Azo dyes are a group of chemical moieties joined by azo (-N=N-) group with potential usefulness in different industrial applications. But these dyes are not devoid of hazardous consequence because of poor affinity for the fibre and discharge into the water stream. The chemical aspects of 72 azo dyes towards cellulose fibre in terms of their affinity by QSPR have been explored in the present work. We have employed two approaches, namely balance of correlation without IIC (TF₁) and balance of correlation with IIC (TF₂), to generate 16 QSAR models from 8 splits. The determination coefficient of calibration and validation set was found higher when the QSPR models were developed using the index of ideality correlation (IIC) parameter (TF₂). The model developed with TF₂ for split 3 was considered as a prominent model because the determination coefficient of the validation set was maximum (r ² = 0.9468). The applicability domain (AD) was also analysed based on ‘statistical defect’, d(A) for a SMILES attribute. The mechanistic interpretation was done by identifying the SMILES attributes responsible for the promoter of endpoint increase and promoter of endpoint decrease. These SMILES attributes were applied to design 15 new dyes with higher affinity for cellulose fibre.

偶氮染料是由偶氮基（-N = N-）连接的一组化学部分，在不同的工业应用中具有潜在的用途。但是这些染料由于对纤维的亲和性很差，并排放到水流中，因此并非没有危险的后果。在目前的工作中，已经探究了72种偶氮染料对纤维素纤维的QSPR亲和力的化学方面。我们采用了两种方法，即没有IIC的相关平衡（TF ₁）和带有IIC的相关平衡（TF ₂），从8个分割中生成了16个QSAR模型。使用理想相关指数（IIC）建立QSPR模型时，发现校正和验证集的测定系数较高）参数（TF ₂）。用TF ₂为拆分3开发的模型被认为是突出的模型，因为验证集的确定系数最大（r ²  = 0.9468）。还针对“ SMILES”属性基于“统计缺陷” d（A）分析了适用域（AD）。通过识别负责终点增加的启动子和终点减少的启动子的SMILES属性来完成机械解释。这些SMILES属性用于设计15种对纤维素纤维具有更高亲和力的新型染料。