API Documentation

The SIDISH framework integrates single-cell and bulk RNA-seq data to identify high-risk cells and potential biomarkers. This section provides detailed API documentation for all public functions and classes in the SIDISH module.

Quick Start

To use the SIDISH framework, first import the module:

from SIDISH import SIDISH

Initialise SIDISH

SIDISH(adata, bulk[, device, seed, ...])

SIDISH (Semi-Supervised Iterative Deep Learning for Identifying High-Risk Cells).

SIDISH.SIDISH.SIDISH.init_Phase1(epochs, ...)

Initializes Phase 1: training a Variational Autoencoder (VAE) on single-cell RNA-seq data.

SIDISH.SIDISH.SIDISH.init_Phase2(epochs, ...)

Initializes Phase 2: training a Deep Cox model for survival analysis using bulk RNA-seq data.

Train SIDISH Model

SIDISH.SIDISH.SIDISH.train(iterations, ...)

Trains the SIDISH framework iteratively, refining the identification of High-Risk cells.

Reload Trained SIDISH Model

SIDISH.SIDISH.SIDISH.reload(path[, num_workers])

Reload Trained SIDISH Model

SIDISH.SIDISH.SIDISH.reload(path[, num_workers])

Plotting Functions

SIDISH.SIDISH.SIDISH.plotUMAP(resolution[, ...])

Performs UMAP dimensionality reduction and Leiden clustering on the latent space.

SIDISH.SIDISH.SIDISH.plot_KM([penalizer, ...])

Plot Kaplan-Meier survival curves for High-Risk and background patient groups.

SIDISH.SIDISH.SIDISH.plot_HighRisk_UMAP([...])

SIDISH.SIDISH.SIDISH.plot_CellType_UMAP([...])

Perturbation

SIDISH.SIDISH.SIDISH.run_Perturbation([n_jobs])

SIDISH.SIDISH.SIDISH.analyze_perturbation_effects()