Identification of Protein Biomarkers for Diabetic Retinopathy using Sequence Mining Techniques

Bioinformatics and sequence mining are the application and development of data mining techniques to solve problems by comprehending biological data. Sequence analysis is the most primitive operation in sequence mining techniques. Modern sequence mining research is specialized in analyzing sequential patterns which are relevant and distinct from one another and utilizing retrieved sequences similarity and distance between different protein sequences can be analyzed. Diabetic retinopathy is the major cause of blindness in individuals mostly adults with diabetes and is it is the common problem of diabetes mellitus across the world. Various research analyses stated that there are many proteins which are found to take part in diabetic retinopathy. In this paper, we have evaluated certain proteins which are closely related with diabetic retinopathy with the help of multiple alignment tool viz. Clustal Omega and obtained a phylogenetic tree of 28 protein sequences gathered from National Center for Biotechnology Information (NCBI). In this work data mining technique called sequence mining plays a significant role in providing phylogram obtained with Neighbor-Joining algorithm. From the phylogenetic tree it was recognized that cortistatin, vitamin-D receptor and somatostatin proteins has close connection with diabetic retinopathy. Molecular docking studies have also been performed which is the most extensively used method for the calculation of protein-ligand interactions. In silico docking studies indicated that four inhibitory compounds i.e. Quercetin, Kaempferol, Naringenin and Melicitrin interact with aldose reductase which also found to have role in diabetic retinopathy. Outcomes infer that techniques intended to standardize cortistatin, vitamin-D receptor and somatostatin activities be of huge advantage and provide benefit in inhibiting diabetic retinopathy.