/******************************************************************************/ /*Program: pdbconv-whatif2amber */ /*Author: Stefan Henrich */ /*Email: stefan.henrich@eml-r.villa-bosch.de */ /*Date: 20.01.2005 version 2.02 */ /* */ /*Purpose: convert of whatif output pdb files for AMBER */ /* */ /*COMPILATION: cc -o pdbconv-whatif2amber pdbconv-whatif2amber.c */ /*USAGE: >pdbconv whatifout.pdb whatif2amber.pdb ligandname */ /*USAGE: >pdbconv-whatif2amber 1ejn.modifnew.pdb 1ejn.whatifout.tmp.pdb A25 */ /******************************************************************************/ #include #include int main ( int argc, /* Number of args */ char ** argv) /* Arg list */ { FILE *finput,*foutput,*foutput2,*fcyxin; char line[120],newline[120],templine[120],templine2[120],ssbond[200],hdeline[120]; char buffer[4],fill[]=" ",resinew[]=" ",resiold[]=" ",atomold[]=" "; int mark=0,a=0,aa=0,b=0,bb=0; int cyxresi[40],cyxnumb=0; //array for cyx residue numbers, counter for array char cyx[150],cyxtemp[]=" "; //string for storing fcyxin,substring of cyx if((finput = fopen(argv[1] , "r"))==NULL) {printf("Input file can not be opened .\n");exit(0);} if((foutput = fopen("RENUMBTMP.PDB", "w"))==NULL) {printf("Temp file RENUMBTMP.PDB can not be written .\n");exit(0);} if((foutput2 = fopen(argv[2], "w"))==NULL) {printf("OUT File can not be written .\n");exit(0);} if((fcyxin = fopen("CYX-RESIDUES.TMP", "r"))==NULL) {printf("CYX-RESIDUES.TMP File can not be read.\n");exit(0);} printf("pdbconv version 2.10\nconverting whatif pdb file for xleap\n\n"); //////////////////////////////////////////////////////// // STARTING WITH PDB while(fgets(line,100,finput)){/*printf("%s",line);*/ strncpy(templine,line,99); strncpy(templine2,line,99); strncpy(resinew,line+22,4); //get string of residue number // RENAMING HYDROGENS OF WATER if(strncmp(line+13,"O",1)!=0 && strncmp(line+17,"HOH",3)==0) { strncpy(newline,templine,12);newline[12]='\0'; if (mark==0) { strcat(newline," H1 ");strncat(newline,templine+16,1);strcat(newline,"HOH"); mark=1;} else {strcat(newline," H2 ");strncat(newline,templine+16,1);strcat(newline,"HOH"); mark=0;} strncat(newline,templine+20,46); strncpy(templine,newline,66); } // RENAMING HYDROGENS OF PROTEIN // if(strcmp(resinew,resiold)!=0) hydrogen=1; //start hydrogen numbering for new residue with H1 if(strncmp(line,"ATOM ",4)==0 && strncmp(line+17,"HOH",3)!=0 && strncmp(line+17,argv[3],3)!=0 && strncmp(line+17,"CAA",3)!=0 && strncmp(line+17,"Cl-",3)!=0 && strncmp(line+13,"C",1)!=0 && strncmp(line+13,"O",1)!=0 && strncmp(line+13,"N",1)!=0 && strncmp(line+13,"S",1)!=0 ) { strncpy(newline,line,12);newline[12]='\0'; // sprintf(buffer,"%d",hydrogen); //copy hydrogen into buffer strncat(buffer,fill,4); //add blank to buffer if(strncmp(atomold," N ",4)==0) {strncpy(buffer," H ",4);} //N if(strncmp(atomold," ND1",4)==0) {strncpy(buffer," HD1",4);} //HIS if(strncmp(atomold," NE2",4)==0 && strncmp(line+17,"HIS",3)==0) {strncpy(buffer," HE2",4);} //HIS if(strncmp(atomold," ND2",4)==0 && strncmp(line+17,"ASN",3)==0) {strncpy(buffer,"HD21",4);} //ASN if(strncmp(atomold,"HD21",4)==0 && strncmp(line+17,"ASN",3)==0) {strncpy(buffer,"HD22",4);} //ASN if(strncmp(atomold," NE2",4)==0 && strncmp(line+17,"GLN",3)==0) {strncpy(buffer,"HE21",4);} //GLN if(strncmp(atomold,"HE21",4)==0) {strncpy(buffer,"HE22",4);} //GLN if(strncmp(atomold," NE ",4)==0) {strncpy(buffer," HE ",4);} //ARG if(strncmp(atomold," NH1",4)==0) {strncpy(buffer,"HH11",4);} //ARG if(strncmp(atomold,"HH11",4)==0) {strncpy(buffer,"HH12",4);} //ARG if(strncmp(atomold," NH2",4)==0) {strncpy(buffer,"HH21",4);} //ARG if(strncmp(atomold,"HH21",4)==0) {strncpy(buffer,"HH22",4);} //ARG if(strncmp(atomold," NZ ",4)==0) {strncpy(buffer," HZ1",4);} //LYS if(strncmp(atomold," HZ1",4)==0) {strncpy(buffer," HZ2",4);} //LYS if(strncmp(atomold," HZ2",4)==0) {strncpy(buffer," HZ3",4);} //LYS if(strncmp(atomold," NE1",4)==0) {strncpy(buffer," HE1",4);} //TRP if(strncmp(atomold," OD1",4)==0) {strncpy(buffer," HD1",4);} //ASP if(strncmp(atomold," OD2",4)==0) {strncpy(buffer," HD2",4);} //ASP if(strncmp(atomold," OE1",4)==0) {strncpy(buffer," HE1",4);} //GLU if(strncmp(atomold," OE2",4)==0) {strncpy(buffer," HE2",4);} //GLU if(strncmp(atomold," OG1",4)==0) {strncpy(buffer," HG1",4);} //THR if(strncmp(atomold," OG ",4)==0) {strncpy(buffer," HG ",4);} //SER if(strncmp(atomold," OH ",4)==0) {strncpy(buffer," HH ",4);} //TYR if(strncmp(atomold," N ",4)==0 && strncmp(line+21," 