跳至主導覽 跳至搜尋 跳過主要內容

Stack-DCL: A Density-Aware and Local-Geometry Stacking Ensemble for Cell-Penetrating and Quorum-Sensing Peptide Classification

  • Xiaorui Kang
  • , Jinjin Li
  • , Chan Tong Lam
  • , Quan Zou
  • , Changhang Lin
  • , Leyi Wei
  • Macao Polytechnic University
  • University of Electronic Science and Technology of China

研究成果: Article › 同儕審查

摘要

Cell-penetrating peptides (CPPs) and quorum-sensing peptides (QSPs) represent peptide functions related to intracellular delivery and microbial signaling. Sequence-based prediction remains difficult because benchmark embeddings often show uneven local support, overlapping class regions, and high dimensionality. A single classifier may therefore miss either local or global structure. We propose Stack-DCL, an out-of-fold stacking framework for CPP and QSP classification with fixed UniRep embeddings. Stack-DCL combines a density-aware weighted random forest, a cosine-neighborhood model, and an L2-regularized logistic regression classifier. The meta-learner is also logistic regression and fuses only positive-class probabilities generated from held-out folds, which reduces fusion-stage leakage. On benchmark train/test splits with five-fold cross-validation on training data and final held-out testing, Stack-DCL achieves independent-test AUC values of 0.980 for QSP and 0.974 for CPP. Ablation results indicate that the three branches capture local support, directional neighborhood similarity, and global linear separability as different representation-level signals. These results support Stack-DCL as a benchmark-level stacking design for the two evaluated peptide tasks.

原文English
頁(從 - 到)4316-4326
頁數11
期刊ACS Synthetic Biology
卷15
發行號10
DOIs
出版品狀態Published - 16 10月 2026

指紋

深入研究「Stack-DCL: A Density-Aware and Local-Geometry Stacking Ensemble for Cell-Penetrating and Quorum-Sensing Peptide Classification」主題。共同形成了獨特的指紋。

引用此