Li Ting, Fan Henghui, Zhao Jianping, Yang Xiaomei, Xia Junfeng
College of Mathematics and Systems Science, Xinjiang University, No. 777 Huarui Road, Shuimogou District, Urumqi, Xinjiang Uygur Autonomous Region 830046, China.
Institutes of Physical Science and Information Technology, Anhui University, No. 111 Jiulong Road, Economic and Technological Development Zone, Hefei, Anhui Province 230601, China.
Brief Bioinform. 2025 May 1;26(3). doi: 10.1093/bib/bbaf274.
Identifying multifunctional therapeutic peptides (MFTP) is an important yet complex challenge in the realm of peptide recognition. Unlike monofunctional peptides, MFTP classification requires discerning fine-grained labeling information associated with amino acids, making it more intricate. Existing methods often ignore the nuanced semantics of these labels and fail to fully explore the interplay between peptide sequences and their labels. To address these issues, we propose a multilabel classification method named MultiPep-DLCL. This method uses a deep learning-based model architecture to translate peptide sequences into sequence features by learning the local and global dependencies of multifunctional therapeutic peptide sequences. Additionally, the Label-Sequence Fusion Transformer is employed to efficiently learn high-quality label embeddings by mining effective information from peptide sequences. Finally, the correspondence between sequence features and label embeddings is strengthened through label-sequence contrastive learning. To tackle dataset imbalance, MultiPep-DLCL integrates a multilabel focal dice loss function alongside the traditional cross-entropy loss function. Experimental results demonstrate that the MultiPep-DLCL significantly outperforms existing methods in MFTP recognition.
识别多功能治疗性肽（MFTP）是肽识别领域一项重要但复杂的挑战。与单功能肽不同，MFTP分类需要辨别与氨基酸相关的细粒度标签信息，这使其更加复杂。现有方法往往忽略这些标签的细微语义，并且未能充分探索肽序列与其标签之间的相互作用。为了解决这些问题，我们提出了一种名为MultiPep-DLCL的多标签分类方法。该方法使用基于深度学习的模型架构，通过学习多功能治疗性肽序列的局部和全局依赖性，将肽序列转化为序列特征。此外，标签-序列融合Transformer通过从肽序列中挖掘有效信息，来高效学习高质量标签嵌入。最后，通过标签-序列对比学习加强序列特征与标签嵌入之间的对应关系。为了解决数据集不平衡问题，MultiPep-DLCL在传统交叉熵损失函数的基础上，集成了多标签焦点骰子损失函数。实验结果表明，在MFTP识别方面，MultiPep-DLCL显著优于现有方法。
