output problems

@ChainA{@ChainB}=(1)x@ChainB;
#should probably be:
@ChainB{@ChainB}=(1)x@ChainB;

Hi ozo,

Yeah, sorry that was my mistake. But I still don't think the program is removing the corresponding Surface Resitype chainB and Surface Resitype chainD letters along with the numbers

So basically, the program is removing all the same numbers from "surface residues chainB" that are in the "Interfacing Residues Chain B" or "Neighboring Residues Chain B" (and obviously the same from chain D) but I need it to remove the corresponding letter from the Surface Resitype chainB line (and the same situation for chain D).

open (IN,'1bbbAB60') || die "Unable to open the Input File $!";
{local $/; $_=<IN>;} close IN;
@ChainB=();  @ChainD=();
if( m#Interfacing Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,\s*/,$1))};
if( m#Neighboring Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,\s*/,$1))};
if( m#Interfacing Residues Chain D: ?([\s,\d]*)# ){push(@ChainD,split(/\s*,\s*/,$1))};
if( m#Neighboring Residues Chain D: ?([\s,\d]*)# ){push(@ChainD,split(/\s*,s*/,$1))};

    @SurfaceResidueB=();  @SurfaceResidueD=();
if( m#Surface Residues chainB: ?([\s\d,]*)# ){push@SurfaceResidueB,split/\s*,\s*/,$1 };
if( m#Surface Residues chainD: ?([\s,\d]*)# ){push@SurfaceResidueD,split/\s*,\s*/,$1 };

if( m#Surface Resitype chainB: ?([\s,\w]*)# ){push@SurfaceResitypeB,split/\s*,\s*/,$1 };
if( m#Surface Resitype chainD: ?([\s,\w]*)# ){push@SurfaceResitypeD,split/\s*,\s*/,$1 };
    @ResitypeB{@SurfaceResidueB} = @SurfaceResitypeB;
    @ResitypeD{@SurfaceResidueD} = @SurfaceResitypeD;
    @ChainB{@ChainB}=(1)x@ChainB;
    $SRA=join(",", map{sprintf("%-3s", $_)} grep {!$ChainB{$_}} @SurfaceResidueB);
s#(Surface Residues chainB:)[\d\s,]*#$1$SRA#;
    @ChainD{@ChainD}=(1)x@ChainD;
    $SRB=join(",", map{sprintf("%-3s", $_)} grep {!$ChainD{$_}} @SurfaceResidueD);
s#(Surface Residues chainD:)[\d\s,]*#$1$SRB#;
   
    $SR = join",",map{sprintf("%-3s",$ResitypeB{$_})} grep {!$ChainB{$_}} @SurfaceResidueB;
s#(Surface Resitype chainB:)[\w\s,]*#$1$SR#;

     $SR = join",",map{sprintf("%-3s",$ResitypeD{$_})} grep {!$ChainD{$_}} @SurfaceResidueD;
s#(Surface Resitype chainD:)[\w\s,]*#$1$SR#;

    open (OUT,">outty.txt") or die $!;
    print OUT;

Hi ozo,

That program is removing the letters now, which is great but it is still not removing some of the numbers in "interfacing residue chains" and "neighboring residue chains" from the "surface Residue chains". I tried it on the below example..I'll give the input file, the program and the output. I hope you can help...you're really good at this.  As you can see, for example, in the output 178 from the "interface chainA"and 179 from the "neighboring chainA" are still been collected in the surface residuesChainA.


Input:
mdsAB
Interfacing Residues Chain A:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cA:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Interfacing Residues Chain B:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cB:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Neighboring Residues Chain A:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cA:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R
Neighboring Residues Chain B:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cB:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R

