API Reference

This section provides detailed API documentation for the modules, classes, and functions in the scDynOmics package.

scdynomics.Masked_Pretrainer(*args, **kwargs)	Pretrainer module with input masking and reconstruction for self-supervised learning.
scdynomics.bimodal_pretrain(config_path, ...)	Pretraining pipeline for bimodal data
scdynomics.FT_Encoder(*args, **kwargs)	Fine-Tuning Encoder that adapts a pretrained model for downstream tasks.
scdynomics.FT_Masked_Tuner(*args, **kwargs)	Fine-tuning module utilizing masked reconstruction with Parameter-Efficient Fine-Tuning (PEFT).
scdynomics.FT_MLP_Classifier(*args, **kwargs)	Supervised Classification Tuner Using MLP Modules over a foundation model.
scdynomics.ft_kfold_classification(...[, ...])	Classification pipeline for multimodal or monomodal data with k-fold cross validation.
scdynomics.ft_clf_predict([clf_adata, ...])	Predict the labels of the data using the fine-tuned classifier.
scdynomics.ft_clf_explain([clf_adata, ...])	Explain the fine-tuned classifier's predictions using integrated gradients.
scdynomics.utils	Utilities for scDynOmics