**********************************************************************************************
**                                                                                          **
**                                         SNPs&GO                                          **
**                  Predicting disease associated variation using GO terms                  **
**                                                                                          **
**********************************************************************************************

      Sequence File: fileseq.seq

      Mutation     Prediction   RI  Probability   Method
          T90I        Disease    5        0.728   PhD-SNP:  F[T]=68%  F[I]=4%   Nali=810
          T90I        Neutral    2        0.391   PANTHER:  F[T]=27%  F[I]=9%  
          T90I        Neutral    4        0.306   SNPs&GO

         M130I        Disease    5        0.750   PhD-SNP:  F[M]=35%  F[I]=11%  Nali=819
         M130I        Neutral    6        0.205   PANTHER:  F[M]=22%  F[I]=23% 
         M130I        Neutral    3        0.335   SNPs&GO

         E146G        Disease    4        0.686   PhD-SNP:  F[E]=19%  F[G]=0%   Nali=842
         E146G        Neutral    1        0.474   PANTHER:  F[E]=16%  F[G]=3%  
         E146G        Neutral    4        0.297   SNPs&GO

         E192K        Disease    5        0.726   PhD-SNP:  F[E]=65%  F[K]=3%   Nali=831
         E192K        Disease    1        0.534   PANTHER:  F[E]=31%  F[K]=5%  
         E192K        Neutral    0        0.489   SNPs&GO

         D193A        Disease    3        0.655   PhD-SNP:  F[D]=63%  F[A]=2%   Nali=833
         D193A        Disease    3        0.674   PANTHER:  F[D]=47%  F[A]=4%  
         D193A        Neutral    0        0.486   SNPs&GO


      Mutation: WT+POS+NEW
      WT:  Residue in wild-type protein
      POS: Residue position
      NEW: New residue after mutation
      Prediction:
             Neutral: Neutral variation
             Disease: Disease associated variation
      RI: Reliability Index
      Probability: Disease probability (if >0.5 mutation is predicted Disease)
      Method: SVM type and data
             PANTHER: Output of the PANTHER algorithm
             PhD-SNP:  SVM input is the sequence and profile at the mutated position
             SNPs&GO:  SVM input is all the input in PhD-SNP, PANTHER  and GO term features
      F[X]: Frequency of residue X in the sequence profile
      Nali: Number of aligned sequences in the mutated site

**********************************************************************************************
**                                                                                          **
**     Calabrese R, Capriotti E, Fariselli P, Martelli PL, Casadio R. (2009). Functional    **
**     annotations improve the predictive score of human disease-related mutations in       **
**     proteins. Human Mutation. 30:1237-1244.                                              **
**                                                                                          **
**     Capriotti E, Altman RB. (2011). Improving the prediction of disease-related vari-    **
**     ants using protein three-dimensional structure. BMC Bioinformatics. 12 (Sup.4) S3.   **
**                                                                                          **
**********************************************************************************************