option to use average distance instead of shortest distance measures.…

… also added v0.5.5 tar.gz
ding-lab · Sep 29, 2016 · 67a72a6 · 67a72a6
1 parent 0ac2f78
commit 67a72a6
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 2 deletions.
diff --git a/HotSpot3D-0.5.4.tar.gz → HotSpot3D-0.5.5.tar.gz b/HotSpot3D-0.5.4.tar.gz → HotSpot3D-0.5.5.tar.gz
diff --git a/lib/TGI/Mutpro/Preprocess/Calpro.pm b/lib/TGI/Mutpro/Preprocess/Calpro.pm
@@ -59,6 +59,9 @@ use TGI::Mutpro::Preprocess::Uniprot;
 use TGI::Mutpro::Preprocess::PdbStructure;
 use TGI::Mutpro::Preprocess::HugoGeneMethods;
 
+my $MINDISTANCE = "minDistance";
+my $AVGDISTANCE = "averageDistance";
+
 sub new {
     my $class = shift;
     my $this = {};
@@ -70,6 +73,7 @@ sub new {
     $this->{'uniprot_ref'} = undef;
     $this->{'stat'} = undef;
     $this->{'pdb_file_dir'} = undef;
+    $this->{'distance_measure'} = $AVGDISTANCE;
     ## add drug port database file (08.04.2014)
     #$this->{'drugport_file'} = undef;
     bless $this, $class;
@@ -87,6 +91,7 @@ sub process {
         'output-dir=s'    => \$this->{'output_dir'},
         'uniprot-id=s'    => \$this->{'uniprot_id'},
         'pdb-file-dir=s'  => \$this->{'pdb_file_dir'},
+        'measure=s'  => \$this->{'distance_measure'},
         #'drugport-file=s' => \$this->{'drugport_file'},
 
         'help' => \$help,
@@ -96,6 +101,10 @@ sub process {
     unless(defined $this->{'uniprot_id'}) { warn 'You must provide a Uniprot ID !', "\n"; die $this->help_text(); }
     unless( $this->{'output_dir'} and (-e $this->{'output_dir'} ) ) { warn 'You must provide a output directory ! ', "\n"; die $this->help_text(); }
     unless( $this->{'pdb_file_dir'} and (-e $this->{'pdb_file_dir'}) ) { warn 'You must provide a PDB file directory ! ', "\n"; die $this->help_text(); }
+	if ( $this->{'distance_measure'} eq $MINDISTANCE or $this->{'distance_measure'} eq $AVGDISTANCE ) {
+		warn "HotSpot3D::Calpro warning: measure not recognized, resetting to default = averageDistance\n";
+		$this->{'distance_measure'} = $AVGDISTANCE;
+	}
     #unless( $this->{'drugport_file'} and (-e $this->{'drugport_file'}) ) { warn 'You must provide a drugport database file ! ', "\n"; die $this->help_text(); }
     #### processing ####
     # This can be used if only want to write out pairs when one is in a Uniprot-annotated domain
@@ -314,7 +323,13 @@ sub writeProximityFile {
                     # is not close to the amino acid at '$residuePosition' 
                     # of peptide chain '$uniprotChain'
 		    $aaObjRef = $$peptideRef{$chain}->getAminoAcidObject($position);
-		    $distanceBetweenResidues = $$aaObjRef->minDistance($uniprotAminoAcidRef);
+			if ( $this->{'distance_measure'} == $MINDISTANCE ) {
+				$distanceBetweenResidues = $$aaObjRef->minDistance($uniprotAminoAcidRef);
+			} elsif ( $this->{'distance_measure'} == $AVGDISTANCE ) {
+				$distanceBetweenResidues = $$aaObjRef->averageDistance($uniprotAminoAcidRef);
+			} else {
+				$distanceBetweenResidues = $$aaObjRef->averageDistance($uniprotAminoAcidRef);
+			}
 		    if ( $distanceBetweenResidues > $this->{'max_3d_dis'} ) { next; }
 		    # Also skip if the two amino acids are in the same chain and 
                     # within <= $PrimarySequenceDistance
@@ -557,6 +572,7 @@ Usage: hotspot3d calpro [options]
                              OPTIONAL
 --3d-distance-cutoff         Maximum 3D distance (<= Angstroms), default: 100
 --linear-cutoff              Minimum linear distance (> peptides), default: 0
+--measure                    Distance measurement between residues (minDistance or averageDistance), default: averageDistance
 
