Direct or indirect consumption of pesticides and their related products by humans and other living organisms without safe dosing may pose a health risk. The risk may arise after a short/long time which depends on the nature and amount of chemicals consumed. Therefore, the maximum acceptable daily intake of chemicals must be calculated to prevent these risks. In the present work, regression-based quantitative structure–activity relationship (QSAR) models were developed using 39 pesticides with maximum acceptable daily intake (MADI) for humans as the endpoint. From the statistical results (R² = 0.674–0.712, Q_LOO² = 0.553–0.580, Q_(F1)² = 0.544–0.611, and Q_(F2)² = 0.531–0.599), it can be inferred that the developed models were robust, reliable, reproducible, accurate, and predictive. Intelligent Consensus Prediction (ICP) was employed to improve the external predictivity (Q_(F1)² =0.579–0.657 and Q_(F2)² = 0.563–0.647) of the models. Some of the chemical markers responsible for toxicity enhancement are the presence of unsaturated bonds, lipophilicity, presence of C< (double bond–single bond–single bonded carbon), and the presence of sulphur and phosphate bonds at the topological distances 1 and 6, while the presence of hydrophilic groups and short chain fragments reduces the toxicity. The Pesticide Properties Database (PPDB) (1694 pesticides) was also screened with the developed models. Hence, this research work will be helpful for the toxicity assessment of pesticides before their synthesis, the development of eco-friendly and safer pesticides, and data-gap filling reducing the time, cost, and animal experimentation. Thus, this study might hold promise for future potential MADI assessment of pesticides and provide a meaningful contribution to the field of risk assessment.

中文翻译：

---

第一份使用智能共识预测评估人类每日最大可接受农药摄入量 (MADI) 的报告

人类和其他生物体在没有安全剂量的情况下直接或间接消耗农药及其相关产品可能会造成健康风险。风险可能会在短/长时间后出现，这取决于所消耗化学品的性质和数量。因此，必须计算每日可接受的化学品最大摄入量，以预防这些风险。在目前的工作中，使用 39 种农药开发了基于回归的定量构效关系 (QSAR) 模型，以人类每日最大可接受摄入量 (MADI) 作为终点。从统计结果（R ² = 0.674–0.712，Q _LOO ² = 0.553–0.580，Q _(F1) ² = 0.544–0.611，Q _(F2) ² = 0.531–0.599）可以推断，所开发的模型稳健、可靠、可重复、准确且具有预测性。采用智能共识预测（ICP）来提高模型的外部预测率（ Q _（F1）² =0.579-0.657和Q _（F2）² =0.563-0.647）。导致毒性增强的一些化学标记是不饱和键的存在、亲脂性、C<（双键-单键-单键碳）的存在以及拓扑距离1和6处硫键和磷酸键的存在，而亲水基团和短链片段的存在降低了毒性。农药特性数据库（PPDB）（1694 种农药）也用开发的模型进行了筛选。因此，这项研究工作将有助于农药合成前的毒性评估，开发环保且更安全的农药，以及填补数据空白，减少时间、成本和动物实验。因此，这项研究可能为未来潜在的农药 MADI 评估带来希望，并为风险评估领域做出有意义的贡献。