Radiosensitizers are aimed to augment tumor cell killing by radiation while having much less effect on normal tissues. Nitroimidazoles and related analogues are efficient radiation sensitivity enhancers, and they particularly work on hypoxic tumor cells. In the current study, we have developed two partial least squares (PLS) regression-based two-dimensional quantitative structure-activity relationship (2D-QSAR) models using a novel class of 84 nitroimidazole compounds to understand their radiosensitization effectiveness (pC 1.6 ). Feature selection was done by genetic algorithm along with stepwise regression, while model validation was performed using various stringent validation criteria following the strict rules of OECD guidelines of QSAR validation. The variables included in the models were obtained from Dragon (version 7.0) and simplex representation of molecular structures (SiRMS) (version 4.1.2.270) software. The developed models were robust, externally predictive, and useful tools to predict the radiosensitization effectiveness of nitroimidazole compounds. True external prediction was carried out using a group of six nitroimidazole derivatives and the model reliability was checked using the Prediction Reliability Indicator tool ( http://dtclab.webs.com/software-tools ). Furthermore, the developed models will give an insight for development of new radiosensitizers with enhanced radiation sensitivity.

中文翻译：

---

探索硝基咪唑作为放射增敏剂：多层特征选择方法在 QSAR 建模中的应用

放射增敏剂旨在通过放射增加杀伤肿瘤细胞，同时对正常组织的影响要小得多。硝基咪唑和相关类似物是有效的辐射敏感性增强剂，它们特别适用于缺氧的肿瘤细胞。在当前的研究中，我们开发了两种基于偏最小二乘 (PLS) 回归的二维定量构效关系 (2D-QSAR) 模型，使用一类新的 84 硝基咪唑化合物来了解它们的放射增敏效果 (pC 1.6)。特征选择是通过遗传算法和逐步回归完成的，而模型验证是使用各种严格的验证标准按照经合组织 QSAR 验证指南的严格规则进行的。模型中包含的变量来自 Dragon（版本 7. 0) 和分子结构的单纯形表示 (SiRMS)（版本 4.1.2.270）软件。开发的模型是强大的、外部预测的和有用的工具，可用于预测硝基咪唑化合物的放射增敏效果。使用一组六种硝基咪唑衍生物进行真实的外部预测，并使用预测可靠性指标工具 (http://dtclab.webs.com/software-tools) 检查模型可靠性。此外，开发的模型将为开发具有增强辐射敏感性的新型放射增敏剂提供见解。使用一组六种硝基咪唑衍生物进行真实的外部预测，并使用预测可靠性指标工具 (http://dtclab.webs.com/software-tools) 检查模型可靠性。此外，开发的模型将为开发具有增强辐射敏感性的新型放射增敏剂提供见解。使用一组六种硝基咪唑衍生物进行真实的外部预测，并使用预测可靠性指标工具 (http://dtclab.webs.com/software-tools) 检查模型可靠性。此外，开发的模型将为开发具有增强辐射敏感性的新型放射增敏剂提供见解。