CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

2024-08-21

arXiv.org

AI Summary

This study addresses the limited accuracy in predicting protein–RNA binding affinity and mutational effects. We propose Co-Former, the first cross-modal collaborative modeling paradigm: it integrates pretrained protein and RNA language models, introduces a bi-scope pretraining strategy, and enables sequence–structure multimodal joint encoding. We release PRA310—the first large-scale benchmark dataset comprising 310 protein–RNA complexes and over 10,000 affinity measurements. Co-Former achieves state-of-the-art performance across multiple standard benchmarks, accurately predicting both wild-type and mutant binding affinities. Ablation studies confirm the efficacy of both model and data scaling. Our core contributions are (i) a novel cross-biomodal collaborative representation learning framework and (ii) a scalable pretraining–fine-tuning paradigm tailored for protein–RNA interaction modeling.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

Problem

• Protein-RNA binding
• Prediction accuracy
• Mutation impact

Innovation

• CoPRA
• Co-Former
• Mutation Impact Prediction