mRNA Signal Structure Detection (GMD)

Application domain mRNA signal structures
Source TZI, University of Eremen
Dataset size 400 mRN A instances
Data format ground Prolog facts
Systems used RIEL
References [1, 2]

This application [1] is concerned with identifying subsequences in mRNA that are responsible for biological functions. mRNA is a sequence of nucleotic acids (guanine, adenine, uracil, cytosine). The secondary structure of an mRNA contains special subsequences called signal structures that are responsible for special biological functions, such as RNA-protein interactions and cellular transport.

Signal structures are grouped into classes, such as IRE (Iron Responsive Element) that have the same (or similar) biological function. Horvath et al. [1] used RIBL to classify signal structures with unknown classes. They achieve highest accuracy using a term-based representation and similarity measure.


  1. Tamás Horváth, Stefan Wrobel, Uta Bohnebeck: Relational Instance-Based Learning with Lists and Terms. Machine Learning 43(1/2): 53-80 (2001).

  2. U. Eohnebeck and W. Salter and T. Horvith and S. Wrobel and D. Elohm, 'Nleasuring Similarity of RNA Structures by Relational Instance-based Learning: A First Step toward Detecting RNA Signal Structures in Silico', In Proc. of German Conference on Bioinformatics, Technical Report of University Cologne. 1998.

  3. U. Eohnebeck and W. Salter and T. Horvith and S. Wrobel and D. Elohm, 'Nleasuring similarity of RNA structures by relational instance-based learning', Submitted to Bioinformatics.

back to index