Brookhaven awk script?
Stefan Portmann
stefan at org.chem.ethz.ch
Thu Aug 10 08:43:01 EST 1995
--========================_6455518==_
Content-Type: text/plain; charset="us-ascii"
> I'm going to deposit structures of DNA from NMR to Brookhaven PDB.
>Does anyone have a awk script to convert a X-PLOR pdb format to a
>Does anyone have a awk script to convert the X-PLOR pdb format to a
>Brookhaven format?
>
>Thanks in advance.
>
> Tomoko Nishizaki
>
> Faculty of Pharmaceutical Sciences
> Hokkaido Univ.Kitaku Sapporo 060 Japan
> Tel : 011-706-3976
> Fax : 011-706-4989
> E-mail : zaki at ph.hines.hokudai.ac.jp
I use the following script including coordconv and pdbset from the CCP4
package to convert XPLOR to PDB:
--========================_6455518==_
Content-Type: text/plain; name="xplor2pdb.sh"; charset="us-ascii"
Content-Disposition: attachment; filename="xplor2pdb.sh"
#!/bin/sh
#
# X-PLOR to PDB
# nawk sorts the atoms in the residue
# $1 is input file without extension
#
######################################################
#
cell="25.196 40.798 66.265 90.000 90.000 90.000"
space="P212121"
#
######################################################
#
grep -v 'END' $1.xpl > x.xpl
#
coordconv \
XYZIN x.xpl \
XYZOUT x.pdb \
<<eof
INPUT XPLOR
OUTPUT PDB ORTH 1
CELL $cell
END
eof
#
sed '1,$s/'"'"'/*/' x.pdb > xx.pdb; mv xx.pdb x.pdb
#
#
#
##########################################################
nawk '
BEGIN {
resnbr1 = " 1"
i = 0
first = 1
while(getline <"x.pdb"> 0 ) {
if ($1 == "ATOM"){
i += 1
resnbr2 = getatom($0,i)
if (resnbr1 != resnbr2){
sort(resnbr1,first,i-1)
first = i
resnbr1 = resnbr2
}
}
else {
print
}
}
sort(resnbr1,first,i)
}
function getatom(a,ln){
atom_array[ln,1] = "ATOM"
atom_array[ln,2] = substr(a,7,5) # Nr
atom_array[ln,3] = substr(a,13,4) # Name
atom_array[ln,4] = substr(a,18,3) # ResName
atom_array[ln,5] = substr(a,23,4) # ResNr
atom_array[ln,6] = substr(a,31,8) # X
atom_array[ln,7] = substr(a,39,8) # Y
atom_array[ln,8] = substr(a,47,8) # Z
atom_array[ln,9] = substr(a,55,6) # O
atom_array[ln,10] = substr(a,61,6) # T
return atom_array[ln,5]
}
function sort(n,fir,lst){
rtyp = atom_array[lst,4]
if ( rtyp ~ "GUA" ) { guanin(n,fir,lst) }
if ( rtyp ~ "CYT" ) { cytosin(n,fir,lst) }
if ( rtyp ~ "ADE" ) { adenin(n,fir,lst) }
if ( rtyp ~ "THY" ) { thymin(n,fir,lst) }
if ( rtyp ~ "MCT" ) { mct(n,fir,lst) }
if ( rtyp ~ "TIP" ) { print_atom(fir) }
if ( rtyp ~ "SP " ) { print_atom(fir) }
}
function cytosin(n,fir,lst){
search_atom(" P ",n,fir,lst)
search_atom(" O1P",n,fir,lst)
search_atom(" O2P",n,fir,lst)
search_atom(" O5*",n,fir,lst)
search_atom(" C5*",n,fir,lst)
search_atom(" C4*",n,fir,lst)
search_atom(" O4*",n,fir,lst)
search_atom(" C3*",n,fir,lst)
search_atom(" O3*",n,fir,lst)
search_atom(" C2*",n,fir,lst)
search_atom(" O2*",n,fir,lst)
search_atom(" C1*",n,fir,lst)
search_atom(" N1 ",n,fir,lst)
search_atom(" C2 ",n,fir,lst)
search_atom(" O2 ",n,fir,lst)
search_atom(" N3 ",n,fir,lst)
search_atom(" C4 ",n,fir,lst)
search_atom(" N4 ",n,fir,lst)
search_atom(" C5 ",n,fir,lst)
search_atom(" C6 ",n,fir,lst)
}
function guanin(n,fir,lst){
search_atom(" P ",n,fir,lst)
search_atom(" O1P",n,fir,lst)
search_atom(" O2P",n,fir,lst)
search_atom(" O5*",n,fir,lst)
search_atom(" C5*",n,fir,lst)
search_atom(" C4*",n,fir,lst)
search_atom(" O4*",n,fir,lst)
search_atom(" C3*",n,fir,lst)
search_atom(" O3*",n,fir,lst)
search_atom(" C2*",n,fir,lst)
search_atom(" O2*",n,fir,lst)
search_atom(" C1*",n,fir,lst)
search_atom(" N9 ",n,fir,lst)
search_atom(" C8 ",n,fir,lst)
search_atom(" N7 ",n,fir,lst)
search_atom(" C5 ",n,fir,lst)
search_atom(" C6 ",n,fir,lst)
search_atom(" O6 ",n,fir,lst)
