A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding

TL;DR

This paper introduces a new dataset and benchmark for evaluating large language models' ability to understand proteins, demonstrating that with specialized training, LLMs can surpass existing models like GPT-4 in protein comprehension tasks.

Contribution

The authors created ProteinLMDataset and ProteinLMBench, enabling effective pretraining, fine-tuning, and evaluation of LLMs for protein understanding, a novel approach in this domain.

Findings

InternLM2-7B outperforms GPT-4 on ProteinLMBench

ProteinLMDataset contains 17.46 billion tokens for pretraining

ProteinLMBench includes 944 manually verified questions

Abstract

The parallels between protein sequences and natural language in their sequential structures have inspired the application of large language models (LLMs) to protein understanding. Despite the success of LLMs in NLP, their effectiveness in comprehending protein sequences remains an open question, largely due to the absence of datasets linking protein sequences to descriptive text. Researchers have then attempted to adapt LLMs for protein understanding by integrating a protein sequence encoder with a pre-trained LLM. However, this adaptation raises a fundamental question: "Can LLMs, originally designed for NLP, effectively comprehend protein sequences as a form of language?" Current datasets fall short in addressing this question due to the lack of a direct correlation between protein sequences and corresponding text descriptions, limiting the ability to train and evaluate LLMs for protein understanding effectively. To bridge this gap, we introduce ProteinLMDataset, a dataset specifically designed for further self-supervised pretraining and supervised fine-tuning (SFT) of LLMs to enhance their capability for protein sequence comprehension. Specifically, ProteinLMDataset includes 17.46 billion tokens for pretraining and 893,000 instructions for SFT. Additionally, we present ProteinLMBench, the first benchmark dataset consisting of 944 manually verified multiple-choice questions for assessing the protein understanding capabilities of LLMs. ProteinLMBench incorporates protein-related details and sequences in multiple languages, establishing a new standard for evaluating LLMs' abilities in protein comprehension. The large language model InternLM2-7B, pretrained and fine-tuned on the ProteinLMDataset, outperforms GPT-4 on ProteinLMBench, achieving the highest accuracy score.