- author = "Yuh-Jyh Hu",
- title = "Prediction of consensus structural motifs in a family of coregulated RNA sequences",
- journal = "Nucleic Acids Research",
- year = "2002",
- volume = "30",
- number = "17",
- pages = "3886--3893",
- keywords = "genetic algorithms, genetic programming",
- broken = "http://www.ingentaconnect.com/content/oup/nar/2002/00000030/00000017/art03886",
-
URL = "
http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=137409.pdf",
-
URL = "
http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=137409",
-
DOI = "
doi:10.1093/nar/gkg521",
- size = "8 pages",
- abstract = "Given a set of homologous or functionally related RNA sequences, the consensus motifs may represent the binding sites of RNA regulatory proteins. Unlike DNA motifs, RNA motifs are more conserved in structures than in sequences. Knowing the structural motifs can help us gain a deeper insight of the regulation activities. There have been various studies of RNA secondary structure prediction, but most of them are not focused on finding motifs from sets of functionally related sequences. Although recent research shows some new approaches to RNA motif finding, they are limited to finding relatively simple structures, e.g. stemloops. In this paper, we propose a novel genetic programming approach to RNA secondary structure prediction. It is capable of finding more complex structures than stem-loops. To demonstrate the performance of our new approach as well as to keep the consistency of our comparative study, we first tested it on the same data sets previously used to verify the current prediction systems. To show the flexibility of our new approach, we also tested it on a data set that contains pseudo knot motifs which most current systems cannot identify. A web-based user interface of the prediction system is set up at http://bioinfo.cis.nctu.edu.tw/service/gprm/.",
-
notes = "PMID: 12202774
p3887 negative examples randomly generated. fitness=F-score. pop=1000, 50gens. Tournament=2 (pop culled to 50percent???). virus 3'-UTR. Matthews correlation coefficient. GP fairly insensitive to crossover and mutation rates. GPRM",
