Merge pull request #4 from MattOates/feature/update_data_download

Make timeout waiting for ELM ten minutes to try and improve chance of…

.gitignore

@@ -28,3 +28,4 @@ inc/
 nytprof.out
 pm_to_blib
 pod2htm*.tmp
+fatlib/

Build.PL

@@ -0,0 +1,32 @@
+use strict;
+use warnings;
+use Module::Build;
+
+use 5.008;
+
+
+my $builder = Module::Build->new(
+    module_name         => 'ELM',
+    license             => 'lgpl_3',
+    dist_author         => 'Matt Oates <[email protected]>',
+    dist_abstract       => 'CLI tool for assigning Eukaryotic Linear Motifs from the ELM.eu.org database',
+    create_makefile_pl  => 0,     #'traditional',
+    script_files        => 'bin/melm',
+    create_readme       => 0,
+    requires            => {
+        'LWP::UserAgent' => '6.15',
+        'BioPerl'        => '1.7.2',
+        'Class::Tiny'    => '1.004',
+        'Pod::Usage'     => '1.69'
+    },
+    build_requires      => {
+        'Test::More'                      => '0.47',
+        'Test::Pod::Coverage'             => '1.10',
+        'Test::Pod'                       => '1.51',
+        'Devel::Cover'                    => '1.23',
+        'Devel::Cover::Report::Coveralls' => '0.11'
+    },
+);
+
+$builder->create_build_script();
+

CHANGES.md

@@ -1,27 +1,32 @@
-###2014-08-30
-   * First features added.
+###2019-05-17
+   * Updated timeout so that downloads from ELM.eu.org are more likely to succeed.
+   * Cut a new maintenance release 1.4.2
 
-###2014-09-05
-   * Masking with only specific ELM classes included based on expect value and motif type
+###2016-07-05
+    * Majority of refactor complete
 
-###2014-09-08
-   * ELM instance downloading
-   * False Positive logic filtering based on ELM instances library.
-   * GFF3 and assignment output
+###2016-06-25
+   * Huge refactor into split packages allowing more ELM based tools, releases now are fatpack
+
+###2016-05-23
+   * Removed bitrot due to changes at ELM.eu.org and enabled support for v1.4 of ELM
+
+###2014-09-10
+   * Allowed for the script to upgrade itself from GitHub and made it a bit more friendly to use
 
 ###2014-09-09
    * Integrated ANCHOR predictions if this is installed on the system (independent of OS)
    * Limit motif assignment to predicted binding regions (MoRF)
    * Limit motif assignment to predicted disordered regions
 
-###2014-09-10
-   * Allowed for the script to upgrade itself from GitHub and made it a bit more friendly to use
+###2014-09-08
+   * ELM instance downloading
+   * False Positive logic filtering based on ELM instances library.
+   * GFF3 and assignment output
 
-###2016-05-23
-   * Removed bitrot due to changes at ELM.eu.org and enabled support for v1.4 of ELM
+###2014-09-05
+   * Masking with only specific ELM classes included based on expect value and motif type
 
-###2016-06-25
-   * Huge refactor into split packages allowing more ELM based tools, releases now are fatpack
+###2014-08-30
+   * First features added.
 
-###2016-07-05
-    * Majority of refactor complete

README.md

@@ -101,7 +101,7 @@ License
 =======
 
            melm - Mask and assign ELM motifs in protein sequence libraries
-           (C) 2014-2016  Dr Matt E. Oates
+           (C) 2014-2019  Dr Matt E. Oates
 
            This program is free software: you can redistribute it and/or modify
            it under the terms of the GNU Affero General Public License as

bin/melm

@@ -68,6 +68,10 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 EXAMPLES
 
+First time running the script, get the ELM library locally installed to your home
+
+    melm --update
+
 Soft mask regions of a protein that do not contain any plausible ELM motifs
 
     melm human_proteins.fa > human_proteins_motifs.fa
@@ -80,10 +84,14 @@ Mask all PTM sites with 'X' in a set of seqences
 
     melm --hard-mask --mask-motifs --type=MOD human_proteins.fa > human_no_ptms.fa
 
-Get a GFF3 file for a whole genomes worth of protein annotations
+Get a GFF3 file for a whole genome's worth of protein annotations
 
     melm --assign --GFF3 human_proteins.fa > human_motifs.gff3
 
+Get another GFF3 file but this time be strict on assignment to those active in native disordered state
+
+    melm --assign --GFF3 --logic-filter --disorder-filter human_proteins.fa > disordered_hiqual_human_motifs.gff3
+
 Get the latest ELM classes library for use in another script or by yourself
 
     melm --update --list-classes
@@ -99,7 +107,7 @@ B<Matt Oates> - I<[email protected]>
 =head1 LICENSE
 
     melm - Mask and assign ELM motifs in protein sequence libraries
-    (C) 2014-2016  Dr Matt E. Oates
+    (C) 2014-2019  Dr Matt E. Oates
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as
@@ -116,6 +124,10 @@ B<Matt Oates> - I<[email protected]>
 
