arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01873q-bio.BM
收藏

Bi-TEAM:一种统一的跨尺度表示学习框架用于化学修饰的生物分子

Bi-TEAM: A Unified Cross-Scale Representation Learning Framework for Chemically Modified Biomolecules

The Chinese University of Hong Kong(香港中文大学);Macao Polytechnic University(澳门理工学院);The Second Xiangya Hospital of Central South University(中南大学湘雅二医院);University of Electronic Science and Technology of China(电子科技大学);Zhejiang University(浙江大学)

Chunbin Gu, Zijun Gao, Mutian He, Jingjie Zhang, Haipeng Wen, Zihao Luo, Xiaorui Wang, Hanqun Cao, Jiajun Bu, Chang-Yu Hsieh, Pheng Ann Heng

AI总结:

Bi-TEAM 通过统一生物语义与化学精度,提供了一种统一的跨尺度表示学习框架,用于化学修饰生物分子的高效建模与预测。

摘要:

蛋白质生化空间的表示学习面临一个艰难的权衡:蛋白质语言模型在捕捉长距离生物语义方面表现出色,但往往忽略了精细的化学细节。相反,化学语言模型编码了原子信息,但缺乏更广泛的序列上下文。为了解决这一问题,我们引入了Bi-TEAM(双门残差空间修改),一种通用框架,它将局部化学变化注入到全局蛋白质上下文中。通过确保对非标准氨基酸、翻译后修饰(PTMs)和拓扑约束的鲁棒性,Bi-TEAM揭示了通常被进化基线所遗漏的功能化学依赖性。机理上,Bi-TEAM将非标准残基映射到其天然对应物,并通过双门残差融合机制注入原子级数据。关键的是,这一过程使用修改感知的提示,确保局部结构变化影响全局功能表示,而无需扩展字母表。我们对十个数据集进行了评估,涵盖化学修饰的肽、PTMs和天然蛋白质。该模型在十个数据集上均优于最先进的基线,实现了在支架相似性划分上的 Matthews 相关系数(MCC)最大提升达 66 百分比点,以及溶血预测准确率增加 350 百分比点。此外,当作为生成建模的 oracle 时,Bi-TEAM 几乎将设计穿透细胞的环状肽的成功率提高了四倍。通过将生物语义与化学精度统一,Bi-TEAM 为驱动机器学习探索肽和蛋白质生化空间提供了灵活的基础。

英文摘要:

Representation learning for protein biochemical space faces a difficult trade-off: protein language models excel at capturing long-range biological semantics but often miss fine-grained chemical details. Conversely, chemical language models encode atomic information but lack broader sequence context. To address this, we introduce Bi-TEAM (Bi-gated Residual Space Modification), a general framework that injects localized chemical variation into global protein contexts. By ensuring robustness against perturbations such as non-canonical amino acids, post-translational modifications (PTMs), and topological constraints, Bi-TEAM uncovers functional chemical dependencies often missed by evolutionary baselines. Mechanistically, Bi-TEAM maps non-canonical residues to their natural counterparts and injects atomic-level data via a bi-gated residual fusion mechanism. Crucially, this process uses modification-aware prompts to ensure that local structural changes influence global functional representations without requiring alphabet expansion. We evaluated Bi-TEAM on ten datasets spanning chemically modified peptides, PTMs, and natural proteins. The model consistently outperformed state-of-the-art baselines, achieving up to a 66 percent improvement in Matthews correlation coefficient (MCC) on scaffold-similarity splits and a 350 percent increase in hemolysis prediction accuracy. Furthermore, when deployed as an oracle for generative modeling, Bi-TEAM nearly quadrupled the success rate for designing cell-penetrating cyclic peptides. By unifying biological semantics with chemical precision, Bi-TEAM provides a versatile foundation for machine learning driven exploration of peptide and protein biochemical space.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