# Commands to make the MySQL tables.

# Only need to drop if the database is not new!

mysql -h webdbsrv -P 3306 -u yogyrw -pyogyex S_pombe_YOGY_1 < drop_yogy.sql
mysql -h webdbsrv -P 3306 -u yogyrw -pyogyex S_pombe_YOGY_1 < create_yogy.sql
mysql -h webdbsrv -P 3306 -u yogyrw -pyogyex S_pombe_YOGY_1 < truncate_yogy.sql

# In the following scripts, it is necessary to download certain
#   database files from the internet - the locations of these
#   files are given in the relevant script or in this script.


# Files to download in perl script.

./yogy_populate.pl


# Selected files to download from:
#   http://inparanoid.cgb.ki.se/download/current/sqltables/

set href = "http://inparanoid.cgb.ki.se/download/current/sqltables"

#foreach file (longsqltable.*)

#foreach file (`cat inp_files.txt`)

  #echo $file

  # These two lines do not work

  #set longfile = `echo "${href}/${file}"`
  #webget.pl -a "$longfile" >! $file

  #./yogy_add_inp_terms.pl $file

#end

foreach file (`cat inp_files.txt`)

  echo $file

  ./yogy_add_inp_terms.pl $file

end


# http://orthomcl.cbil.upenn.edu/ORTHOMCL_DB/all_orthomcl.out
# OLD: http://orthomcl.cbil.upenn.edu/OrthoMCL_DB_Data/all_orthomcl.out

./yogy_add_orthomcl_cluster.pl all_orthomcl.out

# http://orthomcl.cbil.upenn.edu/ORTHOMCL_DB/BAE_geneid_anno

./yogy_add_orthomcl_lookup.pl BAE_geneid_anno


# File to download in perl script.

./yogy_add_go_terms.pl

# Selected files to download from:
#   http://www.geneontology.org/GO.current.annotations.shtml

#foreach file (gene_association.*)

foreach file (`cat go_files.txt`)

  echo $file

  gunzip $file

  ./yogy_add_go_assocs.pl $file:r

  gzip $file:r

end

# Same location, renamed file, so that it doesn't get loaded
#   with the previous loop!

set file = "gene_association.goa_uniprot.gz"

gunzip $file

./yogy_add_go_assocs_uni.pl $file:r

gzip $file:r


# Files to download in perl script.
# This script may fail during running, so some of it may need to be re-run.

gunzip functional_descriptions.WS161.txt.gz
gunzip SwissProt_mappings.WS161.txt.gz

./yogy_add_new_orgs.pl

gzip functional_descriptions.WS161.txt
gzip SwissProt_mappings.WS161.txt


# Selected xrefs files to download from:
#   ftp://ftp.ebi.ac.uk/pub/databases/IPI/current/

#foreach file (ipi.[ABCHMR]*.xrefs)

foreach file (`cat ipi_files.txt`)

  echo $file

  gunzip $file

  ./yogy_add_ipi_lookup.pl $file:r

  gzip $file:r

end


# ftp://ftp.ncbi.nlm.nih.gov/gene/DATA/gene2accession.gz

set file = "gene2accession.gz"

gunzip $file

./yogy_add_gi_lookup.pl $file:r

gzip $file:r

# CURRENT LOCATION

# ftp://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.dat.gz

cd uni_parse

set file = "uniprot_sprot"

gunzip ${file}.dat.gz

./uni_parse.pl ${file}.dat >! ${file}.txt

gzip ${file}.dat

../yogy_add_uniprot_lookup.pl ${file}.txt

gzip ${file}.txt

cd ..


# ftp://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.dat.gz

cd uni_parse

set file = "uniprot_trembl"

gunzip ${file}.dat.gz

./uni_parse.pl ${file}.dat >! ${file}.txt

gzip ${file}.dat

../yogy_add_uniprot_lookup.pl ${file}.txt

gzip ${file}.txt

cd ..


# Takes a couple of days to run this script!
# It speeeds up the on-the-fly searching for UniProt IDs from GI numbers.

./yogy_find_uniprot_ids.pl