def translate_6_frame(in_fasta, out_fasta):
with open(out_fasta, 'w') as outfile:
for h,s in FastaReader(in_fasta):
for frame, seq in sixFrameTranslation(s).items():
outfile.write(">"+h+" _frame_"+str(frame)+"\n")
outfile.write(seq+"\n")
return out_fasta
def pull_out_long_ORFs(bad_file, len_cutoff, outputdir):
out_file = outputdir + os.path.splitext(os.path.basename(bad_file))[0] + "_TranslongORFS.fa"
num_seqs = 0
num_orfs = 0
with open(out_file, "w") as outfile:
for h, s in FastaReader(bad_file):
num_seqs += 1
translation = sixFrameTranslation(s)
orfs = get_long_ORFS(translation, len_cutoff)
for o in orfs:
num_orfs += 1
outfile.write(">" + h + o[0] + "\n")
outfile.write(o[1] + "\n")
print str(num_seqs) + " sequences translated into " + str(num_orfs) + " ORFs"
return out_file
def pull_out_long_ORFs(bad_file, len_cutoff, outputdir):
out_file = (outputdir + os.path.splitext(os.path.basename(bad_file))[0] +
"_TranslongORFS.fa")
num_seqs = 0
num_orfs = 0
with open(out_file, 'w') as outfile:
for h, s in FastaReader(bad_file):
num_seqs += 1
translation = sixFrameTranslation(s)
orfs = get_long_ORFS(translation, len_cutoff)
for o in orfs:
num_orfs += 1
outfile.write(">" + h + o[0] + "\n")
outfile.write(o[1] + "\n")
print str(num_seqs) + " sequences translated into " + str(
num_orfs) + " ORFs"
return out_file
def split_easy_from_hard(inputfile, outputdir):
seqCount = 0
badSeqs = 0
bad_lengths = []
output_file = outputdir + os.path.splitext(os.path.basename(inputfile))[0] + "_translatedL2stops.fa"
with open(output_file + "_BadSeqs", "w") as badfile:
with open(output_file, "w") as outfile:
for h, s in FastaReader(inputfile):
stops = 9999
translation = sixFrameTranslation(s)
for frame in translation:
st = translation[frame].count("*")
if st < stops:
best = frame
stops = st
if stops <= 2:
outfile.write(">" + h + " frame_" + str(best) + "\n")
outfile.write(translation[best] + "\n")
else:
badSeqs += 1
bad_lengths.append(len(s))
badfile.write(">" + h + "\n")
badfile.write(s + "\n")
seqCount += 1
print (
str((100.0 * badSeqs) / seqCount)
+ "percent or "
+ str(badSeqs)
+ " out of "
+ str(seqCount)
+ " were not translated."
)
return output_file, output_file + "_BadSeqs"
def split_easy_from_hard(inputfile, outputdir):
seqCount = 0
badSeqs = 0
bad_lengths = []
output_file = (outputdir +
os.path.splitext(os.path.basename(inputfile))[0] +
"_translatedL2stops.fa")
with open(output_file + "_BadSeqs", 'w') as badfile:
with open(output_file, 'w') as outfile:
for h, s in FastaReader(inputfile):
stops = 9999
translation = sixFrameTranslation(s)
for frame in translation:
st = translation[frame].count('*')
if st < stops:
best = frame
stops = st
if stops <= 2:
outfile.write(">" + h + " frame_" + str(best) + "\n")
outfile.write(translation[best] + "\n")
else:
badSeqs += 1
bad_lengths.append(len(s))
badfile.write(">" + h + "\n")
badfile.write(s + "\n")
seqCount += 1
print(
str((100.0 * badSeqs) / seqCount) + "percent or " + str(badSeqs) +
" out of " + str(seqCount) + " were not translated.")
return output_file, output_file + "_BadSeqs"