def apply_procedure(Classifier):
farser = FastaParser(Classifier.data_file)
genes = farser.parse()
group_genes(Classifier, genes, 'grouped_genes.json')
plot_grouped_genes()
def main():
""" Read and extract data
"""
farser = FastaParser(sys.argv[1])
genes = farser.parse()
#handle_codon_usage(genes)
#store_low_CAA_genes(genes)
#stretch_pos_histogram(genes)
stretch_codu_histogram(genes)
def main():
""" Read and extract data
"""
farser = FastaParser(sys.argv[1])
genes = farser.parse()
exprs = extract_expression_levels('data/gene_expression.csv')
groups = group_expression_levels(genes, exprs)
generate_codon_usage_summary(groups,
'results/grouped_gene_expressions.txt')
def main():
""" Generate overview
"""
farser = FastaParser(sys.argv[1])
genes = farser.parse()
dnana = DNAAnalyzer(strict=False)
codu = dnana.get_avg_codon_usage(genes)
with open('results/plain_codon_usage_table.txt', 'w') as fd:
output_data(codu, fd)
def main():
""" Generate overview
"""
farser = FastaParser(sys.argv[1])
genes = farser.parse()
codu, label = get_codu(genes, 'strong')
rarest = get_rare_codons(codu)
pos = get_codon_positions(rarest.values(), genes)
show_codon_share(pos)
plot_positions(pos.values(), label)
def main():
""" Generate overview
"""
farser = FastaParser(sys.argv[1])
genes = farser.parse()
exprs = extract_expression_levels(sys.argv[2]) if len(
sys.argv) == 3 else None
if exprs is None:
groups = {'all': genes}
else:
groups = group_expression_levels(genes, exprs)
group_codu = get_codu_per_group(groups)
with open('results/codon_usage_table.txt', 'w') as fd:
output_data(group_codu, fd)
def main():
opt = options()
fp = FastaParser(opt.file_path)
sequence_list = fp.get_sequence_list()
print "#" * 10
print "#" * 10
ss = datetime.now()
print "Starting..."
sa = SequenceAligner(sequence_list)
results = sa.get_aligned_sequence()
print "Process complete. Results on the way...."
storage_path = make_storage_path(opt.storage_path)
results_path = write_results_to_file(
results, opt.results_name, storage_path)
elapsed = datetime.now() - ss
print "Job completed after {} min".format(elapsed.total_seconds()/60)
print "Sequence Alignment results stored --> {}".format(results_path)
print "#" * 10
print "#" * 10
import os
# Step 2: One should be able to make new instances from this class
# In fact, one should be able to make as many new objects as one wants
# Here we will just make two in this example.
# The class initialization should take one argument: the path of the fasta
# file to parse.
# Use the included fasta example files, or it won't work.
all_contigs_file_path = os.getenv(
'HOME'
) + "/Desktop/Python_Course/python_ebc_2016/day_05/exercise/all_contigs.fasta"
predicted_genes_file_path = os.getenv(
'HOME'
) + "/Desktop/Python_Course/python_ebc_2016/day_05/exercise/predicted_genes.fasta"
contigs = FastaParser(all_contigs_file_path)
genes = FastaParser(predicted_genes_file_path)
# print(genes.__getitem__())
# Step 3: What if we give a path, but there is no file there ?
# Then your class should complain ! It must throw an exception
# of type IOError. To check this, we will use a function from
# the pytest module. It's like assert but for Exceptions.
# If you don't have pytest just install it with "pip install --user pytest"
import pytest
with pytest.raises(IOError):
not_found = FastaParser('/file_does_not_exist.fasta')
# Step 4: What if we don't give a file path at all when making
# a new instance ? Then your class should complain !
# Step 1: Importing code from other files.
# Once the class exists in a file called "fasta_parser.py", it
# should be possible to import it and the following line should
# work. It just needs to be in the same directory as your current directory.
import fasta_parser
reload(fasta_parser)
from fasta_parser import FastaParser
# Step 2: One should be able to make new instances from this class
# In fact, one should be able to make as many new objects as one wants
# Here we will just make two in this example.
# The class initialization should take one argument: the path of the fasta
# file to parse.
# Use the included fasta example files, or it won't work.
contigs = FastaParser("all_contigs.fasta")
genes = FastaParser("predicted_genes.fasta")
# Step 3: What if we give a path, but there is no file there ?
# Then your class should complain ! It must throw an exception
# of type IOError. To check this, we will use a function from
# the pytest module. It's like assert but for Exceptions.
# If you don't have pytest just install it with "pip install --user pytest"
import pytest
with pytest.raises(IOError): not_found = FastaParser('/file_does_not_exist.fasta')
# Step 4: What if we don't give a file path at all when making
# a new instance ? Then your class should complain !
# It must throw an exception of type TypeError.
with pytest.raises(TypeError): missing = FastaParser()
def main():
genes1 = FastaParser(sys.argv[1]).parse()
genes2 = FastaParser(sys.argv[2]).parse()
res = intersect(genes1, genes2)
writeFastA(res)
Once the exercise is completed, this file should be uploaded to your github repository called "python_homework" in a directory called "day5".
