gtar -Ozxf $soc/dmicsatdpsec.blout.tgz | ../blast92gff.pl -in=stdin -gff -out=dros-dpse-micsat3.gff -nodebug -evalmin=1e-6
perl -pi -e's,blastn:\w+,blastn:drosmicsat,;' dros-dpse-micsat3.gff 

set dspp=(dana dere dgri dmel dmoj dpse dsim dvir dyak)
foreach ds ($dspp)
gtar -Ozxf $soc/dmicsat${ds}c.blout.tgz | \
../blast92gff.pl -in=stdin -gff -out=stdout -nodebug -evalmin=1e-10 | \
perl -pe's,blastn:\w+,blastn:drosmicsat,;' > dros-${ds}-micsat2.gff
end

$gbl/bin/lucegene_bulk_load_gff.pl -database dana_ag0508 \
  -append work/dros-dana-micsat.gff

#!/bin/csh

set gbl=/bio/argos/common/perl/gbrowselive

#dana done
set dspp=( dere dgri dmoj dvir )
foreach ds ($dspp)
$gbl/bin/lucegene_bulk_load_gff.pl -database ${ds}_ag0508 \
  -append dros-${ds}-micsat.gff
end  

# dsim_dgpg040929 dyak_wu040407 dpse-r1.04 dmel_r4.1
$gbl/bin/lucegene_bulk_load_gff.pl -database dmel_r4.1 \
  -append dros-dmel-micsat.gff

$gbl/bin/lucegene_bulk_load_gff.pl -database dpse-r1.04 \
  -append dros-dpse-micsat.gff

$gbl/bin/lucegene_bulk_load_gff.pl -database dyak_wu040407 \
  -append dros-dyak-micsat.gff

$gbl/bin/lucegene_bulk_load_gff.pl -database dsim_dgpg040929 \
  -append dros-dsim-micsat.gff


gbrowse.conf:::::::::::::

default features = tblastDM tblastSC tblastAG tblastCE blastndmel 
  blastdmic:overview blastdmic

[blastdmic:overview]
feature       =  match:blastn:drosmicsat
label         = 0
glyph         = generic
bgcolor       = lavender
height        = 5
key           = Microsatellites
bump  = 0
bump density  = 5

[blastdmic]
feature  = nucleotide_match:blastn:drosmicsat
glyph    = segments
stranded     = 1
bgcolor  = lavender
fgcolor  = black
key      = Dros. microsatellites
citation = Dros. microsatellites
category = Analysis
label = sub { my $f = shift;
  my @na= ($f->attributes('Name'), $f->attributes('Alias'), $f->attributes('symbol'));
  return $na[0] || $f->display_name;
  }
link = sub {
  my($ac) = shift->attributes('ID'); $ac =~ s/[\.\|].*$//;
  return 'http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Search&db=Nucleotide&doptcmdl=GenBank&tool=GMOD&term='.$ac if ($ac);
  }

..................
# marker genes = dmel named genes, located on all dspp, 
# "best" in each 500kb section of each chr

## missing dpse-dmelgn.ids/dpse-prot9 data !
set dspp=(dana dere dgri  dmoj  dsim dvir dyak)
foreach ds ($dspp)
echo ---- $ds dmelgn.ids ------
gzgrep modDM $ds/gff/$ds-prot9.gff.gz | grep -v match_part |\
 perl -ne'($id)=m/ID=(\w+)/;print "$id\n";' | sort | uniq > work/$ds-dmelgn.ids
end

13074   13074   98322 dana-dmelgn.ids
13328   13328  100322 dere-dmelgn.ids
12585   12585   94492 dgri-dmelgn.ids
12675   12675   95188 dmoj-dmelgn.ids
13246   13246   99679 dsim-dmelgn.ids
11902   11902   89405 dvir-dmelgn.ids
13043   13043   98188 dyak-dmelgn.ids

cat *dmelgn.ids | sort | uniq -c | grep ' 7 ' | perl -pe's/\s+7\s+//;' > dmelgn-all.ids
cat *all.ids | perl -pe's/(\w+)/ID=$1;/;' > allids.patt
split allids.patt allidpatt.

