Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework

TL;DR

This paper introduces 2D-ProteinRAG, a novel framework that enhances protein-text question answering by integrating biological workflows with dual-dimensional filtering, improving robustness and generalization to out-of-distribution proteins.

Contribution

The paper presents 2D-ProteinRAG, a new framework that enables LLMs to operate within biological research workflows and employs a dual-dimensional filtering strategy for better information extraction.

Findings

Achieves state-of-the-art performance on biological OOD benchmarks.

Outperforms fine-tuned baselines and other RAG methods.

Demonstrates robustness and scalability in real-world scenarios.

Abstract

Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language. The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) that efficiently leverages biological databases and facilitates reasoning offers a potent approach for it. However, constrained by the standard RAG pipeline, these models often rely on curated, static datasets instead of expert-proven biological workflows, lacking the fine-grained information processing and struggling to generalize to novel (OOD) proteins. To bridge this gap, we propose 2D-ProteinRAG, a novel framework that empowers LLMs to operate within the gold-standard biological research workflow (BLAST). To further extract high-quality information from noisy retrieval contexts, we introduce a dual-dimensional (2D) filtering strategy following the expert analytical paradigms. Horizontal Fine-grained Attribute Alignment utilizes a lightweight, intent-aware discriminative filter to prune irrelevant metadata and align database entries with specific user queries. Vertical Homology-based Semantic Denoising resolves functional contradictions and redundancy across multiple homologs via hierarchical clustering. Extensive evaluations on both In-Distribution and diverse biological OOD benchmarks demonstrate that 2D-ProteinRAG consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods. Our results validate the framework's robustness and scalability, providing a practical solution for interpreting protein functions in real-world scientific scenarios.