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

      Sequence File: KLF12_HUMAN.seq

      Mutation     Prediction   RI  Probability   Method
         H317R        Disease    4        0.698   PhD-SNP:  F[H]=62%  F[R]=0%   Nali=1265
         H317R        Disease    9        0.971   PANTHER:  F[H]=94%  F[R]=0%  
         H317R        Disease    8        0.918   SNPs&GO

         K326E        Disease    7        0.830   PhD-SNP:  F[K]=85%  F[E]=1%   Nali=1905
         K326E        Disease   10        0.988   PANTHER:  F[K]=96%  F[E]=0%  
         K326E        Disease    9        0.933   SNPs&GO

         S331G        Neutral    3        0.333   PhD-SNP:  F[S]=49%  F[G]=5%   Nali=1912
         S331G        Disease    8        0.905   PANTHER:  F[S]=88%  F[G]=1%  
         S331G        Disease    4        0.718   SNPs&GO

         A336P        Disease    4        0.705   PhD-SNP:  F[A]=30%  F[P]=0%   Nali=1912
         A336P        Disease    9        0.956   PANTHER:  F[A]=90%  F[P]=0%  
         A336P        Disease    8        0.885   SNPs&GO

         R360G        Disease    6        0.779   PhD-SNP:  F[R]=58%  F[G]=0%   Nali=1941
         R360G        Disease   10        0.997   PANTHER:  F[R]=99%  F[G]=0%  
         R360G        Disease    8        0.924   SNPs&GO

         R360P        Disease    8        0.903   PhD-SNP:  F[R]=58%  F[P]=0%   Nali=1941
         R360P        Disease   10        0.998   PANTHER:  F[R]=99%  F[P]=0%  
         R360P        Disease    9        0.945   SNPs&GO

         T365R        Neutral    0        0.496   PhD-SNP:  F[T]=28%  F[R]=3%   Nali=1943
         T365R        Disease    9        0.967   PANTHER:  F[T]=90%  F[R]=0%  
         T365R        Disease    8        0.892   SNPs&GO

         R369C        Disease    8        0.905   PhD-SNP:  F[R]=85%  F[C]=0%   Nali=1943
         R369C        Disease   10        0.994   PANTHER:  F[R]=95%  F[C]=0%  
         R369C        Disease    8        0.920   SNPs&GO

         C382Y        Disease    9        0.931   PhD-SNP:  F[C]=100% F[Y]=0%   Nali=1924
         C382Y        Disease   10        0.995   PANTHER:  F[C]=97%  F[Y]=0%  
         C382Y        Disease    9        0.937   SNPs&GO

         R384C        Disease    6        0.799   PhD-SNP:  F[R]=32%  F[C]=0%   Nali=1924
         R384C        Disease   10        0.988   PANTHER:  F[R]=93%  F[C]=0%  
         R384C        Disease    9        0.929   SNPs&GO

         R384H        Disease    1        0.527   PhD-SNP:  F[R]=32%  F[H]=0%   Nali=1924
         R384H        Disease    9        0.974   PANTHER:  F[R]=93%  F[H]=0%  
         R384H        Disease    8        0.891   SNPs&GO

         R397W        Disease    6        0.809   PhD-SNP:  F[R]=58%  F[W]=0%   Nali=1878
         R397W        Disease    7        0.825   PANTHER:  F[R]=45%  F[W]=0%  
         R397W        Disease    6        0.813   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.   **
**                                                                                          **
**********************************************************************************************