scdynomics.ft_clf_predict

scdynomics.ft_clf_predict(clf_adata: anndata.AnnData = None, clf_adata_path: str = None, mod1_layer: str = None, mod2_layer: str = None, obs_label: str = None, label_dict_path: str = None, token_dict_path: str = '../data/gene_dict/token_dict.json.gz', base_model_ckpt: str = None, tuned_model_ckpt: str = None, outpath: str = None, accelerator: str = 'cpu', seed: int = 42, **kwargs) → tuple

Predict the labels of the data using the fine-tuned classifier.

Parameters:

clf_adata: ad.AnnData (default: None)

The loaded AnnData object to run predictions on.

clf_adata_path: str (default: None)

The path to the AnnData file. Must provide either this or clf_adata.

mod1_layer: str (default: None)

The layer specifying the first modality to use for prediction.

mod2_layer: str (default: None)

The layer specifying the second modality to use for prediction.

obs_label: str (default: None)

The key in adata.obs containing the true labels (used only to generate a classification report).

label_dict_path: str (default: None)

Path to the JSON dictionary mapping text labels to integer classes. Required if obs_label is provided.

token_dict_path: str (default: "../data/gene_dict/token_dict.json.gz")

Path to the token dictionary file.

base_model_ckpt: str (default: None)

Path to the base pretrained foundation model checkpoint.

tuned_model_ckpt: str (default: None)

Path to the fine-tuned classifier checkpoint.

outpath: str (default: None)

File path to save the resulting predictions (and classification report).

accelerator: str (default: "cpu")

The accelerator to be used for training. It can be “auto”, “cuda”, “mps”, or “cpu”.

seed: int (default: 42)

The random seed for reproducibility.

kwargs: dict

Additional keyword arguments.

Returns: tuple

all_preds: dict

A dictionary mapping cell IDs to their predicted class probabilities.

report: dict or None

The sklearn classification report dictionary (if obs_label and label_dict_path were provided).