ProteinLMDataset

The ProteinLMDataset is a dataset containing 17.46 billion tokens of text and protein sequences used for self-supervised pretraining and supervised fine-tuning of models in protein engineering tasks.

Papers using ProteinLMDataset (2)

A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding2024 · 9 citesTourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering2024 · 5 cites