I am trying to analyze the similarity between miRNAs and putting them in some distinct groups, non-overlapped groups, based on their similarities.
I need some suggestions about the measure of similarity, for example one of them can be similarity in their sequences.
Of course, I have expression profile of them, so another way to categorize them is clustering based on expression analysis.
Now, I want to know is there any other idea for considering as similarity measure?
1 answer
http://nar.oxfordjournals.org/content/37/suppl_1/D111.full
This was for miRNA prediction from sequence hairpins, but maybe some of the features for the svm can be used by you:
We investigated a number of the most discriminating features, such as the minimum free-energy index (34) or the mean base pair distance in the ensemble of structures, and trained an SVM (support vector machine) classifier using LIBSVM (http://www.csie.ntu.edu.tw/%7Ecjlin/libsvm). The total number of features used for this first SVM was 253.
Minimum free energy, conserved stem etc..
Log in to answer this question.
-
What could be a good balance between baseMean and Log2FoldChange?
written by Apex92 •
-
RNA Seq Classification
written by mosquitoking •
-
Are there any databases for gene co-expression or gene clustering by spatial/cell-type patterns?
written by Yep •
-
Patient-to-patient similarities network
written by Omics data mining
-
Improving the selection process of functional variants of an enzyme
written by parism9 •
-
Do we need to correct GC-content bias and/or length bias in RNA-Seq level 3 from TCGA?
written by Na Sed
-
How to find biological meaning of my results at probe level ?
written by XBria
-
Any suggestion for combining different types of scores
written by Na Sed
-
Plant miRNA prediction
written by swati25887 •
-
Domain-Based Clustering Of Protein Structures
written by Pals
