Skip to content

Modified namedb.py and annotate-seqs.py to work with files supplied via ... #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RamRS wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Modified namedb.py and annotate-seqs.py to work with files supplied via ... #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b82fd5b
Modified namedb.py and annotate-seqs.py to work with files supplied v…
RamRS Aug 23, 2013
cdb8675
Modified annotate-seqs, make-namedb and namedb to work on custom seq
RamRS Aug 25, 2013
eb177a4
Pickling no longer uses dict. var seqFile stores seq file name
RamRS Aug 26, 2013
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,3 +12,4 @@ mouse.protein.faa.psq
petMar_lamp0.fasta
petMar_lamp3.fasta
petMar_mrna.lamp3.orig.fasta.gz
/.project
8 changes: 4 additions & 4 deletions annotate-seqs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ def main():

o = ortho.get(name)
if o:
annot = namedb.mouse_names.get(transform_name(o, args.ncbi))
annot = namedb.data_names.get(transform_name(o, args.ncbi))
tr_dict[tr] = ('ortho', annot)
else:
if tr in tr_dict and tr_dict[tr][0] == 'ortho':
Expand All @@ -52,7 +52,7 @@ def main():

h, score = h[0]
score = round(float(score) / float(len(record.sequence)) * 100)
annot = namedb.mouse_names[transform_name(h, args.ncbi)]
annot = namedb.data_names[transform_name(h, args.ncbi)]

if score > oldscore:
tr_dict[tr] = (oldscore, annot)
Expand All @@ -76,7 +76,7 @@ def main():

o = ortho.get(name)
if o:
annot = namedb.mouse_names.get(transform_name(o, args.ncbi))
annot = namedb.data_names.get(transform_name(o, args.ncbi))
annot = "ortho:" + annot
annot_ortho_count += 1
else:
Expand All @@ -85,7 +85,7 @@ def main():
if h:
h, score = h[0]
score = round(float(score) / float(len(record.sequence)) * 100)
annot = namedb.mouse_names[transform_name(h, args.ncbi)]
annot = namedb.data_names[transform_name(h, args.ncbi)]
annot = "h=%d%% => " % score + annot
annot += " "
annot_homol_count += 1
Expand Down
13 changes: 8 additions & 5 deletions make-namedb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,13 @@
import screed
import sys

outfile = sys.argv[2]
# the name-db
outfile = "names.db"
seqFile = sys.argv[1]

d = {}
e = {}
for record in screed.open(sys.argv[1]):
for record in screed.open(seqFile):
if record.name.startswith('gi|'):
ident = record.name.split('|')[3]
else:
Expand All @@ -17,7 +19,8 @@
e[ident] = record.name

fp = open(outfile, 'w')
dump(d, fp)
dump(seqFile, fp)
dump(d,fp)

fp = open(outfile + '.fullname', 'w')
dump(e, fp)
fp = open('fullnames.db', 'w')
dump(e, fp)
6 changes: 3 additions & 3 deletions namedb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import cPickle
import screed

mouse_names = cPickle.load(open('mouse.namedb'))
mouse_fullname = cPickle.load(open('mouse.namedb.fullname'))
mouse_seqs = screed.ScreedDB('mouse.protein.faa')
data_names = cPickle.load('names.db')
data_fullname = cPickle.load(open('fullnames.db'))
data_seqs = screed.ScreedDB(cPickle.load('names.db'))