1",5)==0) {strncpy(buffer," H1 ",4);} //N-TERM if(strncmp(atomold," H1 ",4)==0) {strncpy(buffer," H2 ",4);} //N-TERM if(strncmp(atomold," H2 ",4)==0) {strncpy(buffer," H3 ",4);} //N-TERM // printf("%s\n",buffer); strncat(newline,buffer,4); strncat(newline+16,line+16,51); strncpy(templine,newline,66); // strncpy(templine2,newline,66); // hydrogen=hydrogen+1; // strcpy(resiold,resinew); //store residue number for next cycle } strncpy(atomold,templine+12,4); //store atom type for next cycle // printf("%s",atomold); fprintf(foutput,"%s",templine); } /* end of while */ //////////////////////////////////////////////////////// // SSBOND CYS -> CYX //read CYX residue numbers from fcyxin (CYX-RESIDUES.TMP) and store it into cyxresi[cyxnumb] fgets(cyx,100,fcyxin); /*printf("%s",cyx);*/ while(strlen(cyx)>=(cyxnumb*4+4)) { cyxresi[cyxnumb]=atoi(strncpy(cyxtemp,cyx+cyxnumb*4,4)); cyxnumb=cyxnumb+1; } //////////////////////////////////////////////////////// fclose(foutput); foutput = fopen("RENUMBTMP.PDB", "r"); //////////////////////////////////////////////////////// // STARTING WITH PDB while(fgets(line,100,foutput)){ // printf("%s",line); strncpy(templine,line,99); strncpy(resinew,line+22,4); //get string of residue number // SSBOND CYS -> CYX if((strncmp(line+17,"CYS",3)==0) && (strncmp(line,"ATOM ",6)==0)) { for(cyxnumb=0;(cyxnumb*4+4)<=strlen(cyx);cyxnumb++) { if(cyxresi[cyxnumb]==atoi(resinew)) { strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"CYX",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66); } // end of if } // end of for } // HIS -> HID, HIE, HIP // The residues musn't be separated! (eg. no remark-lines within a residue) if((strncmp(line+17,"HIS",3)==0) && (strncmp(line,"ATOM ",6)==0)) { int hde=0,address; char hydrotempline[120]; int HYDROGEN(char hydroline[120], int kk) { if((strncmp(hydroline+13,"HD1",3)==0) && (strncmp(line+17,"HIS",3)==0)) kk=kk+1; if((strncmp(hydroline+13,"HE2",3)==0) && (strncmp(line+17,"HIS",3)==0)) kk=kk+2; fgets(hydroline,100,foutput); if(strncmp(hydroline+17,"HIS",3)!=0) return kk; else HYDROGEN(hydroline, kk); } // end of HYDROGEN address=ftell(foutput); //get current address of line hde=HYDROGEN(line,a); //start function HYDROGEN fseek(foutput,address,SEEK_SET); //back to current pointer of line if(hde>=aa) aa=hde; if(aa==0){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"HIS",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} else if(aa==1){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"HID",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} else if(aa==2){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"HIE",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} else if(aa>2){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"HIP",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} // detect end of residue HIS fgets(hdeline,100,foutput); if(strncmp(hdeline+17,"HIS",3)!=0) aa=0; fseek(foutput,address,SEEK_SET); //back to current pointer of line } // end of if his //--ASP, ASH (name of HD2 in original pdf-file unclear (no example could be found)) // The residues musn't be separated! (eg. no remark-lines within a residue) if((strncmp(line+17,"ASP",3)==0) && (strncmp(line,"ATOM ",6)==0)) { int hde=0,address; char hydrotempline[120]; int HYDROGEN(char hydroline[120], int kk) { if((strncmp(hydroline+13,"HD2",3)==0) && (strncmp(line+17,"ASP",3)==0)) kk=kk+1; fgets(hydroline,100,foutput); if(strncmp(hydroline+17,"ASP",3)!=0) return kk; else HYDROGEN(hydroline, kk); } address=ftell(foutput); //get current address of line hde=HYDROGEN(line,b); //start function HYDROGEN fseek(foutput,address,SEEK_SET); //back to current pointer of line if(hde>=bb) bb=hde; if(bb==0){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"ASP",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} else if(bb==1){ strncpy(newline,templine,17);newline[17]='\0'; strncat(newline,"ASH",3); strncat(newline+20,templine+20,46); strncpy (templine,newline,66);} else // detect end of residue ASP fgets(hdeline,100,foutput); if(strncmp(hdeline+17,"ASP",3)!=0) bb=0; fseek(foutput,address,SEEK_SET); //back to current pointer of line } // end of if ASP // C-terminal oxygen is not written in pdb if((strncmp(line+22," O2",4)!=0 && strncmp(line+12," O2 ",4)!=0) && (strncmp(line+17,argv[3],3)!=0)) { fprintf(foutput2,"%s",templine); } // fprintf(foutput2,"%s",templine); } /* end of while */ fclose(finput); fclose(fcyxin); fclose(foutput); fclose(foutput2); return(1); }