For in-silico tool, I would like to classify coding and non-coding regions of gene.So can anybody kindly explain the the properties of these two regions for classification?
Thank you in advance
Very bfiefly (like Mr Putin likes to say :) ). If you count a triplet frequency dictionary so that the triplets are tiled with no gaps, but with no overlapping, for coding and non-coding area, then such triplet frequency dictionaries differs significatnly to distinguish he coding from non-coding parts. Meanwhile, quite a lot depends on specific issues of the task...
You might want to capitalize from the paper attached, and from few more references:
\bibitem{gorban1}
Gorban AN, Zinovyev AYu, Popova TG.
\newblock Seven clusters in genomic triplet distributions
\newblock Silico Biology. 2003 3(4):471--82.
\bibitem{gorban2}
Gorban AN, Zinovyev AYu, Popova TG.
\newblock Four basic symmetry types in the universal 7-cluster structure of microbial genomic sequences
\newblock Silico Biology. 2005 5(3):265--82.
\bibitem{gorbanzyn2}
Gorban~AN, Zinovyev~AYu, W\"{u}nsch~D\,III
\newblock Application of the method of elastic maps in analysis of genetic texts
\newblock Proceedings of International Joint Conference on Neural Networks, 2003 3:1826--31.
\bibitem{gorbanzyn1}
Gorban~AN, Zinovyev~AYu
\newblock Principal manifolds and graphs in practice: from molecular biology to dynamical systems
\newblock Int. J. of Neural Systems 2010 20(3):219--32.
- Badges
- Science topic
- Similar topics
- Data Mining
- Classification