diff --git a/misc-scripts/xref_projection/submit_projections.pl b/misc-scripts/xref_projection/submit_projections.pl index 3ccd8a9e57b44ad0895786f496fc62e67ae9f2e2..efa96fc720fdc9899a19f87bf8f5a237f13c089d 100644 --- a/misc-scripts/xref_projection/submit_projections.pl +++ b/misc-scripts/xref_projection/submit_projections.pl @@ -4,11 +4,11 @@ use strict; # Remember to check/set the various config optons # ------------------------------ config ------------------------------- -my $release = 51; +my $release = 52; my $base_dir = "/lustre/scratch1/ensembl/gp1/projections/"; -my $conf = "release_51.ini"; # registry config file, specifies Compara location +my $conf = "release_52.ini"; # registry config file, specifies Compara location # location of other databases my $host = "ens-staging"; @@ -16,6 +16,9 @@ my $port = 3306; my $user = "ensadmin"; my $pass = "ensembl"; +# load limit for ens-staging MySQL instance above which jobs won't be started +my $limit = 200; + # -------------------------- end of config ---------------------------- # check that base directory exists @@ -34,32 +37,42 @@ if (! -e $dir) { # common options my $script_opts = "-conf $conf -host $host -user $user -port $port -pass $pass -version $release -release $release -quiet"; -#my $bsub_opts = "-R'select[myens-staging<200]'"; my $bsub_opts = ""; - -my @names_and_go = (["human", "alpaca" ], - ["human", "armadillo" ], - ["human", "bushbaby" ], - ["human", "cat" ], - ["human", "chicken" ], - ["human", "chimp" ], - ["human", "cow" ], - ["human", "dog" ], - ["human", "dolphin" ], - ["human", "elephant" ], - ["human", "ground_shrew" ], - ["human", "guinea_pig" ], - ["human", "horse" ], - ["human", "hyrax" ], - ["human", "kangaroo_rat" ], - ["human", "squirrel" ], - ["human", "tarsier" ], - ["human", "tenrec" ], - ["human", "tree_shrew" ], - ["human", "western_european_hedgehog"], - ["human", "xenopus" ], - ["mouse", "kangaroo_rat" ], - ["mouse", "rat" ]); +$bsub_opts .= "-R'select[myens-staging<$limit]'"; + + +my @names_1_1 = (["human", "chimp" ], + ["human", "opossum" ], + ["human", "dog" ], + ["human", "cow" ], + ["human", "macaque" ], + ["human", "chicken" ], + ["human", "xenopus" ], + ["human", "guinea_pig" ], + ["human", "armadillo" ], + ["human", "tenrec" ], + ["human", "western_european_hedgehog"], + ["human", "cat" ], + ["human", "elephant" ], + ["human", "microbat" ], + ["human", "platypus" ], + ["human", "rabbit" ], + ["human", "bushbaby" ], + ["human", "ground_shrew" ], + ["human", "squirrel" ], + ["human", "tree_shrew" ], + ["human", "pika" ], + ["human", "mouse_lemur" ], + ["human", "horse" ], + ["human", "orang_utan" ], + ["human", "dolphin" ], + ["human", "hyrax" ], + ["human", "megabat" ], + ["human", "tarsier" ], + ["human", "alpaca" ], + ["human", "gorilla" ], + ["mouse", "kangaroo_rat" ], + ["mouse", "rat" ]); my @names_1_many = (["human", "zebrafish" ], ["human", "medaka" ], @@ -67,64 +80,96 @@ my @names_1_many = (["human", "zebrafish" ], ["human", "fugu" ], ["human", "stickleback"]); -my @go_only = (["human", "mouse" ], - ["human", "rat" ], - ["mouse", "alpaca" ], - ["mouse", "armadillo" ], - ["mouse", "bushbaby" ], - ["mouse", "cat" ], - ["mouse", "chicken" ], - ["mouse", "chimp" ], - ["mouse", "cow" ], - ["mouse", "dog" ], - ["mouse", "dolphin" ], - ["mouse", "elephant" ], - ["mouse", "ground_shrew" ], - ["mouse", "guinea_pig" ], - ["mouse", "human" ], - ["mouse", "hyrax" ], - ["mouse", "kangaroo_rat" ], - ["mouse", "macaque" ], - ["mouse", "megabat" ], - ["mouse", "microbat" ], - ["mouse", "mouse_lemur" ], - ["mouse", "opossum" ], - ["mouse", "orang_utan" ], - ["mouse", "pika" ], - ["mouse", "platypus" ], - ["mouse", "rabbit" ], - ["mouse", "rat" ], - ["mouse", "squirrel" ], - ["mouse", "tarsier" ], - ["mouse", "tenrec" ], - ["mouse", "tree_shrew" ], - ["mouse", "western_european_hedgehog"], - ["mouse", "horse" ], - ["rat", "human" ], - ["rat", "mouse" ], - ["drosophila", "anopheles" ], - ["drosophila", "aedes" ], - ["danio", "xenopus" ], - ["danio", "fugu" ], - ["danio", "tetraodon" ], - ["xenopus", "danio" ]); +my @go_terms = (["human", "mouse" ], + ["human", "rat" ], + ["human", "dog" ], + ["human", "chicken" ], + ["human", "cow" ], + ["human", "chimp" ], + ["human", "macaque" ], + ["human", "guinea_pig" ], + ["human", "bushbaby" ], + ["human", "rabbit" ], + ["human", "cat" ], + ["human", "ground_shrew" ], + ["human", "western_european_hedgehog"], + ["human", "microbat" ], + ["human", "armadillo" ], + ["human", "elephant" ], + ["human", "tenrec" ], + ["human", "opossum" ], + ["human", "platypus" ], + ["human", "squirrel" ], + ["human", "tree_shrew" ], + ["human", "pika" ], + ["human", "mouse_lemur" ], + ["human", "horse" ], + ["human", "orang_utan" ], + ["human", "dolphin" ], + ["human", "hyrax" ], + ["human", "megabat" ], + ["human", "tarsier" ], + ["human", "alpaca" ], + ["human", "kangaroo_rat" ], + ["human", "gorilla" ], + ["mouse", "human" ], + ["mouse", "rat" ], + ["mouse", "dog" ], + ["mouse", "chicken" ], + ["mouse", "cow" ], + ["mouse", "chimp" ], + ["mouse", "macaque" ], + ["mouse", "guinea_pig" ], + ["mouse", "bushbaby" ], + ["mouse", "rabbit" ], + ["mouse", "cat" ], + ["mouse", "ground_shrew" ], + ["mouse", "western_european_hedgehog"], + ["mouse", "microbat" ], + ["mouse", "armadillo" ], + ["mouse", "elephant" ], + ["mouse", "tenrec" ], + ["mouse", "opossum" ], + ["mouse", "platypus" ], + ["mouse", "squirrel" ], + ["mouse", "tree_shrew" ], + ["mouse", "pika" ], + ["mouse", "horse" ], + ["mouse", "orang_utan" ], + ["mouse", "mouse_lemur" ], + ["mouse", "dolphin" ], + ["mouse", "hyrax" ], + ["mouse", "megabat" ], + ["mouse", "tarsier" ], + ["mouse", "alpaca" ], + ["mouse", "kangaroo_rat" ], + ["mouse", "gorilla" ], + ["rat", "human" ], + ["rat", "mouse" ], + ["drosophila", "anopheles" ], + ["drosophila", "aedes" ], + ["danio", "xenopus" ], + ["danio", "fugu" ], + ["danio", "tetraodon" ], + ["xenopus", "danio" ]); my ($from, $to, $o, $e, $n); # ---------------------------------------- -# Display names and GO terms +# Display names -foreach my $pair (@names_and_go) { +# 1:1 +foreach my $pair (@names_1_1) { ($from, $to) = @$pair; $o = "$dir/names_${from}_$to.out"; $e = "$dir/names_${from}_$to.err"; $n = substr("n_${from}_$to", 0, 10); # job name display limited to 10 chars my $all = ($from eq "human") ? "" : "--all_sources"; # non-human from species -> use all sources - print "Submitting name and GO term projection from $from to $to\n"; - system "bsub $bsub_opts -o $o -e $e -J $n perl project_display_xrefs.pl $script_opts -from $from -to $to -names -delete_names -go_terms -delete_go_terms -no_database $all"; + print "Submitting name projection from $from to $to\n"; + system "bsub $bsub_opts -o $o -e $e -J $n perl project_display_xrefs.pl $script_opts -from $from -to $to -names -delete_names -no_database $all"; } -# 1:many name projections +# 1:many foreach my $pair (@names_1_many) { ($from, $to) = @$pair; $o = "$dir/names_${from}_$to.out"; @@ -135,11 +180,11 @@ foreach my $pair (@names_1_many) { } # ---------------------------------------- -# GO terms only +# GO terms $script_opts .= " -nobackup"; -foreach my $pair (@go_only) { +foreach my $pair (@go_terms) { ($from, $to) = @$pair; $o = "$dir/go_${from}_$to.out"; $e = "$dir/go_${from}_$to.err";