 =head1 EDIT HISTORY
 
+2019-05-17
+   * Updated timeout so that downloads from ELM.eu.org are more likely to succeed.
+   * Cut a new maintenance release 1.4.2
+
 2016-07-05 - Matt Oates
     * Majority of refactor complete
 
@@ -147,6 +159,8 @@ B<Matt Oates> - I<[email protected]>
 =head1 TODO
 
     * Create an HTML output report with everything in
+    * Get the interaction partner data and report on it
+    * Do some domain assignment and match up the PDB interaction partners
 
 =cut
 
@@ -167,7 +181,7 @@ use ELM;
 use ELM::Utils 'get_www';
 
 #Current version of the script
-our $VERSION = "v1.4.1";
+our $VERSION = "v1.4.2";
 
 #User options
 my $help;
@@ -220,7 +234,7 @@ my @fasta_files = @ARGV;
 #Print out some help if it was asked for or if no arguments were given.
 pod2usage(-exitstatus => 0, -verbose => 2) if $help;
 
-pod2usage(-exitstatus => 0, -verbose => 1, -msg => "mELM version $VERSION by Matt Oates (C) 2014-2016. Please provide some sequence files to mask or assign ELM motifs to.") 
+pod2usage(-exitstatus => 0, -verbose => 1, -msg => "mELM version $VERSION by Matt Oates (C) 2014-2019. Please provide some sequence files to mask or assign ELM motifs to.") 
     unless $update or $upgrade or $list_classes or $list_instances or scalar @fasta_files >= 1;
 
 my $elm = ELM->new(

lib/ELM.pm

@@ -1,12 +1,12 @@
-package ELM v1.4.1;
+package ELM v1.4.2;
 =encoding UTF-8
 =head1 NAME
 
 ELM - Class to do analysis with the ELM regex library
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -219,7 +219,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as

lib/ELM/AminoAcids.pm

@@ -1,4 +1,4 @@
-package ELM::AminoAcids v1.4.1;
+package ELM::AminoAcids v1.4.2;
 require Exporter;
 =encoding UTF-8
 =head1 NAME
@@ -7,7 +7,7 @@ ELM::AminoAcids - Functions for dealing with amino acid specific calculations
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -142,7 +142,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as

lib/ELM/Anchor.pm

@@ -1,12 +1,12 @@
-package ELM::Anchor v1.4.1;
+package ELM::Anchor v1.4.2;
 =encoding UTF-8
 =head1 NAME
 
 ELM::Anchor - Class to wrap ANCHOR and get assignments
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -194,7 +194,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as

lib/ELM/Calc.pm

@@ -1,4 +1,4 @@
-package ELM::Calc v1.4.1;
+package ELM::Calc v1.4.2;
 require Exporter;
 =encoding UTF-8
 =head1 NAME
@@ -7,7 +7,7 @@ ELM::Calc - Functions for calculating sequence assignment specific tasks
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -138,7 +138,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as

lib/ELM/Library.pm

@@ -1,12 +1,12 @@
-package ELM::Library v1.4.1;
+package ELM::Library v1.4.2;
 =encoding UTF-8
 =head1 NAME
 
 ELM::Library - Class to hold the ELM regex library
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -170,7 +170,7 @@ sub _get_instance_seqs($self) {
 sub _update_elm_instances($self) {
     my $instances_version;
     my %instance_logic = ('false positive' => 'FP','true negative' => 'TN','true positive', => 'TP', 'unknown' => 'U');
-    my $instances_tsv = get_www('http://elm.eu.org/instances.tsv?q=*&taxon=&instance_logic=');
+    my $instances_tsv = get_www('http://elm.eu.org/instances.tsv?q=*');
     my %uniprot_sequences = $self->_get_instance_seqs();
     #Each record looks like:
     #Accession, ELMType, ELMIdentifier, ProteinName, Primary_Acc, Accessions, Start, End, References, Methods, InstanceLogic, PDB, Organism
@@ -234,7 +234,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as

lib/ELM/Utils.pm

@@ -1,4 +1,4 @@
-package ELM::Utils v1.4.1;
+package ELM::Utils v1.4.2;
 require Exporter;
 =encoding UTF-8
 =head1 NAME
@@ -7,7 +7,7 @@ ELM::Utils - Common helper functions
 
 =head1 VERSION
 
-Version v1.4.1
+Version v1.4.2
 
 =cut
 
@@ -49,6 +49,7 @@ sub get_www($url) {
     }
     #Decided to localise this and just handle checking for deps properly
     my $ua = LWP::UserAgent->new;
+    $ua->timeout(600); # Wait at least 10 minutes, ELM can be very slow to respond
 
     my $response = $ua->get($url);
     if ($response->is_success) {
@@ -105,7 +106,7 @@ If you have used mELM with ANCHOR predictions please cite the following:
 
 =head1 LICENSE AND COPYRIGHT
 
-Copyright 2016 Matt Oates.
+Copyright 2019 Matt Oates.
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as