Difference between revisions of "Split NMR-style multiple model pdb files into individual models"
From CCP4 wiki
Jump to navigationJump to search (Created page with 'This assumes that you have a correctly formatted pdb file that contains both MODEL and ENDMDL records. It gets split into individual pdb files names model_###.pdb. grep -n 'MOD…') |
|||
| Line 1: | Line 1: | ||
| − | This assumes that you have a correctly formatted pdb file that contains both MODEL and ENDMDL records. | + | This assumes that you have a correctly formatted pdb file that contains both MODEL and ENDMDL records. |
| + | |||
| + | |||
| + | |||
| + | == Bash/awk one-liner == | ||
| + | |||
| + | |||
| + | This one-liner splits the file models.pdb into individual pdb files names model_###.pdb. | ||
grep -n 'MODEL\|ENDMDL' models.pdb | | grep -n 'MODEL\|ENDMDL' models.pdb | | ||
| Line 5: | Line 12: | ||
awk '{if(NR%2) printf "sed -n %d,",$1+1; else printf "%dp > model_%03d.pdb\n", $1-1,NR/2;}' | | awk '{if(NR%2) printf "sed -n %d,",$1+1; else printf "%dp > model_%03d.pdb\n", $1-1,NR/2;}' | | ||
bash -sf | bash -sf | ||
| + | |||
| + | == Perl script == | ||
| + | |||
| + | $base='1g9e';open(IN,"<$base.pdb");@indata = <IN>;$i=0; | ||
| + | |||
| + | foreach $line(@indata) { | ||
| + | |||
| + | if($line =~ /^MODEL/) {++$i;$file="${base}_$i.pdb";open(OUT,">$file");next} | ||
| + | |||
| + | if($line =~ /^ENDMDL/) {next} | ||
| + | |||
| + | if($line =~ /^ATOM/ || $line =~ /^HETATM/) {print OUT "$line"} | ||
| + | |||
| + | } | ||
Revision as of 14:42, 14 December 2010
This assumes that you have a correctly formatted pdb file that contains both MODEL and ENDMDL records.
Bash/awk one-liner
This one-liner splits the file models.pdb into individual pdb files names model_###.pdb.
grep -n 'MODEL\|ENDMDL' models.pdb | cut -d: -f 1 | awk '{if(NR%2) printf "sed -n %d,",$1+1; else printf "%dp > model_%03d.pdb\n", $1-1,NR/2;}' | bash -sf
Perl script
$base='1g9e';open(IN,"<$base.pdb");@indata = <IN>;$i=0;
foreach $line(@indata) {
if($line =~ /^MODEL/) {++$i;$file="${base}_$i.pdb";open(OUT,">$file");next}
if($line =~ /^ENDMDL/) {next}
if($line =~ /^ATOM/ || $line =~ /^HETATM/) {print OUT "$line"}
}
