The blood–brain barrier (BBB) protects the brain from the toxic side effects of drugs and exogenous molecules. However, it is crucial that medications developed for neurological disorders cross into the brain in therapeutic concentrations. Understanding the BBB interaction with drug molecules based on physicochemical property space can guide effective and efficient drug design. An algorithm, designated “BBB Score”, composed of stepwise and polynomial piecewise functions, is herein proposed for predicting BBB penetration based on five physicochemical descriptors: number of aromatic rings, heavy atoms, MWHBN (a descriptor comprising molecular weight, hydrogen bond donor, and hydrogen bond acceptors), topological polar surface area, and pKa. On the basis of statistical analyses of our results, the BBB Score outperformed (AUC = 0.86) currently employed MPO approaches (MPO, AUC = 0.61; MPO_V2, AUC = 0.67). Initial evaluation of physicochemical property space using the BBB Score is a valuable addition to currently available drug design algorithms.

中文翻译：

---

血脑屏障（BBB）得分。

血脑屏障（BBB）保护大脑免受药物和外源分子的毒副作用。然而，至关重要的是，针对神经系统疾病开发的药物以治疗浓度进入大脑。基于理化性质空间了解BBB与药物分子的相互作用可以指导有效和高效的药物设计。本文提出了一种算法，该算法由逐步函数和多项式分段函数组成，称为“ BBB分数”，用于基于五个物理化学描述子来预测BBB渗透：芳环的数量，重原子，MWHBN（包括分子量的描述子，氢键供体，和氢键受体），拓扑极性表面积和pKa。在对结果进行统计分析的基础上，BBB得分优于（AUC = 0。86）目前采用的MPO方法（MPO，AUC = 0.61； MPO_V2，AUC = 0.67）。使用BBB评分对理化性质空间进行初步评估是对当前可用药物设计算法的宝贵补充。