This web server has been developed for discrimination of CDS sequence from intronic sequence. For each of the CDS and intron sequence, five different indices, based on methylation mediated substitution and spontaneous deamination, was computed. These indices have been developed in earlier study (Xia, 2005). The numerically coded intron and CDS sequences were then used as negative and positive instances for classification using binary Random Forest supervised learning approach. This approach has been validated in Cattle and Rice dataset. By using this server, user will get the output in terms of probability with which the submitted test sequence was predicted as coding sequence.The user has to supply only the test sequence (at least two) in FASTA format to run this server.

Team: Prabina Kumar Meher, Tanmaya Kumar Sahu, A. R. Rao and S. D. Wahi
Contact: meherprabin@yahoo.com; tanmayabioinfo@gmail.com; arrao@iasri.res.in

Technical Assited by: Jai Bhagwan; jai.kharb@icar.gov.in

Please Cite:

Meher, P. K., Sahu, T. K., Rao, A. R. and Wahi, S. D. (2016). Discriminating coding from non-coding regions based on codon structure and methylation-mediated substitution: An application in rice and cattle. Computers and Electronics in Agriculture, 129, 66-73.