Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models

TL;DR

This paper introduces Biology-Instructions, a large-scale dataset and benchmark for training and evaluating large language models on multi-omics biological sequences, aiming to improve their understanding and reasoning in complex biological tasks.

Contribution

It provides the first instruction-tuning dataset for multi-omics sequences and proposes ChatMultiOmics, a novel training pipeline that enhances LLMs' biological understanding.

Findings

Current LLMs perform poorly on multi-omics tasks without specialized training.

ChatMultiOmics achieves superior performance on biological understanding tasks.

The dataset and baseline are publicly available for future research.

Abstract

Large language models (LLMs) have shown remarkable capabilities in general domains, but their application to multi-omics biology remains underexplored. To address this gap, we introduce Biology-Instructions, the first large-scale instruction-tuning dataset for multi-omics biological sequences, including DNA, RNA, proteins, and multi-molecules. This dataset bridges LLMs and complex biological sequence-related tasks, enhancing their versatility and reasoning while maintaining conversational fluency. We also highlight significant limitations of current state-of-the-art LLMs on multi-omics tasks without specialized training. To overcome this, we propose ChatMultiOmics, a strong baseline with a novel three-stage training pipeline, demonstrating superior biological understanding through Biology-Instructions. Both resources are publicly available, paving the way for better integration of LLMs in multi-omics analysis. The Biology-Instructions is publicly available at: https://github.com/hhnqqq/Biology-Instructions.