The use of CisRNA-SVM model requires prior installation of

Libsvm 2.9: http://www.csie.ntu.edu.tw/~cjlin/libsvm/
Perl module: Tie::IxHash 

Usage: 
--------------------

perl CisRNA_SVM.pl -h (for detailed input information)

Input format:

-s filename (file containing a list of scores from RNAalifold (free energy/length of alignment), mlocarna (free energy/length of alignment), Foldalign (average pairwise score/length of alignment), coveb (score/length of alignment). Each line starts with alignment_name.start.end and scores separated by tab or empty space, e.g. IRE_test_score.txt)

-d directory where the executable svm-predict (from Libsvm 2.9) is located. e.g. /usr/local/bin

-a directory where the alignments are. Clustalw format, filename: alignment_name.extention and alignment_name contains no "." e.g. /Users/myname/Documents/aln

-m SVM model e.g. CisRNA_SVM.model

Output: predicted alignments with structures are written to a directory (result_alignment) and scores to a file (svm_prediction.txt). 

--------------------
Example:

perl CisRNA_SVM.pl -s IRE_test_score.txt -m CisRNA_SVM.model -a /Users/myuser/Documents/aln -d /user/local/bin > IRE.log


-------------------
If you want to generate scores from alignments then
Install:
RNAalifold from Vienna RNA package: http://www.tbi.univie.ac.at/RNA
LocARNA: http://rna.informatik.uni-freiburg.de:8080/LocARNA.jsp
Foldalign: http://foldalign.ku.dk
Cove: http://selab.janelia.org/software.html


Then analyse the alignments using RNAalifold, mlocarna, foldalign, coveb and extract normalized average scores (average score/length of alignment) for each alignment, then use CisRNA_SVM.pl for prediction.