Translation initiation sites prediction with mixture gaussian models
Translation initiation sites (TIS) are important signals in cDNA sequences. Many research efforts have tried to predict TIS in cDNA sequences. In this paper, we propose using mixture Gaussian models to predict TIS in cDNA sequences. Some new global measures are used to generate numerical features from cDNA sequences, such as the length of the open reading frame downstream from ATG, the number of other ATGs upstream and downstream from the current ATGs, etc. With these global features, the proposed method predicts TIS with sensitivity 98% and specificity 92%. The sensitivity is much better than that from other methods. We attribute the improvement in sensitivity to the nature of the global features and the mixture Gaussian models. © Springer-Verlag 2004.
Artificial intelligence, Bioinformatics, Forecasting, Mixtures, Numerical methods, Translation (languages), cDNA sequence, Global feature, Global measures, Mixture Gaussian model, Numerical features, Open reading frame, Research efforts, Translation initiation site
Numerical Analysis and Scientific Computing
Algorithms in Bioinformatics: 4th International Workshop, WABI 2004, Bergen, Norway, September 17-21, 2004. Proceedings
Inge Jonassen, Junhyong Kim
City or Country
Li, Guoliang; Tze-Yun LEONG; and Zhang, Louxin.
Translation initiation sites prediction with mixture gaussian models. (2004). Algorithms in Bioinformatics: 4th International Workshop, WABI 2004, Bergen, Norway, September 17-21, 2004. Proceedings. 3240, 338-349. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3050