A New Deep-learning-Based Approach For mRNA Optimization: High Fidelity, Computation Efficiency, and Multiple Optimization Factors

2025-05-29

AI Summary

mRNA sequence optimization must jointly balance fidelity, computational efficiency, and multiple biological objectives—yet existing methods fail to integrate full-lifecycle factors including sequence features, secondary structure, translational elongation kinetics, and tRNA abundance. To address this, we propose RNop: the first end-to-end deep learning framework for mRNA optimization. RNop introduces a novel quadruple specialized loss function (GPLoss, CAILoss, tAILoss, MFELoss), enabling, for the first time, simultaneous optimization of species-specific codon adaptation, tRNA availability, and structural stability under high-fidelity constraints. Trained on >3 million sequences, the model incorporates multi-task learning and biophysically informed feature embeddings, achieving an inference throughput of 47.32 sequences/second. Both in vitro and in vivo experiments demonstrate significantly enhanced functional protein expression. RNop consistently outperforms state-of-the-art methods across all evaluated metrics.

Technology Category

• Machine Learning: Optimization
• Natural Language Processing: Learning & Optimization for NLP
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The mRNA optimization is critical for therapeutic and biotechnological applications, since sequence features directly govern protein expression levels and efficacy. However, current methods face significant challenges in simultaneously achieving three key objectives: (1) fidelity (preventing unintended amino acid changes), (2) computational efficiency (speed and scalability), and (3) the scope of optimization variables considered (multi-objective capability). Furthermore, existing methods often fall short of comprehensively incorporating the factors related to the mRNA lifecycle and translation process, including intrinsic mRNA sequence properties, secondary structure, translation elongation kinetics, and tRNA availability. To address these limitations, we introduce extbf{RNop}, a novel deep learning-based method for mRNA optimization. We collect a large-scale dataset containing over 3 million sequences and design four specialized loss functions, the GPLoss, CAILoss, tAILoss, and MFELoss, which simultaneously enable explicit control over sequence fidelity while optimizing species-specific codon adaptation, tRNA availability, and desirable mRNA secondary structure features. Then, we demonstrate RNop's effectiveness through extensive in silico and in vivo experiments. RNop ensures high sequence fidelity, achieves significant computational throughput up to 47.32 sequences/s, and yields optimized mRNA sequences resulting in a significant increase in protein expression for functional proteins compared to controls. RNop surpasses current methodologies in both quantitative metrics and experimental validation, enlightening a new dawn for efficient and effective mRNA design. Code and models will be available at https://github.com/HudenJear/RPLoss.

Problem

• Achieving high fidelity in mRNA optimization without unintended amino acid changes
• Improving computational efficiency and scalability for mRNA sequence design
• Incorporating multiple optimization factors like codon adaptation and tRNA availability

Innovation

• Deep learning method for mRNA optimization
• Four specialized loss functions for control
• High fidelity and computational efficiency achieved