PSVS Links for Rosetta MR Project

#! /usr/bin/perl #this script is designed to parse PSVS reports by project_name, and generate html file which contains a table about protein information #Target name, source, link to PSVS concise report, summary report, bb/all r.m.s.d for order region, RPF score,link to precision map,Z score, link of superimposed image with pdb structure, #link of coordinate file, chemcial shift file and peak list files use strict; use warnings; use LWP::UserAgent; use HTTP::Request; use XML::Simple; use Data::Dumper; my $ua = LWP::UserAgent->new(timeout => 600); my $psvs_url = 'http://psvs.nesg.org/results/rosetta_MR/'; my $psvs_path = '/data/PSVS/PSVS-v1.4-dev/results/rosetta_MR/'; #my $si_path = $eNMR_path.'si/'; my $output_file = $psvs_path.'PSVS_summary_blind.html'; die("Usage:generateTable.pl \n") if(scalar @ARGV < 1); my ($rmsd_file) = shift @ARGV; my %projs = ('nmr' => 'NMR', 'r3' => 'R3', 'r3_cst' => 'R3Cons'); #rmsd file stored rmsd, gdt_ts, tm, and Ca_chemical_shift_pred_corrlation information open(RMSD,"<$rmsd_file") or die("failed to open rmsd file:$!"); my %rmsd; while(){ chomp($_); next if(/^target/); my @values = split(/\s+/,$_); my($target,$source,$ca_rmsd,$bb_rmsd_order,$bb_rmsd_all,$heavy_rmsd_order,$heavy_rmsd_all,$tm,$gdt,$n1,$n2) = @values; $target =~ tr/a-z/A-Z/; $rmsd{$target}->{$source}->{'proj_name'} = $target.'_'.$projs{$source}.'_em_bcr3'; $rmsd{$target}->{$source}->{'ca_rmsd'} = $ca_rmsd; $rmsd{$target}->{$source}->{'bb_rmsd_order'} = $bb_rmsd_order; $rmsd{$target}->{$source}->{'bb_rmsd_all'} = $bb_rmsd_all; $rmsd{$target}->{$source}->{'heavy_rmsd_order'} = $heavy_rmsd_order; $rmsd{$target}->{$source}->{'heavy_rmsd_all'} = $heavy_rmsd_all; $rmsd{$target}->{$source}->{'gdt'} = $gdt; $rmsd{$target}->{$source}->{'tm'} = $tm; # $rmsd{$target}->{$source}->{'Ca_R'} = $Ca_R; } close RMSD; my %table = (); #to save all the information included in the table foreach my $target (sort keys %rmsd){ foreach my $source (sort keys %projs){ my $projName = $rmsd{$target}->{$source}->{'proj_name'}; $table{$target}->{$source} = parsePSVS($projName); } } outputLink(); outputTable($output_file); 1; #create a HTML file linked to all PSVS_results sub outputLink{ open(O,">$psvs_path/psvs_link.html") or die("failed to open psvs_link.html:$!"); print O "\n\nPSVS Links for Rosetta MR Project\n\n\n"; print O "

PSVS Links for Rosetta MR Project

"; print O "\n"; foreach my $target (sort keys %table){ print O "\n"; my @sources = sort keys %{$table{$target}}; unshift(@sources,' '); foreach my $source (@sources){ print O "\n"; } print O "\n\n\n"; foreach my $source (@sources){ next if($source eq ' '); my %info = %{$table{$target}->{$source}}; print O "\n"; } print O "\n"; } print O "

