Suggestion of active 3-chymotrypsin like protease (3CL^Pro) inhibitors as potential anti-SARS-CoV-2 agents using predictive QSAR model based on the combination of ALASSO with an ANN model

The novel severe acute respiratory syndrome coronavirus (SARS CoV-2) was introduced as an epidemic in 2019 and had millions of deaths worldwide. Given the importance of this disease, the recommendation and design of new active compounds are crucial. 3-chymotrypsin-like protease (3 CL^pro) inhibitors have been identified as potent compounds for treating SARS-CoV-2 disease. So, the design of new 3 CL^pro inhibitors was proposed using a quantitative structure-activity relationship (QSAR) study. In this context, a powerful adaptive least absolute shrinkage and selection operator (ALASSO) penalized variable selection method with inherent advantages coupled with a nonlinear artificial neural network (ANN) modelling method were used to provide a QSAR model with high interpretability and predictability. After evaluating the accuracy and validity of the developed ALASSO-ANN model, new compounds were proposed using effective descriptors, and the biological activity of the new compounds was predicted. Ligand-receptor (LR) interactions were also performed to confirm the interaction strength of the compounds using molecular docking (MD) study. The pharmacokinetics properties and calculated Lipinski’s rule of five were applied to all proposed compounds. Due to the ease of synthesis of these suggested new compounds, it is expected that they have acceptable pharmacological properties.新型严重急性呼吸综合征冠状病毒（SARS CoV-2）于2019年首次以疫情形式暴发，已在全球造成数百万例死亡。鉴于该疾病的重大公共卫生意义，新型活性化合物的筛选与设计至关重要。3-胰凝乳蛋白酶样蛋白酶（3 CL^pro）抑制剂已被证实为治疗SARS CoV-2感染的强效候选药物。据此，本研究采用定量构效关系（QSAR）方法，开展新型3 CL^pro抑制剂的设计研究。在此研究框架下，本研究采用兼具固有优势的自适应最小绝对收缩与选择算子（ALASSO）惩罚变量选择方法，结合非线性人工神经网络（ANN）建模方法，构建了兼具高可解释性与高预测性能的QSAR模型。在对所构建的ALASSO-ANN模型的准确性与有效性进行评估后，本研究基于有效分子描述符设计了新型化合物，并预测了其生物活性。此外，本研究通过分子对接（MD）实验开展配体-受体（LR）相互作用分析，以验证候选化合物与靶点的结合强度。对所有候选化合物均进行了药代动力学性质评估，并计算了其Lipinski五规则符合情况。鉴于上述候选化合物合成难度较低，预期其具备良好的药理活性与成药性。