melon.% foreach idp (allidpatt.*)
foreach? fgrep -f $idp dmel-named-genes.gff >> dmel-best-genes.gff
foreach? end

melon.% wc *gff
    3872   34848  967106 dmel-best-genes.gff
    4808   43272 1206928 dmel-named-genes.gff

cat dmel-best-genes.gff | perl -ne\
'BEGIN{open(F,"bestrefs.tsv");while(<F>){chomp;($gn,$r)=split"\t";$rn{$gn}=$r;}}\
($c,$s,$t,$b,$e,@x)=split"\t";$sg=500000*int($b/500000);\
($nm)=m/Name=(\w+)/; $w=length($_); $w=int($w/2) if($nm=~/[^a-z]/);\
($gn)=m/(FBgn\d+)/;$nr=$rn{$gn}; $w += 10*$nr;\
print "$sg\t$w\t",$_;' |\
sort -k3,3 -k1,1n -k2,2rn | \
perl -ne'($s,$w,$c,@x)=split"\t";print join("\t",$c,@x) unless(0 < $gn{$c.$s}++);' \
> dmel-best-gene3.gff

cat dmel-best-gene3.gff | perl -ne'($id)=m/ID=(\w+)/;($nm)=m/Name=([^;]+)/;print"$id\t$nm\n";' > dmel-best-gene3.ids
.....
set ds=dana

set dspp=(dana dere dgri  dmoj  dsim dvir dyak)
foreach ds ($dspp)
gzgrep modDM $spd/$ds/gff/$ds-prot9.gff.gz | grep -v match_part |\
 perl -ne'BEGIN{open(F,"dmel-best-gene3.ids");%best=map{chomp;($d,$n)=split;$d,$n;} <F>;}\
 ($id)=m/ID=(\w+)/;if($best{$id}){ s/tblastn:modDM/marker:modDM/; \
 s/ID=[^;]+;/Name=$best{$id};/; s/;loc=[^;\n]+//; print;}' \
 > $spd/$ds/gff/$ds-markers.gff
end

-------------------------------
sort -k3,3 -k1,1n -k2,2rn |more

#$w=int($w/0.9) if(/GB_protein/);

2L      .       gene    3771706 3784129 .       +       .       ID=CG10021;Name=bowl;Dbxref=FlyBase
:FBan0010021,FlyBase:FBgn0004893;cyto_range=24C3-24C4;dbxref_2nd=FlyBase:FBgn0014041,FlyBase:FBgn00
22034,GB:CG10021;gbunit=AE003578;synonym=bowl;synonym_2nd=17-29-5,Bowl,Su(tor)2-1,bowel,l(2)c,l(2)k
08617,org2


... use ugpxml summary size for weight of marker genes?

500000  377     2L      .       gene    541235  542572  .       -       .       ID=CG3018;Name=lwr; <<
Dbxref=FlyBase:FBan0003018,FlyBase:FBgn0010602;cyto_range=21D1-21D1;dbxref_2nd=FlyBase:CG3018,FlyBa
se:FBgn0010523,FlyBase:FBgn0015755,FlyBase:FBgn0022761;gbunit=AE003589;synonym=lwr;synonym_2nd=DUbc
9,DmUbc9,Dmubc9,FBgn0010602,Lwr,UBC9,Ubc9,dUBC9,dUbc9,dip4,hbl,i105,i56,l(2)01519,l(2)02858,l(2)054
86,l(2)05487,semi,ubc9,unnamed
500000  302     2L      .       gene    624644  625453  .       +       .       ID=CG2826;Name=lect
in-21Ca;Dbxref=FlyBase:FBan0002826,FlyBase:FBgn0040107,GB_protein:AAF51470.1;cyto_range=21D1-21D1;d
bxref_2nd=FlyBase:FBgn0031272,Gadfly:CG2826;gbunit=AE003588;synonym=lectin-21Ca;synonym_2nd=AC+0045
73A,AC004573a,Lectin21Ca
500000  265     2L      .       gene    868675  869911  .       -       .       ID=CG4258;Name=dbe;
Dbxref=FlyBase:FBan0004258,FlyBase:FBgn0020305;cyto_range=21D4-21D4;dbxref_2nd=FlyBase:CG4258,FlyBa
se:FBgn0022118,FlyBase:FBgn0022171,FlyBase:FBgn0024894;gbunit=AE003588;synonym=dbe;synonym_2nd=l(2)
k05428,l(2)k06708
500000  237     2L      .       gene    620433  621540  .       -       .       ID=CG13686;Name=lec
tin-21Cb;Dbxref=FlyBase:FBan0013686,FlyBase:FBgn0040106;cyto_range=21D1-21D1;dbxref_2nd=FlyBase:FBg
n0031271;gbunit=AE003588;synonym=lectin-21Cb;synonym_2nd=AC+004573B,AC004573b,Lectin21Cb
500000  235     2L      .       gene    825964  833245  .       +       .       ID=CG3727;Name=dock <<
;Dbxref=FlyBase:FBan0003727,FlyBase:FBgn0010583;cyto_range=21D3-21D3;dbxref_2nd=FlyBase:CG3727,FlyB
ase:FBgn0041141;gbunit=AE003588;synonym=dock;synonym_2nd=Dm0447,Dock,dck,doc,l(2)04723
500000  211     2L      .       gene    523467  540541  .       +       .       ID=CG2762;Name=ush;
Dbxref=FlyBase:FBan0002762,FlyBase:FBgn0003963;cyto_range=21D1-21D1;dbxref_2nd=FlyBase:CG2762;gbuni
t=AE003589;synonym=ush;synonym_2nd=FOG,Ush,l(2)19,u-sh,ushaped
500000  196     2L      .       gene    861849  868352  .       -       .       ID=CG4276;Name=aru;
Dbxref=FlyBase:FBan0004276,FlyBase:FBgn0029095;cyto_range=21D4-21D4;dbxref_2nd=FlyBase:FBgn0031290;
gbunit=AE003588;synonym=aru;synonym_2nd=arouser
500000  182     2L      .       gene    640021  714968  .       -       .       ID=CG17941;Name=ds;
Dbxref=FlyBase:FBan0017941,FlyBase:FBgn0000497;cyto_range=21D1-21D2;gbunit=AE003588;synonym=ds;syno
nym_2nd=CT39575,Ds,cad2,l(2)05142
500000  177     2L      .       gene    833584  851061  .       -       .       ID=CG3365;Name=dron <<
go;Dbxref=FlyBase:FBan0003365,FlyBase:FBgn0020304;cyto_range=21D3-21D4;dbxref_2nd=FlyBase:CG3365;gb
unit=AE003588;synonym=drongo
500000  177     2L      .       gene    852767  854539  .       +       .       ID=CG3943;Name=krak
en;Dbxref=FlyBase:FBan0003943,FlyBase:FBgn0020545;cyto_range=21D4-21D4;dbxref_2nd=FlyBase:CG3943;gb
unit=AE003588;synonym=kraken
500000  155     2L      .       gene    583540  594687  .       -       .       ID=CG2851;Name=Gsc;

