Q-RASAR
The quantitative Read-Across Structure-Activity Relationship concept has been developed by the by merging Read-Across and QSAR. It is a statistical modeling approach that uses the similarity and error-based measures as descriptors in addition to the usual structural and physicochemical descriptors, and it has been shown to enhance the external predictivity of QSAR/QSPR models.
The novel quantitative read-across structure-activity relationship approach combines the advantages of both QSAR and read-across, thus resulting in enhanced predictivity for the same level of chemical information used. This approach utilizes similarity-based considerations yet can generate simple, interpretable, and transferable models. This approach may be used for any type of structural and physicochemical descriptors and with any modeling algorithms.
has been used by different research groups for different endpoints. Among different RASAR descriptors, RA function, Average Similarity and gm have shown high importance in modeling in some studies. In 2023, Banerjee-Roy similarity coefficients sm1 and sm2 have also been proposed to identify potential activity cliffs in a data set. The q-RASAR approach has the potential in data gap filling in predictive toxicology, materials science, medicinal chemistry, food sciences, nano-sciences, agricultural sciences, etc.
A on q-RASAR is available. Recently, the q-RASAR framework has been improved by its integration with the ARKA descriptors in QSAR.