3mdsAB
Surface Residues chainA:1  ,2  ,3  ,5  ,7  ,8  ,10 ,12 ,13 ,14 ,15 ,17 ,18 ,19 ,
23 ,26 ,30 ,31 ,35 ,38 ,39 ,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,
67 ,68 ,70 ,71 ,72 ,74 ,88 ,91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,
111,114,115,118,119,122,125,126,139,140,141,142,144,147,149,150,156,157,158,160,
175,178,179,181,182,185,189,194,198,201,202,203
Surface Resitype chainA:P  ,Y  ,P  ,K  ,P  ,D  ,G  ,P  ,Y  ,E  ,A  ,E  ,P  ,H  ,
K  ,E  ,Q  ,K  ,A  ,T  ,N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,
Q  ,D  ,Q  ,T  ,A  ,R  ,R  ,T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,
G  ,Q  ,A  ,E  ,K  ,Q  ,M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,P  ,N  ,M  ,E  ,G  ,T  ,
K  ,N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,K  ,K  ,A
Surface Residues chainB:1  ,3  ,5  ,6  ,7  ,8  ,10 ,12 ,14 ,15 ,17 ,18 ,19 ,23 ,
26 ,30 ,31 ,35 ,38 ,39 ,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,67 ,
68 ,70 ,71 ,72 ,74 ,88 ,91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,111,
114,115,117,118,119,121,122,125,126,139,140,141,142,144,147,149,157,158,160,175,
178,179,181,182,185,189,194,198,201,202,203
Surface Resitype chainB:P  ,P  ,K  ,L  ,P  ,D  ,G  ,P  ,E  ,A  ,E  ,P  ,H  ,K  ,
E  ,Q  ,K  ,A  ,T  ,N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,Q  ,
D  ,Q  ,T  ,A  ,R  ,R  ,T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,G  ,
Q  ,A  ,K  ,E  ,K  ,T  ,Q  ,M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,P  ,E  ,G  ,T  ,K  ,
N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,K  ,K  ,A


program:
#!usr/local/bin/perl



open (IN,'8catAB2') || die "Unable to open the Input File $!";
{local $/; $_=<IN>;} close IN;
@ChainA=();  @ChainB=();
if( m#Interfacing Residues Chain A: ?([\s,\d]*)# ){push(@ChainA,split(/\s*,\s*/,
$1))};
if( m#Neighboring Residues Chain A: ?([\s,\d]*)# ){push(@ChainA,split(/\s*,\s*/,
$1))};
if( m#Interfacing Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,\s*/,
$1))};
if( m#Neighboring Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,s*/,$
1))};

    @SurfaceResidueA=();  @SurfaceResidueB=();
if( m#Surface Residues chainA: ?([\s\d,]*)# ){push@SurfaceResidueA,split/\s*,\s*
/,$1 };
if( m#Surface Residues chainB: ?([\s,\d]*)# ){push@SurfaceResidueB,split/\s*,\s*
/,$1 };
if( m#Surface Resitype chainA: ?([\s,\w]*)# ){push@SurfaceResitypeA,split/\s*,\s
*/,$1 };
if( m#Surface Resitype chainB: ?([\s,\w]*)# ){push@SurfaceResitypeB,split/\s*,\s
*/,$1 };
    @ResitypeA{@SurfaceResidueA} = @SurfaceResitypeA;
    @ResitypeB{@SurfaceResidueB} = @SurfaceResitypeB;
    @ChainA{@ChainA}=(1)x@ChainA;
    $SRA=join(",", map{sprintf("%-3s", $_)} grep {!$ChainA{$_}} @SurfaceResidueA
);
s#(Surface Residues chainA:)[\d\s,]*#$1$SRA#;
    @ChainB{@ChainB}=(1)x@ChainB;
    $SRB=join(",", map{sprintf("%-3s", $_)} grep {!$ChainB{$_}} @SurfaceResidueB
);
s#(Surface Residues chainB:)[\d\s,]*#$1$SRB#;
$SR = join",",map{sprintf("%-3s",$ResitypeA{$_})} grep {!$ChainA{$_}} @Surfa
ceResidueA;
s#(Surface Resitype chainA:)[\w\s,]*#$1$SR#;

     $SR = join",",map{sprintf("%-3s",$ResitypeB{$_})} grep {!$ChainB{$_}} @Surf
aceResidueB;
s#(Surface Resitype chainB:)[\w\s,]*#$1$SR#;

    open (OUT,">8catAB") or die $!;
    print OUT;