"""
# Step 1: Importing code from other files.
# Once the class exists in a file called "fasta_parser.py", it
# should be possible to import it and the following line should
# work. It just needs to be in the same directory as your current directory.
from fasta_parser import FastaParser
# Step 2: One should be able to make new instances from this class
# In fact, one should be able to make as many new objects as one wants
# Here we will just make two in this example.
# The class initialization should take one argument: the path of the fasta
# file to parse.
# Use the included fasta example files, or it won't work.
contigs = FastaParser("all_contigs.fasta")
genes = FastaParser("predicted_genes.fasta")
# Step 3: What if we give a path, but there is no file there ?
# Then your class should complain ! It must throw an exception
# of type IOError. To check this, we will use a function from
# the pytest module. It's like assert but for Exceptions.
# If you don't have pytest just install it with "pip install --user pytest"
import pytest
with pytest.raises(IOError):
not_found = FastaParser('/file_does_not_exist.fasta')
# Step 4: What if we don't give a file path at all when making
# a new instance ? Then your class should complain !
# It must throw an exception of type TypeError.
with pytest.raises(TypeError):
def lookUp(patterns, data_file):
""" Try to match given pattern in all fasta entries specified in given file
"""
def match(record):
ret = []
seq = str(record.seq)
for pat in patterns:
match = re.search(pat, seq)
if not match: continue
ret.append((record, match))
return ret
# parse genome data
farser = FastaParser(data_file)
genes = farser.parse()
print('Matching \n > "%s"' % '"\n > "'.join(patterns))
pbar = ProgressBar(maxval=len(genes))
pbar.start()
# generate result
res = []
for i, record in enumerate(genes):
foo = match(record)
if foo: res.extend(foo)
pbar.update(i)
pbar.finish()
# sort result in natural order
def natural_keys(text):
def atoi(text):
return int(text) if text.isdigit() else text
return [atoi(c) for c in re.split('(\d+)', text)]
res = sorted(res,
key=lambda e: natural_keys(get_position(e[0].description)))
# save result
with open('results/regex_lookup.fa',
'w') as fd, open('results/regex_lookup_fragments.fa',
'w') as fd_frag:
for record, match in res:
seqs = match.groups()
name = get_gene_name(record.description)
pos = get_position(record.description)
for seq in seqs:
# save full match
rec = SeqRecord(Seq(seq, IUPAC.ambiguous_dna),
id=record.id,
name=record.name,
description=record.description + '|' +
str(match.span()))
SeqIO.write(rec, fd, 'fasta')
# save match fragments
for i, s in enumerate(get_subsequences(seq)):
rec_frag = SeqRecord(Seq(s, IUPAC.ambiguous_dna),
id=record.id,
name=record.name,
description=record.description + '|' +
str(match.span()) + '|' +
('fragment #%d' % i))
SeqIO.write(rec_frag, fd_frag, 'fasta')
def main():
farser = FastaParser('dicty_primary_cds')
genes = farser.parse()
#find_special_AAA_freqs(genes)
find_longest_A_stretch(genes)
Written by Lucas Sinclair.
Kopimi.
"""
# Step 1: Importing code from other files.
# Once the class exists in a file called "fasta_parser.py", it
# should be possible to import it and the following line should
# work:
from fasta_parser import FastaParser
# Step 2: One should be able to make new instances from this class
# In fact, one should be able to make as many new objects as one wants
# Here we will just make two in this example.
# The class initialization should take one argument: the path of the fasta
# file to parse. Two files are provided in this exercise.
contigs = FastaParser("all_contigs.fasta")
genes = FastaParser("predicted_genes.fasta")
# Step 3: What if we give a path, but there is no file there ?
# Then your class should complain ! It must throw an exception
# of type IOError. To check this we will use a function from
# the pytest module. It's like assert but for Exceptions.
# If you don't have pytest just install it.
import pytest
with pytest.raises(IOError): not_found = FastaParser('/file_does_not_exist.fasta')
# Step 4: What if we don't give a file path at all when making
# a new instance ? Then your class should complain also !
# It must throw an exception of type TypeError.
with pytest.raises(TypeError): missing = FastaParser()