Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: MiRPara: a SVM-based software tool for prediction of most probable microRNA coding regions in genome scale sequences

Figure 1

Properties of pri-miRNA and negative test sequences. (a) Key Structural Components of pri-miRNA. Following Han, J. et al [34] the secondary structure of a pri-miRNA sequence was assumed to be characterized by a combination of the following five features: Basal Segment, Lower Stem, Upper Stem, Top Stem and Terminal Loop. In this paper, the pre-miRNA was defined as the processed product of Drosha in the nucleus while the pri-miRNA was the combination of pre-miRNA and its flanking sequences. All five features were not present in all sequences, but every pri-miRNA contained a Terminal Loop and Upper Stem. (b) Construction of negative sequences used for SVM training. These sequences were based on experimentally verified pri-miRNA, but the start position of the miRNA was randomly shifted (by at least 5 bp) within the sequence. These negative sequences were called Random-Start miRNA.

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us