ouput

3mdsAB
Interfacing Residues Chain A:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cA:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Interfacing Residues Chain B:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cB:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Neighboring Residues Chain A:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cA:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R
Neighboring Residues Chain B:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cB:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R
3mdsAB
Surface Residues chainA:1  ,2  ,3  ,5  ,7  ,8  ,10 ,12 ,13 ,14 ,15 ,17 ,18 ,19 ,
38 ,39 ,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,67 ,68 ,70 ,71 ,72 ,
88 ,91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,111,114,115,118,119,122,
125,126,139,140,141,142,144,147,156,157,158,160,178,179,181,182,185,189,194,198,
201,202,203
Surface Resitype chainA:P  ,Y  ,P  ,K  ,P  ,D  ,G  ,P  ,Y  ,E  ,A  ,E  ,P  ,H  ,
T  ,N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,Q  ,D  ,Q  ,T  ,A  ,
R  ,T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,G  ,Q  ,A  ,E  ,K  ,Q  ,
M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,M  ,E  ,G  ,T  ,N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,
K  ,K  ,A
Surface Residues chainB:1  ,3  ,5  ,6  ,7  ,8  ,10 ,12 ,14 ,15 ,17 ,18 ,19 ,38 ,
39 ,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,67 ,68 ,70 ,71 ,72 ,88 ,
91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,111,114,115,117,118,119,121,
122,125,126,139,140,141,142,144,147,157,158,160,178,179,181,182,185,189,194,198,
201,202,203
Surface Resitype chainB:P  ,P  ,K  ,L  ,P  ,D  ,G  ,P  ,E  ,A  ,E  ,P  ,H  ,T  ,
N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,Q  ,D  ,Q  ,T  ,A  ,R  ,
T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,G  ,Q  ,A  ,K  ,E  ,K  ,T  ,
Q  ,M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,E  ,G  ,T  ,N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,
K  ,K  ,A

The input lines are all read in in one line like :
Interfacing Residues Chain A:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150

if that helps?

Can you see anything wrong Ozo?

#a small typo:
if( m#Neighboring Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,s*/,$1))};
#should be
if( m#Neighboring Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,\s*/,$1))};

#There could also be a problem could be with the last chain on a line, which you can fix with
chomp @ChainA;
chomp @ChainB;
chomp @SurfaceResidueA;
chomp @SurfaceResidueB;
#You'll probably have to put the end of line back with
s#(Surface Residues chainA:)[\d\s,]*#$1$SRA\n#;

mmm, I'm not sure I follow...how would this look compared with my original script?  Where would I put the "chomp" part?

#!usr/local/bin/perl



open (IN,'8catAB2') || die "Unable to open the Input File $!";
{local $/; $_=<IN>;} close IN;
@ChainA=();  @ChainB=();
if( m#Interfacing Residues Chain A: ?([\s,\d]*)# ){push(@ChainA,split(/\s*,\s*/,
$1))};
if( m#Neighboring Residues Chain A: ?([\s,\d]*)# ){push(@ChainA,split(/\s*,\s*/,
$1))};
if( m#Interfacing Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,\s*/,
$1))};
if( m#Neighboring Residues Chain B: ?([\s,\d]*)# ){push(@ChainB,split(/\s*,s*/,$
1))};

    @SurfaceResidueA=();  @SurfaceResidueB=();
if( m#Surface Residues chainA: ?([\s\d,]*)# ){push@SurfaceResidueA,split/\s*,\s*
/,$1 };
if( m#Surface Residues chainB: ?([\s,\d]*)# ){push@SurfaceResidueB,split/\s*,\s*
/,$1 };
if( m#Surface Resitype chainA: ?([\s,\w]*)# ){push@SurfaceResitypeA,split/\s*,\s
*/,$1 };
if( m#Surface Resitype chainB: ?([\s,\w]*)# ){push@SurfaceResitypeB,split/\s*,\s
*/,$1 };

chomp @ChainA;
chomp @ChainB;
chomp @SurfaceResidueA;
chomp @SurfaceResidueB;
chomp @SurfaceResitypeA;
chomp @SurfaceResitypeB;

    @ResitypeA{@SurfaceResidueA} = @SurfaceResitypeA;
    @ResitypeB{@SurfaceResidueB} = @SurfaceResitypeB;
    @ChainA{@ChainA}=(1)x@ChainA;
    $SRA=join(",", map{sprintf("%-3s", $_)} grep {!$ChainA{$_}} @SurfaceResidueA
);
s#(Surface Residues chainA:)[\d\s,]*#$1$SRA\n#;
    @ChainB{@ChainB}=(1)x@ChainB;
    $SRB=join(",", map{sprintf("%-3s", $_)} grep {!$ChainB{$_}} @SurfaceResidueB
);
s#(Surface Residues chainB:)[\d\s,]*#$1$SRB\n#;
$SR = join",",map{sprintf("%-3s",$ResitypeA{$_})} grep {!$ChainA{$_}} @SurfaceResidueA;
s#(Surface Resitype chainA:)[\w\s,]*#$1$SR\n#;

