sources/alscript/src/mzcons.c

   1 #include <stdio.h>
   2 #include <stdlib.h>
   3 #include <string.h>
   4 #include <gjutil.h>
   5
   6 int GJindex(char *str,char c);
   7
   8 float mzcons(unsigned char *pos,int n)
   9
  10 /* calculate conservation value according to Zvelebil et al for a set
  11    of amino acids and gaps stored in string pos of length n
  12
  13    Copyright:  Geoffrey J. Barton (1992,1997)
  14
  15    email: geoff@ebi.ac.uk
  16    Please see the README file for details of conditions for use of this program.
  17
  18    $Id: mzcons.c,v 1.2 1998/09/17 16:55:07 geoff Exp $
  19    $Log: mzcons.c,v $
  20    Revision 1.2  1998/09/17 16:55:07  geoff
  21    Check consistency with archive
  22
  23
  24 */
  25
  26 {
  27
  28 /* --  conmat contains a table like that shown in the JMB paper
  29        order of amino acids is GAP,ARNDCQEGHILKMFPSTWYBZX
  30 */
  31     static char *acids = " ARNDCQEGHILKMFPSTWYBZX";
  32     static int conmat[24][10] = {
  33         {1,1,1,1,1,1,1,1,1,1},
  34         {1,0,0,0,0,1,1,0,0,0},
  35         {0,1,0,1,1,0,0,0,0,0},
  36         {0,0,0,1,0,1,0,0,0,0},
  37         {0,0,1,1,1,1,0,0,0,0},
  38         {1,0,0,0,0,1,0,0,0,0},
  39         {0,0,0,1,0,0,0,0,0,0},
  40         {0,0,1,1,1,0,0,0,0,0},
  41         {1,0,0,0,0,1,1,0,0,0},
  42         {1,1,0,1,1,0,0,0,1,0},
  43         {1,0,0,0,0,0,0,1,0,0},
  44         {1,0,0,0,0,0,0,1,0,0},
  45         {1,1,0,1,1,0,0,0,0,0},
  46         {1,0,0,0,0,0,0,0,0,0},
  47         {1,0,0,0,0,0,0,0,1,0},
  48         {0,0,0,0,0,1,0,0,0,1},
  49         {0,0,0,1,0,1,1,0,0,0},
  50         {1,0,0,1,0,1,0,0,0,0},
  51         {1,0,0,1,0,0,0,0,1,0},
  52         {1,0,0,1,0,0,0,0,1,0},
  53         {1,0,0,0,0,1,0,1,0,0},
  54         {0,0,0,1,0,0,0,0,0,0},
  55         {0,0,0,1,0,0,0,0,0,0},
  56         {1,1,1,1,1,1,1,1,1,1}
  57     };
  58
  59     int concnt,it,i,j,k,l,tcnt,ibseq;
  60     int nide, facid;
  61
  62     concnt = 0;
  63     for(j=0;j<10;++j){
  64         /*found: outer loop over properties
  65         set IT to the value of the first amino acid*/
  66         it = conmat[GJindex(acids,pos[0])][j];
  67         /*loop over remaining acids, if a difference occurs then
  68         set tcnt to 1*/
  69         tcnt = 0;
  70         for(k=1;k<n;++k){
  71            if(it != conmat[GJindex(acids,pos[k])][j]){
  72                 tcnt = 1;
  73            }
  74         }
  75         /*add tcnt to concnt*/
  76         concnt += tcnt;
  77     }
  78     /* check for total identity at this position*/
  79     facid = pos[0];
  80     nide = 0;
  81     for(k=1;k<n;++k){
  82         if(facid == pos[k]){
  83              ++nide;
  84         }
  85     }
  86
  87     /*calculate the conservation*/
  88     if(concnt == 10){
  89       con = 0.0;
  90     }else if(concnt == 0){
  91         if(nide == n){
  92             /*total identity*/
  93             con = 1.0;
  94         }else{
  95             /*not identity, but same properties*/
  96               con = 0.9;
  97         }
  98     }else{
  99         con = 0.9 - 0.1 * concnt;
 100     }
 101     return con;
 102 }
 103
 104
 105 int GJindex(char *str,char c)
 106 {
 107     char *t;
 108     t = strchr(str,c);
 109     if(t == NULL) return NULL;
 110     return (int) (t - str);
 111 }
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122