#variables to set

fa="../data/fa/Ahyacinthus_v1.fasta"

db="/Applications/BLAST/ncbi-blast-2.2.29\+/db/uniprot_sprot_r2013_12"

sqls="/Users/sr320/sqlshare-pythonclient/tools/"

usr="sr320@washington.edu"

sp="Ahyacinthus"


!head -2 {fa}

!fgrep -c ">" {fa}


!/Applications/BLAST/ncbi-blast-2.2.29\+/bin/blastx \
-query {fa} \
-db {db} \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
-evalue 1E-05 \
-num_threads 3 \
-out ../analyses/{sp}_sprot.tab

!ls ../analyses/A*

!wc -l ../analyses/{sp}_sprot.tab

!tr '|' "\t" <../analyses/{sp}_sprot.tab> ../analyses/{sp}_sprot_sql.tab
!head -1 ../analyses/{sp}_sprot.tab
!echo SQLShare ready version has Pipes converted to Tabs ....
!head -1 ../analyses/{sp}_sprot_sql.tab 

!python {sqls}singleupload.py \
-d _blast_sprot \
../analyses/{sp}_sprot_sql.tab  

!python {sqls}fetchdata.py \
-s "SELECT Column1 as ContigID, term, GOSlim_bin, aspect, ProteinName \
FROM [{usr}].[_blast_sprot]md \
left join \
[samwhite@washington.edu].[UniprotProtNamesReviewed_yes20130610]sp \
on md.Column3=sp.SPID \
left join \
[sr320@washington.edu].[SPID and GO Numbers]go \
on md.Column3=go.SPID \
left join \
[sr320@washington.edu].[GO_to_GOslim]slim on go.GOID=slim.GO_id \
where aspect like 'P'" \
-f tsv \
-o ../analyses/{sp}_sprot_GOdescriptions.tab

!head ../analyses/{sp}_sprot_GOdescriptions.tab

!grep -c "stress response" ../analyses/{sp}_sprot_GOdescriptions.tab 

!grep "stress response" ../analyses/{sp}_sprot_GOdescriptions.tab \
> ../analyses/{sp}_sprot_GOdescriptions-stress.tab

!cut -f2 ../analyses/{sp}_sprot_GOdescriptions-stress.tab | sort | uniq -c


pylab inline


#FIXME - below I added '[Haliotis_kam]' 

from pandas import *

gs = read_table('../analyses/Ahyacinthus_sprot_GOdescriptions.tab')

gs

gs.groupby('GOSlim_bin').ContigID.count().plot(kind='barh', color=list('y'))
savefig('../analyses/Ahyacinthus_GOSlim.png', bbox_inches='tight')

!python {sqls}fetchdata.py \
-s "SELECT Distinct \
Column1 as ContigID, GOSlim_bin \
FROM [{usr}].[_blast_sprot]md \
left join \
[sr320@washington.edu].[SPID and GO Numbers]go \
on md.Column3=go.SPID \
left join \
[sr320@washington.edu].[GO_to_GOslim]slim on go.GOID=slim.GO_id \
where aspect like 'P'" \
-f tsv \
-o ../analyses/{sp}_GOslim.tab

!head ../analyses/{sp}_GOslim.tab

from pandas import *

slim = read_table('../analyses/Ahyacinthus_GOslim.tab')

slim.groupby('GOSlim_bin').ContigID.count().plot(kind='barh', color=list('y'))
savefig('../analyses/Ahyacinthus_GOSlim-distinct.png', bbox_inches='tight')