     $SR = join",",map{sprintf("%-3s",$ResitypeB{$_})} grep {!$ChainB{$_}} @SurfaceResidueB;
s#(Surface Resitype chainB:)[\w\s,]*#$1$SR\n#;

    open (OUT,">8catAB") or die $!;
    print OUT;

Hi Ozo,

Thats still not removing those numbers and now my output is like this wit the surface residue chainB numbers on a different line

3mdsAB
Interfacing Residues Chain A:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cA:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Interfacing Residues Chain B:23 ,27 ,31 ,32 ,36 ,75 ,128,129,130,150,151,168,169
,170,173,174,177,178
Interface Residue matched cB:K  ,I  ,K  ,H  ,Y  ,N  ,F  ,G  ,S  ,N  ,Q  ,W  ,E
,H  ,Y  ,L  ,Q  ,N
Neighboring Residues Chain A:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cA:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R
Neighboring Residues Chain B:22 ,24 ,26 ,28 ,30 ,33 ,35 ,37 ,74 ,76 ,127,131,149
,152,167,171,172,175,176,179
Neighboring Residue match cB:A  ,T  ,E  ,H  ,Q  ,H  ,A  ,V  ,R  ,N  ,R  ,G  ,P
,D  ,V  ,A  ,Y  ,K  ,Y  ,R

3mdsAB
Surface Residues chainA:1  ,2  ,3  ,5  ,7  ,8  ,10 ,12 ,13 ,14 ,15 ,17 ,18 ,19 ,
23 ,26 ,30 ,31 ,35 ,38 ,39 ,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,
67 ,68 ,70 ,71 ,72 ,74 ,88 ,91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,
111,114,115,118,119,122,125,126,139,140,141,142,144,147,149,150,156,157,158,160,
175,178,179,181,182,185,189,194,198,201,202,203
Surface Resitype chainA:P  ,Y  ,P  ,K  ,P  ,D  ,G  ,P  ,Y  ,E  ,A  ,E  ,P  ,H  ,
K  ,E  ,Q  ,K  ,A  ,T  ,N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,
Q  ,D  ,Q  ,T  ,A  ,R  ,R  ,T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,
G  ,Q  ,A  ,E  ,K  ,Q  ,M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,P  ,N  ,M  ,E  ,G  ,T  ,
K  ,N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,K  ,K  ,A
Surface Residues chainB
:1  ,3  ,5  ,6  ,7  ,8  ,10 ,12 ,14 ,15 ,17 ,18 ,19 ,23 ,26 ,30 ,31 ,35 ,38 ,39
,42 ,45 ,46 ,48 ,49 ,52 ,54 ,56 ,57 ,60 ,61 ,63 ,64 ,67 ,68 ,70 ,71 ,72 ,74 ,88
,91 ,92 ,93 ,96 ,97 ,99 ,100,101,103,104,107,108,109,111,114,115,117,118,119,121
,122,125,126,139,140,141,142,144,147,149,157,158,160,175,178,179,181,182,185,189
,194,198,201,202,203
Surface Resitype chainB:P  ,P  ,K  ,L  ,P  ,D  ,G  ,P  ,E  ,A  ,E  ,P  ,H  ,K  ,
E  ,Q  ,K  ,A  ,T  ,N  ,A  ,E  ,K  ,P  ,Y  ,G  ,E  ,E  ,V  ,R  ,H  ,A  ,A  ,Q  ,
D  ,Q  ,T  ,A  ,R  ,R  ,T  ,P  ,G  ,K  ,E  ,V  ,G  ,E  ,K  ,K  ,D  ,E  ,Q  ,G  ,
Q  ,A  ,K  ,E  ,K  ,T  ,Q  ,M  ,G  ,P  ,F  ,G  ,K  ,H  ,S  ,P  ,E  ,G  ,T  ,K  ,
N  ,R  ,A  ,D  ,Q  ,N  ,D  ,E  ,K  ,K  ,A

What is wrong with the output you're getting now?

Im getting as above......"surface Residues ChainB" residues are moved onto a different line ie:

Surface Residues chainB
:1  ,3  ,5  ,6  ,7  ,8  ,10 ,12 ,14 ,15 ,17 ,18 ,19 ,23 ,26 ,30 ,31 ,35 ,38 ,39  (like this) plus I'm still seeing numbers eg 178 in the Surface Residues chainA and surface residues chainB

You're brilliant Ozo....many thanks...sleepless nights are over! Sarah