Following steps should be followed while using the RNApred web-server :

• Input sequence: There are two ways of sequence submission. Either paste directly into the text-box or upload the text file using 'BROWSE' option. Before uploading please ensure that the sequence must be in FASTA format and in single-letter code of amino acid representation. Every thing except ACDEFGHIKLMNPQRSTVWY, will be ignored from the sequence during prediction. With amino acid composition based approach, batch mode submission is also allowed. In case of PSSM profile based prediction, only one sequence can be predicted at a time. If more than one sequence is submitted only first sequence will be considered for prediction.
  

• Prediction approach : There are three prediction approaches on the basis of input vectors used to train SVM
  
  
  1. Amino acid composition: Amino acid composition of input sequence will be used for prediction.
  2. PSSM profile: PSSM generated by 3 iterations of PSI-BLAST, used as input.
  3. Hybrid: (Approach 2 + Fraction of RNA-binding Amino Acids present in the input sequence). RNA-binding amino acid prediction is done by PPRINT web-server.
  
  
• SVM threshold : Selection of prediction threshold is the most important parameter of prediction. RNAPred server provides threshold in range of -1 to +1 (default= -0.2). If the prediction score of query sequence is more than specified threshold, it will be predicted as RNA-binding otherwise non RNA-binding protein. To get prediction with less number of false positives, user should choose higher threshold. For prediction with less number of false negatives, threshold should be very low. In summary, for prediction with very high specificity, threshold should be very high. But for high sensitivity, threshold should be low.
  
  
• Output :The output shows SVM score along with the prediction results.