用检测思路预测酶功能，能自动找关键氨基酸片段并解释结果。
Interpretable Enzyme Function Prediction via Residue-Level Detection
- 将酶功能预测转为检测任务，用可学习查询提取局部特征。
- 在多个数据集上比现有方法准确率提升5%以上，最高达12.3%。
- 能可视化识别不同功能对应的氨基酸区域，适合生物医学研究者。
从酶序列预测多个由酶委员会（EC）编号标记的功能具有重要意义，但因其稀疏多标签分类特性而面临挑战——每个酶通常仅关联6000多个可能的EC编号中的少数几个。现有机器学习方法通常为每个酶学习固定全局表示以分类所有功能，缺乏可解释性，且某些功能特异的局部残基片段信息可能被掩盖。本文提出一种基于注意力机制的框架ProtDETR（Protein Detection Transformer），将酶功能预测视为检测问题。它使用一组可学习的功能查询，自适应地从残基级特征序列中提取不同的局部表示以预测不同的EC编号。ProtDETR不仅显著优于现有深度学习方法，还在跨注意力机制下提供了自动检测不同功能对应局部区域的新可解释视角。代码已开源：https://github.com/yangzhao1230/ProtDETR。
原文摘要 · Abstract (English)
Predicting multiple functions labeled with Enzyme Commission (EC) numbers from the enzyme sequence is of great significance but remains a challenge due to its sparse multi-label classification nature, i.e., each enzyme is typically associated with only a few labels out of more than 6000 possible EC numbers. However, existing machine learning algorithms generally learn a fixed global representation for each enzyme to classify all functions, thereby they lack interpretability and the fine-grained information of some function-specific local residue fragments may be overwhelmed. Here we present an attention-based framework, namely ProtDETR (Protein Detection Transformer), by casting enzyme function prediction as a detection problem. It uses a set of learnable functional queries to adaptatively extract different local representations from the sequence of residue-level features for predicting different EC numbers. ProtDETR not only significantly outperforms existing deep learning-based enzyme function prediction methods, but also provides a new interpretable perspective on automatically detecting different local regions for identifying different functions through cross-attentions between queries and residue-level features. Code is available at https://github.com/yangzhao1230/ProtDETR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。