def read_rep():
dn = 'rep.dict.pkl'
if cmn.filexist(dn):
print('loading repeats using precomputed data...')
return cmn.pickle_read(dn)
freps = cmn.cmd2lines('ls annotation_repeats/*.gff3')
repdict = {}
for frep in freps:
for line in cmn.file2lines(fn):
items = line.strip().split()
scaf = items[0]
if scaf not in repdict:
repdict[scaf] = set([])
i, j = list(map(int, items[3:5]))
repdict[scaf] = repdict[scaf] | set(range(i, j))
cmn.pickle_write(repdict, dn)
return repdict
return [char1, char1]
else:
char1, char2 = flist[-2:]
print(count_dict, char1, char2, count_dict, cutoff, 'twochars')
return [char1, char2]
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
try:
fblast, fread = sys.argv[1:3]
except:
print('*.py blastExon.dict.pkl readSp.dict.pkl', file=sys.stderr)
sys.exit()
blast_dict = cmn.pickle_read(fblast)
#reads[sp][name] = seq
read_dict = cmn.pickle_read(fread)
splist = set(read_dict.keys())
#read in ranges for exons
#{'COX1': readID: {2:(1,2,3)}}
#TODO: fill in missing
stack_dict = {}
exon_lengths = {}
for exon in blast_dict:
info = blast_dict[exon]
stack_dict[exon] = {}
sys.exit()
cwd = os.getcwd()
#subsetIDs = set(cmn.getid(fsubset))
subsetJobs = set([
cmn.lastName(line.replace('sbatch', '').strip())[4:-4]
for line in cmn.file2lines(fsubset)
])
#1. read in info
fsams = cmn.cmd2lines('ls %s/*/*/*.sam' % mapdir)
#print fsams
samdirs = set(['/'.join(fsam.split('/')[:-2]) for fsam in fsams])
#print samdirs
require_refs = cmn.pickle_read(freq)
fq_dict = {}
refdict = {}
#1. tell by reftable
#make the requirement by the reftable
for line in cmn.file2lines(freftable):
items = line.strip().split()
sp = items[0]
fastqs = items[1].split(',')
fq_dict[sp] = fastqs
# check for reference
#2. tell by best mapping
for samdir in samdirs:
sp = cmn.lastName(samdir)
sys.path.append(python_lib)
import cmn
import ete3
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
fname = sys.argv[2]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
nameDict = cmn.pickle_read(fname)
t = ete3.Tree(fn)
for node in t:
name = node.name
node.name = nameDict[name]
dn = cmn.lastName(fn) + '.mapnamed'
cmn.write_file(t.write(), dn)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py 1708_mapped.pileup", file=sys.stderr)
sys.exit()
new = []
try:
coding = cmn.pickle_read('coding.indexes.pkl')
except:
print('do not find index file for coding region')
print('would not label coding positions')
coding = set([])
with open(fn) as fp:
for line in fp:
try:
scaffold, index, ref_base, count, read_stack, qual_stack = line.strip(
).split()
except:
#coverage is 0
items = line.strip().split()
index, ref_base, count = items[1:4]
print(index, ref_base, count, '0 lowCoverage(0)')
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fns = sys.argv[1:]
except:
print("Usage: *.py read_filelist", file=sys.stderr)
sys.exit()
#read in data
fdict = 'blastBySp.dict.pkl'
sp_dict = cmn.pickle_read(fdict)
#get the read ID, and the exon of it
good_IDs = {}
for sp in sp_dict:
lines = sp_dict[sp]
for line in lines:
readID = line.split()[2]
print('readID', readID)
good_IDs[readID] = sp
#get the reads and split them into exons
#fns = cmn.getid(fn)
rdict = {}
for fn in fns:
