深度学习
稳健性(进化)
人工智能
生物信息学
溶血
计算机科学
更安全的
机器学习
毒性
二元分类
急性毒性
训练集
优先次序
桥接(联网)
肽
模式识别(心理学)
计算生物学
数学
数据挖掘
模型验证
数据建模
工程类
序列(生物学)
二进制数
作者
Peng Qiu,Hanqi Feng,Meng-Chun Zhang,Barnabas Poczos
标识
DOI:10.1109/bibm66473.2025.11357112
摘要
In antimicrobial peptide development, red-blood-cell lysis ($\text{HC}_{50}$) is the principal safety barrier, but existing in silico tools stop at a binary toxicity classification. Here we propose a new method, AmpLyze, that closes this gap by predicting the actual $\text{HC}_{50}$ value from protein sequence alone and explaining the residues that drive toxicity. The model couples residue-level ProtT5/ESM2 embeddings with sequence-level descriptors in dual local and global branches, aligned by a cross-attention module and trained with log-cosh loss for robustness to assay noise. The optimal AmpLyze model reaches a PCC of 0.756 and an MSE of 0.987, outperforming classical regressors and the state-of-the-art. Ablations confirm that both branches are essential, and cross-attention adds a further $1 \% \text{PCC}$ and 3% MSE improvement. Expected-Gradients attributions reveal known toxicity hotspots and suggest safer substitutions. By turning hemolysis assessment into a quantitative, sequence-based, and interpretable prediction, AmpLyze facilitates AMP design and offers a practical tool for early-stage toxicity screening.
科研通智能强力驱动
Strongly Powered by AbleSci AI