$source
$target

\n\n"; close O; } #to output the PSVS information into a html table sub outputTable{ my $output_file = shift; open(P,">psvs_info.txt") or die("can't open file psvs_info.txt:$!"); my @psvs_fields = ('Target','Method','bb_rmsd_ord','bb_rmsd_all','heavy_rmsd_ord','heavy_rmsd_all','0.1','0.2','0.5','deg1','deg10','Precision','Recall','DP','v3d','prosa','procheck_bb','procheck_all','molprobity'); print P join("\t",@psvs_fields),"\n"; open(O,">$output_file") or die("failed to open $output_file:$!"); print O "\n\nAnalysis for Rosetta MR Project\n\n\n"; print O "\n\n\n\n"; print O "\n\n\n\n\n\n\n\n"; my @fields = ('Target','Method','Model#', 'Ca_All¹','BB_Ord²','BB_All²','Hvy_Ord²','Hvy_All²','TM-Score¹','GDT-TS³', 'Concise Report','Summary', 'backbone⁴','heavy⁴', '0.1-0.2 Å','0.2-0.5 Å','>0.5 Å', '1-10 °','>10 °', 'DP-score','Precicison Map', 'Verify3D','ProsaII','Procheck (phi-psi)⁴','Procheck (all)⁴','MolProbity Clashscore', 'superimposed Coordinates','input files⁵'); foreach (@fields){ print O "\n"; } print O "\n"; my $class = ''; foreach my $target (sort keys %table){ my @sources = sort keys %{$table{$target}}; my $n_source = scalar @sources; $class = $sources[0]; # $class = ($i%2 == 1?'specalt':'spec'); print O "\n"; my $j = 0; foreach my $source (@sources){ #$class = ($i%2 == 1?'specalt':'spec'); print O "\n" if($j); my %info = %{$table{$target}->{$source}}; my @values = ($projs{$source}); my @psvss = ($target,$source); my $data = $info{'data'}; cpush(\@values,[$data->{'STRUCTURES_USED'}]); cpush(\@values,[$rmsd{$target}->{$source}->{'ca_rmsd'},$rmsd{$target}->{$source}->{'bb_rmsd_order'},$rmsd{$target}->{$source}->{'bb_rmsd_all'},$rmsd{$target}->{$source}->{'heavy_rmsd_order'},$rmsd{$target}->{$source}->{'heavy_rmsd_all'},$rmsd{$target}->{$source}->{'tm'},$rmsd{$target}->{$source}->{'gdt'}]); cpush(\@values,[$info{'c_rpt'},$info{'s_rpt'}],1); cpush(\@values,[$data->{'RMSD'}->{'SELECTED'}->{'BACKBONE_ATOMS'},$data->{'RMSD'}->{'SELECTED'}->{'HEAVY_ATOMS'}]); cpush(\@psvss,[$data->{'RMSD'}->{'SELECTED'}->{'BACKBONE_ATOMS'},$data->{'RMSD'}->{'ALL'}->{'BACKBONE_ATOMS'}, $data->{'RMSD'}->{'SELECTED'}->{'HEAVY_ATOMS'},$data->{'RMSD'}->{'ALL'}->{'HEAVY_ATOMS'}]); cpush(\@values,[$data->{'DIST_VIOLATIONS'}->{'GROUP1'},$data->{'DIST_VIOLATIONS'}->{'GROUP2'},$data->{'DIST_VIOLATIONS'}->{'GROUP3'}]); cpush(\@psvss,[$data->{'DIST_VIOLATIONS'}->{'GROUP1'},$data->{'DIST_VIOLATIONS'}->{'GROUP2'},$data->{'DIST_VIOLATIONS'}->{'GROUP3'}]); cpush(\@values,[$data->{'DIHEDRAL_VIOLATIONS'}->{'GROUP1'},$data->{'DIHEDRAL_VIOLATIONS'}->{'GROUP2'}]); cpush(\@psvss,[$data->{'DIHEDRAL_VIOLATIONS'}->{'GROUP1'},$data->{'DIHEDRAL_VIOLATIONS'}->{'GROUP2'}]); if($data->{'RPF'}){ cpush(\@values,[$data->{'RPF'}->{'DP_SCORE'}]); cpush(\@values,[$info{'precMap'}],1); }else{ push(@values,('N/A','N/A')); } cpush(\@psvss,[$data->{'RPF'}->{'PRECISION'},$data->{'RPF'}->{'RECALL'},$data->{'RPF'}->{'DP_SCORE'}]); # cpush(\@values,[$rmsd{$target}->{$source}->{'Ca_R'}]); my $z_score_ref = $data->{'QFACTORS'}->{'ZSCORE'}; cpush(\@values,[$z_score_ref->{'VERIFY3D'},$z_score_ref->{'PROSAII_NEG'},$z_score_ref->{'PROCHECK_G_PHI_PSI'},$z_score_ref->{'PROCHECK_G_ALL'},$z_score_ref->{'MAGE_CLASH'}]); cpush(\@psvss,[$z_score_ref->{'VERIFY3D'},$z_score_ref->{'PROSAII_NEG'},$z_score_ref->{'PROCHECK_G_PHI_PSI'},$z_score_ref->{'PROCHECK_G_ALL'},$z_score_ref->{'MAGE_CLASH'}]); cpush(\@values,[$info{'mol'},$info{'input'}],1); foreach (@values){ print O "\n"; } print O "\n"; print P join("\t",@psvss); $j++; } } print O "

