In the present work, QSTR modeling was conducted for microalga Pseudokirchneriella subcapitata using a data set of 271 molecules belonging to different types of chemical classes for the prediction of EC₅₀ for 72 hr based assays. The balanced QSTR model encompasses seven easily interpretable molecular descriptors and possesses statistical robustness with high predictive ability. This Genetic Algorithm Multi-linear regression (GA-MLR) model was subjected to internal validation, Y-randomization test, applicability domain analysis, and external validation as per the recommended OECD guidelines. The newly developed model fulfilled the threshold values for more than 20 recommended validation parameters including R² = 0.72, Q²_LOO = 0.70, etc. The developed QSTR model was successful in identifying the type of hybridization or specific type of atoms of previously reported and newer structural alerts. Thus, the model could be useful for data gap filling and expanding mechanistic interpretation of toxicity for different chemicals.

在目前的工作中，使用属于不同类型化学类别的 271 个分子的数据集对微藻Pseudokirchneriella subcapitata进行 QSTR 建模，用于预测基于 72 小时的测定的 EC ₅₀。平衡的 QSTR 模型包含七个易于解释的分子描述符，并具有高预测能力的统计稳健性。该遗传算法多元线性回归 (GA-MLR) 模型按照推荐的 OECD 指南进行了内部验证、Y 随机化测试、适用性域分析和外部验证。新开发的模型满足了 20 多个推荐验证参数的阈值，包括 R ²  = 0.72、Q ² _LOO = 0.70 等。开发的 QSTR 模型成功地识别了先前报告的和较新的结构警报的杂交类型或特定类型的原子。因此，该模型可用于填补数据空白和扩大对不同化学品毒性的机械解释。