dnatrans.cc

unix或linux下的DNA分析软件源码 其功能如下 1. Edit up to 256 peptide or DNA sequences simultaneously. 2. Transla

//----------------------------------------------------//
//    dnatrans.cc                                     //
//    Translates DNA to protein in all 6 frames       //
//    Latest revision: 05-06-2000                     //
//----------------------------------------------------//

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <ctype.h>
#include <string.h>
#include <sys/stat.h>
#define max(x,y)     (((x) > (y)) ? (x) : (y))
#define min(x,y)     (((x) < (y)) ? (x) : (y))

int dna(int pos);
char *s1, *s1r, *s2[3];
int filesize(char *filename);

int main(int argc, char **argv)
{
   int index = 0;
   int a, dotpos, frame, i, k, fsize;
   FILE *fp1, *fp2;
   char file1[128], file2[128], tempstring[128];
   char buffer[128];
   char junk[1024];

   printf("dnatrans - Translates DNA or RNA sequence into peptide\n");
   printf("Sequence file:"); fflush(stdout);
   scanf("%s",file1);
   printf("Output file:  "); fflush(stdout);
   scanf("%s",file2);

   // Allocate extra space in case it gets edited
   fsize = filesize(file1);
   fsize = max(10000, 2 * fsize + 10);
   s1 = new char[fsize*3];
   s1r = new char[fsize*3];
   s2[0] = new char[fsize];
   s2[1] = new char[fsize];
   s2[2] = new char[fsize];
   if(s2[2]==NULL){ printf("Insufficient memory\n"); exit(1); }


   if((fp1=fopen(file1,"rb")) == NULL) 
   {  printf("\nUnable to open file %s\n",file1);
      exit(1);
   }

   //----Read the DNA sequence-----//
   while(!feof(fp1))
   {
      a = fgetc(fp1);
      if(a=='#') fgets(junk,1024,fp1);  // comment
      a = toupper(a); 
      if(a == 'A' || a == 'T' || a == 'U' || a == 'C' || a == 'G' || a == 'N')
        s1[index++] = a;
   }
   printf("\n\n");
   fclose(fp1);

   //----Generate base filename---//

   dotpos = strlen(file2);
   for(k=0; k<(int)strlen(file2); k++) if(file2[k]=='.') dotpos=k;
   file2[dotpos]=0;

   //----Translate 1st 3 reading frames----//

   i = 0;
   for(k=0;k<index-2;k+=3)
   {  s2[0][i] = dna(k  );
      s2[1][i] = dna(k+1);
      s2[2][i] = dna(k+2);
      i++;
   }

   for(frame=0;frame<=2;frame++)
   {  sprintf(tempstring,"%s.%d",file2,frame+1);   
      if((fp2=fopen(tempstring,"wt")) == NULL) 
      {  printf("\nUnable to open file %s\n",file2);
         exit(1);
      }
      for(k=0; k<(int)strlen(s2[frame]); k+=50)
      {   strncpy(buffer, s2[frame]+k, 50);
          buffer[50]=0;
          fprintf(fp2,"%s\n", buffer);
          printf("%s\n", buffer);
      }
      fclose(fp2);
   }

   //----Reverse the DNA sequence-----//
  
   for(k=0;k<index;k++)
   {  a = s1[k];
      switch(a)
      {  case 'U': a = 'A'; break;
         case 'T': a = 'A'; break;
         case 'A': a = 'T'; break;
         case 'G': a = 'C'; break;
         case 'C': a = 'G'; break;
         case 'N': a = 'N'; break;
      }
      s1r[index-k-1] = a;
   }
   memcpy(s1,s1r,index);

   //----Translate last 3 reading frames----//

   i = 0;
   for(k=0;k<index-2;k+=3)
   {  s2[0][i] = dna(k  );
      s2[1][i] = dna(k+1);
      s2[2][i] = dna(k+2);
      i++;
   }

   for(frame=0;frame<=2;frame++)
   {  sprintf(tempstring,"%s.%d",file2,frame+4);   
      if((fp2=fopen(tempstring,"wt")) == NULL) 
      {  printf("\nUnable to open file %s\n",file2);
         exit(1);
      }
      for(k=0; k<(int)strlen(s2[frame]); k+=50)
      {   strncpy(buffer, s2[frame]+k, 50);
          buffer[50]=0;
          fprintf(fp2,"%s\n", buffer);
          printf("%s\n", buffer);
      }
      fclose(fp2);
   }
   exit(EXIT_SUCCESS);
}