cp /dev/null bestgeneinfo.tsv
split -l 100 dmel-best-genes.fbid dmbestids.
foreach idf (dmbestids.*)
set idl=`cat $idf | perl -ne'/(\w+)/;print "$1+";'`
curl  -L -bck -cck \
'http://chipmunk.bio.indiana.edu:7082/lucegene/search?lib=fbgn&method=fetch&items=1-9999&headlinefields=1&format=text/tsv&q=docid:('$idl')'\
>> bestgeneinfo.tsv
end

#GSYM    NAM     CLOC    ALESR   REF     DBA     DT      iscore  docid   
grep -v '^GSYM' bestgeneinfo.tsv | perl -ne'($g,$n,$c,$a,$r,$d,$t,$s,$id)=split"\t";print "$id\t$r\n" if($id=~/FBgn/);'

http://chipmunk.bio.indiana.edu:7082/lucegene/search?q=fbgn-PHM:eye%20AND%20ENZ:kinase

curl  -L -bck -cck -i \
'http://chipmunk.bio.indiana.edu:7082/lucegene/search?lib=fbgn&q=docid:(FBgn0010602+FBgn0020304+FBgn0010583)&method=fetch&items=1-9999&headlinefields=1&format=text/tsv'\

HTTP/1.1 200 OK
Date: Sat, 20 Aug 2005 20:31:57 GMT
Server: Apache Coyote/1.0
Expires: Sun, 21 Aug 2005 20:31:57 GMT
Content-Type: text/plain
Content-Length: 234
X-Cache: MISS from chipmunk.bio.indiana.edu
Connection: close

GSYM    NAM     CLOC    ALESR   REF     DBA     DT      iscore  docid
dock    dreadlocks      21E2    26      77      23      24 Dec 04       0.99999994      FBgn0010583
drongo  drongo  21E2    2       16      18      24 Dec 04       0.99999994      FBgn0020304
lwr     lesswright      21E2    16      53      44      24 Dec 04       0.99999994      FBgn0010602

// curl -L -bck -cck -i 'http://microbe.bio.indiana.edu:8080/lucegene/search?\
// lib=uniprot&q=all:signal&method=batchfetch&items=1-10&headlinefields=1&format=text/tsv'

$b/flybase/bin/lucegene-search.sh -lib fbgn -c 'format table;fields title' \
 -c 'find docid:(FBgn0010602 FBgn0020304 FBgn0010583)' |\
perl -ne'($id)=/ID \d (\w+)/;($nr)=/REF (\d+)/;print "$id\t$nr\n";'