Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length in the batch.

Pad encoded inputs (on left/right and up to predefined length or max length in the batch) Args: encoded_inputs: Dictiona

Pad encoded inputs (on left/right and up to predefined length or max length in the batch) Args: encoded_inputs: Dictiona

Convert normalized gene expression vector to tokenized rank value encoding.

Find the correct padding/truncation strategy with backward compatibility for old arguments (truncation_strategy and pad_to_max_length

Find the correct padding/truncation strategy with backward compatibility for old arguments (truncation_strategy and pad_to_max_length

Return a list of indices so that each slice of :obj:`batch_size` consecutive indices correspond to elements of similar lengths. To do this, t

Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length in the batch.

Initialize in silico perturber stats generator. Parameters ---------- mode : {"goal_state_shift","vs_null","mixture_

Initialize in silico perturber. Parameters ---------- perturb_type : {"delete","overexpress","inhibit","activate"}

Initialize tokenizer. Parameters ---------- custom_attr_name_dict : None, dict Dictionary of custom attr

Initialize embedding extractor. Parameters ---------- model_type : {"Pretrained","GeneClassifier","CellClassifier"}