 --help                       this message
 

diff --git a/lib/TGI/Mutpro/Preprocess/Uppro.pm b/lib/TGI/Mutpro/Preprocess/Uppro.pm
@@ -23,6 +23,9 @@ use List::MoreUtils qw( uniq );
 use TGI::Mutpro::Preprocess::Uniprot;
 use TGI::Mutpro::Preprocess::HugoGeneMethods;
 
+my $MINDISTANCE = "minDistance";
+my $AVGDISTANCE = "averageDistance";
+
 sub new {
     my $class = shift;
     my $this = {};
@@ -34,6 +37,7 @@ sub new {
         'status' => undef,
         'pdb_file_dir' => undef,
         'genes' => undef,
+        'distance_measure' => $AVGDISTANCE,
         #'drugport_file' => undef, 
         'cmd_list_submit_file' => "cmd_list_submit_file", 
     );
@@ -53,6 +57,7 @@ sub process {
         'output-dir=s'    => \$this->{'output_dir'},
         'pdb-file-dir=s'  => \$this->{'pdb_file_dir'},
         'gene-file=s'  => \$this->{'genes'},
+        'measure=s'  => \$this->{'distance_measure'},
         #'drugport-file=s' => \$this->{'drugport_file'},
         'cmd-list-submit-file=s' => \$this->{'cmd_list_submit_file'},
         'hold'   => \$this->{'hold'},
@@ -72,11 +77,15 @@ sub process {
     my $pdbcor_dir = "$pro_dir\/pdbCoordinateFiles";
     my $log_file = "$this->{'output_dir'}\/hugo.uniprot.pdb.csv";
     my $log_dir = "$this->{'output_dir'}\/Logs\/";
+    my $measure = $this->{'distance_measure'};
     unless (-e $pro_dir) { mkdir($pro_dir) || die "HotSpot3D Uppro Error: can not make $pro_dir !\n"; }
     unless (-e $log_file) { if (system("touch $log_file") != 0) { die "HotSpot3D Uppro Error: can not make hugo uniprot file !\n"; } }
     unless (-e $inpro_dir) { mkdir($inpro_dir) || die "HotSpot3D Uppro Error: can not make $inpro_dir !\n"; }
     unless (-e $pdbcor_dir) { mkdir($pdbcor_dir) || die "HotSpot3D Uppro Error: can not make $pdbcor_dir !\n"; }
     unless ( -e $log_dir ) { mkdir( $log_dir ) || die "HotSpot3D Uppro Error: can not make $log_dir !\n"; }
+	unless ( $measure eq $MINDISTANCE or $measure eq $AVGDISTANCE ) {
+		warn "HotSpot3D::Uppro warning: measure not recognized, resetting to default = averageDistance\n";
+	}
     my %uniprotid_toupdate;
     my $uniprot_to_structureref = $this->current_structures($log_file);
     my $uniprot_fileref = $this->currentuniprot_files($pro_dir);
@@ -143,7 +152,7 @@ sub process {
         system("touch $inpro_dir/$_.ProximityFile.csv");
 		my $bsub = "bsub -oo ".$log_dir.$_.".err.log -R 'select[type==LINUX64 && mem>16000] rusage[mem=16000]' -M 16000000";
 		my $update_program = " 'hotspot3d calpro";
-		my $programOptions = " --output-dir=".$this->{'output_dir'}." --pdb-file-dir=".$this->{'pdb_file_dir'}." --uniprot-id=".$_." --3d-distance-cutoff=".$this->{'max_3d_dis'}." --linear-cutoff=".$this->{'min_seq_dis'}."'";
+		my $programOptions = " --output-dir=".$this->{'output_dir'}." --pdb-file-dir=".$this->{'pdb_file_dir'}." --uniprot-id=".$_." --3d-distance-cutoff=".$this->{'max_3d_dis'}." --linear-cutoff=".$this->{'min_seq_dis'}." --measure=".$this->{'distance_measure'}."'";
         my $submit_cmd = $bsub.$update_program.$programOptions;
         print STDOUT $submit_cmd."\n"; 
         $cmd_list_submit_file_fh->print($submit_cmd."\n");
@@ -209,6 +218,7 @@ Usage: hotspot3d uppro [options]
 --gene-file                  File with HUGO gene names in the first column (like a .maf)
 --3d-distance-cutoff         Maximum 3D distance (<= Angstroms), defaul: 100
 --linear-distance-cutoff     Minimum linear distance (> peptides), default: 0
+--measure                    Distance measure between residues (minDistance or averageDistance), default: averageDistance
 --cmd-list-submit-file       Batch jobs file to run calpro step in parallel, default: cmd_list_submit_file
 --hold                       Do not submit batch jobs, just write cmd_list_submit_file, default: submits (takes no input)