GFP Dataset¶

The GFP (Green Fluorescent Protein) dataset implementation. This dataset contains protein sequences and their corresponding fluorescence measurements, commonly used for benchmarking protein engineering methods.

class alf_tools.datasets.gfp.GFP(config)[source]¶

Bases: BaseDataset

GFP dataset class.

load_dataset()[source]¶

Load GFP dataset from local file or download from URL if not present. Clean dataset and return as HF dataset.

Return type:: LabelledCandidates
Returns:: A LabelledCandidates object containing the GFP data.
Raises:: FileNotFoundError – If the GFP dataset file is not found.