//---------------------------------------------------------------//
// dna                                                           //
//---------------------------------------------------------------//
int dna(int pos)
{  char code[5];
   code[0] = toupper(s1[pos  ]);
   code[1] = toupper(s1[pos+1]);
   code[2] = toupper(s1[pos+2]);
   code[3] = 0;
   if(code[0]=='T') code[0]='U';
   if(code[1]=='T') code[1]='U';
   if(code[2]=='T') code[2]='U';

   if(!(strcmp(code,"UUU"))) return 'F';
   if(!(strcmp(code,"UUC"))) return 'F';
   if(!(strcmp(code,"UUA"))) return 'L';
   if(!(strcmp(code,"UUG"))) return 'L';

   if(!(strcmp(code,"UCU"))) return 'S';
   if(!(strcmp(code,"UCC"))) return 'S';
   if(!(strcmp(code,"UCA"))) return 'S';
   if(!(strcmp(code,"UCG"))) return 'S';
   if(!(strcmp(code,"UCN"))) return 'S';

   if(!(strcmp(code,"UAU"))) return 'Y';
   if(!(strcmp(code,"UAC"))) return 'Y';
   if(!(strcmp(code,"UAA"))) return 'x';
   if(!(strcmp(code,"UAG"))) return 'x';
   if(!(strcmp(code,"UAN"))) return 'Y';

   if(!(strcmp(code,"UGU"))) return 'C';
   if(!(strcmp(code,"UGC"))) return 'C';
   if(!(strcmp(code,"UGA"))) return 'x';
   if(!(strcmp(code,"UGG"))) return 'W';


   if(!(strcmp(code,"CUU"))) return 'L';
   if(!(strcmp(code,"CUC"))) return 'L';
   if(!(strcmp(code,"CUA"))) return 'L';
   if(!(strcmp(code,"CUG"))) return 'L';
   if(!(strcmp(code,"CUN"))) return 'L';

   if(!(strcmp(code,"CCU"))) return 'P';
   if(!(strcmp(code,"CCC"))) return 'P';
   if(!(strcmp(code,"CCA"))) return 'P';
   if(!(strcmp(code,"CCG"))) return 'P';
   if(!(strcmp(code,"CCN"))) return 'P';

   if(!(strcmp(code,"CAU"))) return 'H';
   if(!(strcmp(code,"CAC"))) return 'H';
   if(!(strcmp(code,"CAA"))) return 'Q';
   if(!(strcmp(code,"CAG"))) return 'Q';

   if(!(strcmp(code,"CGU"))) return 'R';
   if(!(strcmp(code,"CGC"))) return 'R';
   if(!(strcmp(code,"CGA"))) return 'R';
   if(!(strcmp(code,"CGG"))) return 'R';
   if(!(strcmp(code,"CGN"))) return 'R';


   if(!(strcmp(code,"AUU"))) return 'I';
   if(!(strcmp(code,"AUC"))) return 'I';
   if(!(strcmp(code,"AUA"))) return 'I';
   if(!(strcmp(code,"AUG"))) return 'M';

   if(!(strcmp(code,"ACU"))) return 'T';
   if(!(strcmp(code,"ACC"))) return 'T';
   if(!(strcmp(code,"ACA"))) return 'T';
   if(!(strcmp(code,"ACG"))) return 'T';
   if(!(strcmp(code,"ACN"))) return 'T';

   if(!(strcmp(code,"AAU"))) return 'N';
   if(!(strcmp(code,"AAC"))) return 'N';
   if(!(strcmp(code,"AAA"))) return 'K';
   if(!(strcmp(code,"AAG"))) return 'K';

   if(!(strcmp(code,"AGU"))) return 'S';
   if(!(strcmp(code,"AGC"))) return 'S';
   if(!(strcmp(code,"AGA"))) return 'R';
   if(!(strcmp(code,"AGG"))) return 'R';


   if(!(strcmp(code,"GUU"))) return 'V';
   if(!(strcmp(code,"GUC"))) return 'V';
   if(!(strcmp(code,"GUA"))) return 'V';
   if(!(strcmp(code,"GUG"))) return 'V';
   if(!(strcmp(code,"GUN"))) return 'V';

   if(!(strcmp(code,"GCU"))) return 'A';
   if(!(strcmp(code,"GCC"))) return 'A';
   if(!(strcmp(code,"GCA"))) return 'A';
   if(!(strcmp(code,"GCG"))) return 'A';
   if(!(strcmp(code,"GCN"))) return 'A';

   if(!(strcmp(code,"GAU"))) return 'D';
   if(!(strcmp(code,"GAC"))) return 'D';
   if(!(strcmp(code,"GAA"))) return 'E';
   if(!(strcmp(code,"GAG"))) return 'E';

   if(!(strcmp(code,"GGU"))) return 'G';
   if(!(strcmp(code,"GGC"))) return 'G';
   if(!(strcmp(code,"GGA"))) return 'G';
   if(!(strcmp(code,"GGG"))) return 'G';
   if(!(strcmp(code,"GGN"))) return 'G';

   return 'x';
}

//-----------------------------------------------------------------//
//  filesize                                                       //
//-----------------------------------------------------------------//
int filesize(char *filename)
{
     struct stat dstatus;
     stat(filename, &dstatus);
     return dstatus.st_size;
}