We have a transcript classification tool named CNCI, that published on NAR August 6 2013, and the title of this article is "Utilizing sequence intrinsic composition to classify protein-coding and long non-coding transcripts". The source code is writen by python, and can be download at : http://www.bioinfo.org/software/cnci/ . We would like to add CNCI to galaxy cloudman, and help more researchers in transcriptome analysis community . If have any question please contact me!
Looking forward to hearing from you soon.