of the WT tensor, KO tensor, and manifold.

```python
{
    "wt_tensor": knk.tensor_dict["WT"].shape,
    "ko_tensor": knk.tensor_dict["KO"].shape,
    "manifold": knk.manifold.shape,
}
```

--------------------------------

### scTenifoldNet.run_step() Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Executes a single step within the scTenifoldNet pipeline. Steps must be run sequentially.

```python
run_step(step_name: Literal['qc', 'nc', 'td', 'ma', 'dr'], **kwargs: object) -> None
```

--------------------------------

### Plot network heatmap

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/4_visualization.ipynb

Visualizes the network structure of the control data as a heatmap.

```python
plot_network_heatmap(model.tensor_dict["control"].to_numpy())
```

--------------------------------

### Differential regulation QQ plot

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/4_visualization.ipynb

Generates a QQ plot to visualize the differential regulation between conditions.

```python
plot_qqplot(model.d_regulation)
```

--------------------------------

### scTenifoldNet Pipeline

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/pipeline-steps.md

The sequence of steps in the scTenifoldNet pipeline.

```text
data_dict -> qc -> QC_dict -> nc -> network_dict -> td -> tensor_dict -> ma -> manifold -> dr -> d_regulation
```

--------------------------------

### get_data method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Method to return simulated data packaged for downstream scorers.

```python
def get_data(data_type: str, use_normalized: bool) -> Dict[str, object]
```

--------------------------------

### fetch_data function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Function to fetch and load a remote scTenifold dataset by name.

```python
def fetch_data(ds_name: str, dataset_path: Path = PosixPath('/workspace/input/datasets'), owner: str = 'qwerty239qwe') -> Dict[str, DataFrame]
```

--------------------------------

### list_data function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Function to list available scTenifold datasets.

```python
def list_data(owner: str = 'qwerty239qwe', return_list: bool = True) -> Dict[str, Dict[str, List[str]]] | List[str]
```

--------------------------------

### Reload Model from Disk

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/cli.md

Python code to load a saved scTenifoldNet model from disk and display the head of its d_regulation attribute.

```python
from scTenifold import scTenifoldNet

model = scTenifoldNet.load("./saved_net")
print(model.d_regulation.head())
```

--------------------------------

### Selective Save

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/workflow-output.md

By default save() writes every step that has run. Pass comps to restrict which components are saved.

```python
model.save("./saved_net", comps=["qc", "dr"])
```

--------------------------------

### save_data method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Method to save the simulated count matrix as CSV.

```python
def save_data(file_path: str | Path, use_normalized: bool) -> None
```

--------------------------------

### get_test_df function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Function to generate a test dataframe.

```python
def get_test_df(n_cells: int = 100, n_genes: int = 1000, random_state: int | None = None) -> DataFrame
```

--------------------------------

### save() Method

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Saves the current state of the scTenifoldKnk object, including KO-specific fields, to allow for later reconstruction using the load() method.

```python
save(file_dir: str | Path, comps: str | List[str] = 'all', verbose: bool = True, **kwargs: object) -> None
```

--------------------------------

### read_folder function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Function to read mtx, genes, and barcodes from a directory.

```python
def read_folder(file_dir: str | Path, matrix_fn: str = 'matrix', gene_fn: str = 'genes', barcodes_fn: str = 'barcodes') -> DataFrame
```

--------------------------------

### Saving workflow output

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/workflow-output.md

Persists all populated steps and configuration to disk. The load() function reconstructs the object, including intermediate state, without re-running any step.

```python
scTenifoldNet.save(dir)
scTenifoldKnk.save(dir)
```

--------------------------------

### Reloading workflow output

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/workflow-output.md

Reconstructs the object from a saved directory, including intermediate state.

```python
from scTenifold import scTenifoldNet, scTenifoldKnk

net = scTenifoldNet.load("./saved_net")
knk = scTenifoldKnk.load("./saved_knk")
```

--------------------------------

### read_mtx function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Function to read mtx data from specified files.

```python
def read_mtx(mtx_file_name: str | Path, gene_file_name: str | Path, barcode_file_name: str | Path | None) -> DataFrame
```

--------------------------------

### TestDataGenerator Class

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/scTenifold.data.md

Class for generating test data for cell scoring functions.

```python
class scTenifold.data.TestDataGenerator(n_genes: int = 1000, n_samples: int = 100, pos_eff_ratio: float = 0.3, neg_eff_ratio: float = 0, target_pos: Sequence[str] | None = None, target_neg: Sequence[str] | None = None, n_bins: int = 25, n_ctrl: int = 50, random_state: int = 42)
```

--------------------------------

### sc_QC Function

Source: https://github.com/qwerty239qwe/sctenifoldpy/blob/master/docs/source/api.md

Performs quality control and CPM normalization on single-cell RNA-seq data.

```python
sc_QC(X: DataFrame, min_lib_size: float = 1000, remove_outlier_cells: bool = True, min_percent: float = 0.05, max_mito_ratio: float = 0.1, min_exp_avg: float = 0, min_exp_sum: float = 0) -> DataFrame
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.