Namespace molcrawl.protein_sequence.dataset

Sub-modules

molcrawl.protein_sequence.dataset.download_proteingym

Download ProteinGym v1.3 DMS substitution data for fine-tuning …

molcrawl.protein_sequence.dataset.prepare_gpt2
molcrawl.protein_sequence.dataset.prepare_proteingym

ProteinGym Dataset Preparation Script for GPT-2 / BERT Fine-tuning …

molcrawl.protein_sequence.dataset.tokenizer
molcrawl.protein_sequence.dataset.uniprot