Using machine learning models trained with bioactive peptides from DBAASP, we designed new non-hemolytic anticancer peptides (ACPs). The subsequently selected hit-compounds A1 and B1 showed IC₅₀ activities with low micromolar range against several cancer cell lines, having adopted amphiphilic α-helical conformations. Further biological evaluations revealed membranolytic and mitochondria targeting properties of selected anticancer peptides.

中文翻译：

---

机器学习引导发现非溶血性膜破坏性抗癌肽

使用使用 DBAASP 的生物活性肽训练的机器学习模型，我们设计了新的非溶血性抗癌肽 (ACP)。随后选择的命中化合物A1和B1显示出对几种癌细胞系具有低微摩尔范围的IC _{50活性，采用两亲性 α-螺旋构象。}进一步的生物学评估揭示了所选抗癌肽的膜溶解和线粒体靶向特性。