#-----------
# PASA daphj: all dpulex ESTs, dmagna ESTs (13k) + dpulex JGI V11 gene set
# 08nov01

gzcat daphnia-EST-jgi.fa.gz daphnia-EST-HCGS-200608.fa.gz \
  daphnia_ESTnomagna.fa.gz dmagna_est0811.fa.gz \
  > daphnia_EST_0811.fa
#............................

set rname=pasa_daphj
set dest1=daphnia_EST_0811.fa
set dgenome=dpulex_jgi060905.repeatmasked.fa
set dgenes=dpulex_jgi060905_JGI_V11.gff
#............................

touch log.$rname

echo "# Transcript alignments followed by alignment assembly"  \
>> log.$rname

../scripts/Launch_PASA_pipeline.pl -c alignAssembly.config \
-C -R --USE_GMAP \
-g $dgenome -t $dest1 \
>> & log.$rname


## optional
echo "# Importing the latest annotations into the PASA database"  \
>> log.$rname
../scripts/Load_Current_Gene_Annotations.dbi -c alignAssembly.config \
-g $dgenome  -P $dgenes \
>> & log.$rname

## optional
echo "# Performing an annotation comparison"  \
>> log.$rname
../scripts/Launch_PASA_pipeline.pl -c annotCompare.config \
-A -g $dgenome  -t $dest1 \
>> & log.$rname

perl -pi -e's/ID=chain/Parent=chain/;' $rname.pasa_assemblies.gff3

echo "# Updating our gene structure annotations"  \
>> log.$rname

../scripts/cDNA_annotation_updater.dbi \
-M "${rname}:localhost-port=3306-mysql_socket=/tmp/fbmysql.sock:myuser:xxxxxx" -P null \
>> & log.$rname

#.... output training genes

$pa/scripts/pasa_asmbls_to_training_set.dbi \
-g $dgenome \
-M "${rname}:localhost-port=3306-mysql_socket=/tmp/fbmysql.sock" \
-p "myuser:xxxxxx"   \
  > log.train.$rname

#.....

echo "## Identification and Classification of All Alternative Splicing Variations" \
>> log.$rname

../scripts/Launch_PASA_pipeline.pl -c alignAssembly.config \
-g $dgenome -t $dest1  --ALT_SPLICE \
>> & log.$rname

#... if wanted; same as -A gff ...
echo "# dump current annots to gff" \
>> log.$rname

## this regurgitates the -A compare .gff output
../scripts/dump_valid_annot_updates.dbi \
-M "${rname}:localhost-port=3306-mysql_socket=/tmp/fbmysql.sock" \
-p "myuser:xxxxxx"   \
>> & log.$rname


#-------- training set for augustus : genbank fmt -----

gzcat pasa_out/trainingSetCandidates.gff.gz | perl -pe 's/ID=TU.asm/ID=Model.asm/; s/alignAssembly-//
; s/Name=Training gene;//;' > dmel_pasatrain_genes.gff
 $bg/blast/cdsgff2genbank.pl -t='CDS,exon,gene' -a=genbank -pasa \
?  -gff=dmel_pasatrain_genes.gff -fasta=$dgenome > dmel_pasatrain_genes.gb

# filter out dupl. genes, complete only