Analysis for Rosetta MR Project
General	RMSD to X-ray structure(Å) and structural similarity							PSVS reports		Ensemble RMSD(Å)		NOE Violations			ACO Violations		RPF anysis		Structural Quality Z-scores					Misc
$_
$target
$_

\n"; print O "¹ Y. Zhang, J. Skolnick, Scoring function for automated assessment of protein structure template quality, Proteins, 2004 57: 702-710
\n"; print O "¹ RMSD calculated by Pymol
\n"; print O "³ Zemla A. (2003) LGA: A method for finding 3D similarities in protein structures.
\n"; print O "⁴Ensemble RMSDs and Procheck Z-Scores are calculated based on ordered residues of NMR structures deposited in PDB, calculated By PdbStat.
\n"; print O "⁵ Input files including coordinate files, peak list files, chemical shift files and RPF control file.
\n"; print O "\n\n"; close O; close P; } #check if data exists before push sub cpush{ my ($array_ref,$items_ref,$link_b) = @_; foreach my $item (@$items_ref){ if(defined $item){ $item = round($item,3) if($item =~ /^\-?\d+\.\d{4}/); $item = "link" if($link_b); push(@$array_ref,$item); }else{ push(@$array_ref,'N/A'); } } return; } #this script is to parse all the available PSVS report information sub parsePSVS{ my $projName = shift; my $projUrl = $psvs_url.$projName; my $projPath = $psvs_path.$projName; my %info = (); $info{'c_rpt'} = $projUrl.'/OUTPUT.html'; $info{'s_rpt'} = $projUrl."/${projName}_results_summary.html"; $info{'precMap'} = $projUrl.'/precision.jpg' if(-e "${projPath}/precision.jpg"); $info{'sauPic'} = $projUrl.'/sausage.jpg' if(-e "${projPath}/sausage.jpg"); $info{'molPic'} = $projUrl.'/molecule.jpg' if(-e "${projPath}/sausage.jpg"); $info{'mol'} = $projUrl.'/selSi.pdb' if(-e "${projPath}/selSi.pdb"); my $coorFile = $1 if($projName =~ /(.*?)\d*$/); #my $s_rpt_p = $psvs_path."/${projName}_results_summary.html"; #open(S,"<$s_rpt_p") or die("failed to open file $s_rpt_p:$!"); my $xml_path = $projPath."/${projName}_parseable_results.xml"; my $data = XMLin($xml_path); $info{'data'} = $data; createInputHtml($projName); $info{'input'} = "${psvs_url}/htdocs/${projName}_input.html"; return \%info; } sub createInputHtml{ my $projName = shift; my $inputPath = $psvs_path.$projName.'/input'; my $inputUrl = $psvs_url.$projName.'/input/'; open(H,">$psvs_path/htdocs/${projName}_input.html") or die("failed to open input html:$!"); print H "\n\nInput files for $projName\n\n\n"; print H "\n"; my %inp_files = (); opendir(ID,$inputPath) or die("failed to open directory $inputPath:$!"); my @files = readdir(ID); close ID; foreach (@files){ if(/pdb$/){ push(@{$inp_files{'coordinates file'}},$_); }elsif(/bmrb$/){ push(@{$inp_files{'chemical shift file'}},$_); }elsif(/list$/ or /peaks$/){ push(@{$inp_files{'peaks list files'}},$_); }elsif(/upl$/ or /lol$/ or /mr$/){ push(@{$inp_files{'constraints files'}},$_); }elsif(/ctrl_file/){ push(@{$inp_files{'RPF control file'}},$_); } } print H ""; print H "\n"; foreach my $keyword (sort keys %inp_files){ print H ""; my $content = ''; foreach (@{$inp_files{$keyword}}){ $content .= "$_ "; } print H "\n"; } print H "

Table for input files of $projName
file description	file names
$keyword	$content

\n\n"; close H; } sub round{ my ($value,$n) = @_; return int($value*(10**$n)+0.5)/(10**$n); }