Identification of protein coding regions in RNA transcripts

Nucleic Acids Res. 2015 Jul 13;43(12):e78. doi: 10.1093/nar/gkv227. Epub 2015 Apr 13.


Massive parallel sequencing of RNA transcripts by next-generation technology (RNA-Seq) generates critically important data for eukaryotic gene discovery. Gene finding in transcripts can be done by statistical (alignment-free) as well as by alignment-based methods. We describe a new tool, GeneMarkS-T, for ab initio identification of protein-coding regions in RNA transcripts. The algorithm parameters are estimated by unsupervised training which makes unnecessary manually curated preparation of training sets. We demonstrate that (i) the unsupervised training is robust with respect to the presence of transcripts assembly errors and (ii) the accuracy of GeneMarkS-T in identifying protein-coding regions and, particularly, in predicting translation initiation sites in modelled as well as in assembled transcripts compares favourably to other existing methods.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms
  • Animals
  • Arabidopsis / genetics
  • Drosophila melanogaster / genetics
  • Gene Expression Profiling*
  • Genes
  • High-Throughput Nucleotide Sequencing / methods*
  • Mice
  • Open Reading Frames*
  • Peptide Chain Initiation, Translational
  • RNA, Messenger / chemistry
  • Schizosaccharomyces / genetics
  • Sequence Analysis, RNA / methods*
  • Software*


  • RNA, Messenger