search_atom(" N1 ",n,fir,lst)
search_atom(" C2 ",n,fir,lst)
search_atom(" N2 ",n,fir,lst)
search_atom(" N3 ",n,fir,lst)
search_atom(" C4 ",n,fir,lst)
}
function adenin(n,fir,lst){
search_atom(" P ",n,fir,lst)
search_atom(" O1P",n,fir,lst)
search_atom(" O2P",n,fir,lst)
search_atom(" O5*",n,fir,lst)
search_atom(" C5*",n,fir,lst)
search_atom(" C4*",n,fir,lst)
search_atom(" O4*",n,fir,lst)
search_atom(" C3*",n,fir,lst)
search_atom(" O3*",n,fir,lst)
search_atom(" C2*",n,fir,lst)
search_atom(" O2*",n,fir,lst)
search_atom(" C1*",n,fir,lst)
search_atom(" N9 ",n,fir,lst)
search_atom(" C8 ",n,fir,lst)
search_atom(" N7 ",n,fir,lst)
search_atom(" C5 ",n,fir,lst)
search_atom(" C6 ",n,fir,lst)
search_atom(" N6 ",n,fir,lst)
search_atom(" N1 ",n,fir,lst)
search_atom(" C2 ",n,fir,lst)
search_atom(" N3 ",n,fir,lst)
search_atom(" C4 ",n,fir,lst)
}
function mct(n,fir,lst){
search_atom(" P ",n,fir,lst)
search_atom(" O1P",n,fir,lst)
search_atom(" O2P",n,fir,lst)
search_atom(" O5*",n,fir,lst)
search_atom(" C5*",n,fir,lst)
search_atom(" C4*",n,fir,lst)
search_atom(" C6*",n,fir,lst)
search_atom(" C7*",n,fir,lst)
search_atom(" C3*",n,fir,lst)
search_atom(" O3*",n,fir,lst)
search_atom(" C2*",n,fir,lst)
search_atom(" O2*",n,fir,lst)
search_atom(" C1*",n,fir,lst)
search_atom(" N1 ",n,fir,lst)
search_atom(" C2 ",n,fir,lst)
search_atom(" O2 ",n,fir,lst)
search_atom(" N3 ",n,fir,lst)
search_atom(" C4 ",n,fir,lst)
search_atom(" O4 ",n,fir,lst)
search_atom(" C5 ",n,fir,lst)
search_atom(" C5A",n,fir,lst)
search_atom(" C6 ",n,fir,lst)
}
function thymin(n,fir,lst){
search_atom(" P ",n,fir,lst)
search_atom(" O1P",n,fir,lst)
search_atom(" O2P",n,fir,lst)
search_atom(" O5*",n,fir,lst)
search_atom(" C5*",n,fir,lst)
search_atom(" C4*",n,fir,lst)
search_atom(" O4*",n,fir,lst)
search_atom(" C3*",n,fir,lst)
search_atom(" O3*",n,fir,lst)
search_atom(" C2*",n,fir,lst)
search_atom(" O2*",n,fir,lst)
search_atom(" C1*",n,fir,lst)
search_atom(" N1 ",n,fir,lst)
search_atom(" C2 ",n,fir,lst)
search_atom(" O2 ",n,fir,lst)
search_atom(" N3 ",n,fir,lst)
search_atom(" C4 ",n,fir,lst)
search_atom(" O4 ",n,fir,lst)
search_atom(" C5 ",n,fir,lst)
search_atom(" C5A",n,fir,lst)
search_atom(" C6 ",n,fir,lst)
}
function print_atom(b){
printf "%-4s%7d %-4s %3s %4d %8.3f%8.3f%8.3f%6.2f%6.2f\n",
atom_array[b,1],atom_array[b,2],atom_array[b,3],atom_array[b,4],
atom_array[b,5],atom_array[b,6],atom_array[b,7],atom_array[b,8],
atom_array[b,9],atom_array[b,10]
}
function search_atom(name,n,fir,lst){
while ( fir <= lst ){
if ( atom_array[fir,3] == name ){
print_atom(fir)
}
fir += 1
}
}
' > xx.pdb
#
################################################################################
#
mv xx.pdb x.pdb
#
pdbset \
xyzin x.pdb \
xyzout xx.pdb \
<<eof-1
renumber 1
cell $cell
spacegroup $space
eof-1
#
sed '1,$s/CYT/ C/' xx.pdb > x.pdb; mv x.pdb xx.pdb
sed '1,$s/GUA/ G/' xx.pdb > x.pdb; mv x.pdb xx.pdb
sed '1,$s/ADE/ A/' xx.pdb > x.pdb; mv x.pdb xx.pdb
sed '1,$s/THY/ T/' xx.pdb > x.pdb; mv x.pdb xx.pdb
sed '1,$s/TIP/HOH/' xx.pdb > x.pdb; mv x.pdb xx.pdb
mv xx.pdb $1.pdb
/bin/rm x.xpl
#
--========================_6455518==_
Content-Type: text/plain; charset="us-ascii"
##############################################################################
# Stefan Portmann #
# Organic Chemistry Laboratory #
# ETH Swiss Federal Institute of Technology #
# CH-8092 Zuerich #
# Switzerland #
# #
# e-mail stefan at org.chem.ethz.ch #
# phone 01 632 66 38 #
############################################################################
##
--========================_6455518==_--
More information about the X-plor
mailing list
Send comments to us at
archive@iubioarchive.bio.net
