!pwd

!head w1_Intro.ipynb

pwd

cd /Applications/BLAST/ncbi-blast-2.2.26+/

ls

cd bin

ls

!blastn -help

from IPython.display import HTML
HTML('<iframe src=https://docs.google.com/spreadsheet/pub?key=0AtV_gF766XZAdHpubXFXVmZlM0lBVnVSZURUMUdZMGc&output=html&widget=true width=100% height=750></iframe>')

!%s/ .*// Olurida_transcriptome_v3.fasta > test

#can I tunnel into genefish to run blast

cd /Volumes/Bay3/Software

#commmand that list file (-1 = one file per line) and only those that start with "ncbi"
!ls -1 ncbi*

#unzipping  [-]x --extract --get;  -v, --verbose; -z, --gzip; -f, --file F
!tar -xzvf  ncbi-blast-2.2.29+-universal-macosx.tar.gz

#commmand that list file (-1 = one file per line) and only those that start with "ncbi"
!ls -1 ncbi*

cd ncbi-blast-2.2.29+/

cd bin

ls -1

#check to see if "works"
!blastx -h

cd /Volumes/Bay3/Software/

cd ncbi-blast-2.2.29+/

cd db

ls

!gzip -d uniprot_sprot.fasta.gz

ls

pwd

#note I am working in dir db, thus can just use file names. Most times you might use the complete path.
!makeblastdb -in uniprot_sprot.fasta -dbtype prot -out uniprot_sprot_r2013_12 

#creating new directory; 
!pwd

cd ..

!mkdir query

ls

cd query/

#getting file from url to local location
!wget http://eagle.fish.washington.edu/cnidarian/Ab_4denovo_CLC6_a.fa

#lets get a preview
!head Ab_4denovo_CLC6_a.fa

#word count
!wc Ab_4denovo_CLC6_a.fa

#how many sequences? lets count ">" as we know each contig has 1
!grep -c ">" Ab_4denovo_CLC6_a.fa
#will use full paths..
!blastx -query /Volumes/Bay3/Software/ncbi-blast-2.2.29\+/query/Ab_4denovo_CLC6_a.fa -db /Volumes/Bay3/Software/ncbi-blast-2.2.29\+/db/uniprot_sprot_r2013_12 -out /Volumes/Bay3/Software/ncbi-blast-2.2.29\+/out/Ab_4denovo_CLC6_a_uniprot_blastx.tab -evalue 1E-20 -max_target_seqs 1 -outfmt 6
!head /Volumes/Bay3/Software/ncbi-blast-2.2.29\+/out/Ab_4denovo_CLC6_a_uniprot_blastx.tab

!wc /Volumes/Bay3/Software/ncbi-blast-2.2.29\+/out/Ab_4denovo_CLC6_a_uniprot_blastx.tab