def concat_sequences(file1, file2, file3, file4, file5, file6, file7, file8, file9, file10):
sequences1 = AlignIO.read(file1, 'fasta')
sequences2 = AlignIO.read(file2, 'fasta')
sequences3 = AlignIO.read(file3, 'fasta')
sequences4 = AlignIO.read(file4, 'fasta')
sequences5 = AlignIO.read(file5, 'fasta')
sequences6 = AlignIO.read(file6, 'fasta')
sequences7 = AlignIO.read(file7, 'fasta')
sequences8 = AlignIO.read(file8, 'fasta')
sequences9 = AlignIO.read(file9, 'fasta')
sequences10 = AlignIO.read(file10, 'fasta')
complete_sequences = []
for sequence1 in sequences1:
strain_name = util.get_strain_name(sequence1)
sequence2 = util.get_matching_sequence(sequences2, strain_name=strain_name)
sequence3 = util.get_matching_sequence(sequences3, strain_name=strain_name)
sequence4 = util.get_matching_sequence(sequences4, strain_name=strain_name)
sequence5 = util.get_matching_sequence(sequences5, strain_name=strain_name)
sequence6 = util.get_matching_sequence(sequences6, strain_name=strain_name)
sequence7 = util.get_matching_sequence(sequences7, strain_name=strain_name)
sequence8 = util.get_matching_sequence(sequences8, strain_name=strain_name)
sequence9 = util.get_matching_sequence(sequences9, strain_name=strain_name)
sequence10 = util.get_matching_sequence(sequences10, strain_name=strain_name)
if (sequence2 and sequence3 and sequence4 and sequence5 and sequence6 and sequence7 and sequence8 and sequence9 and sequence10):
complete_sequence=[]
complete_sequence.append(util.get_strain_name(sequence1))
complete_sequence.append(sequence1.seq+sequence2.seq+sequence3.seq+sequence4.seq+sequence5.seq+sequence6.seq+sequence7.seq+sequence8.seq+sequence9.seq+sequence10.seq)
complete_sequences.append(complete_sequence)
return complete_sequences
def concat_sequences(file1, file2, file3, file4, file5, file6, file7, file8,
file9, file10):
sequences1 = AlignIO.read(file1, 'fasta')
sequences2 = AlignIO.read(file2, 'fasta')
sequences3 = AlignIO.read(file3, 'fasta')
sequences4 = AlignIO.read(file4, 'fasta')
sequences5 = AlignIO.read(file5, 'fasta')
sequences6 = AlignIO.read(file6, 'fasta')
sequences7 = AlignIO.read(file7, 'fasta')
sequences8 = AlignIO.read(file8, 'fasta')
sequences9 = AlignIO.read(file9, 'fasta')
sequences10 = AlignIO.read(file10, 'fasta')
complete_sequences = []
for sequence1 in sequences1:
strain_name = util.get_strain_name(sequence1)
sequence2 = util.get_matching_sequence(sequences2,
strain_name=strain_name)
sequence3 = util.get_matching_sequence(sequences3,
strain_name=strain_name)
sequence4 = util.get_matching_sequence(sequences4,
strain_name=strain_name)
sequence5 = util.get_matching_sequence(sequences5,
strain_name=strain_name)
sequence6 = util.get_matching_sequence(sequences6,
strain_name=strain_name)
sequence7 = util.get_matching_sequence(sequences7,
strain_name=strain_name)
sequence8 = util.get_matching_sequence(sequences8,
strain_name=strain_name)
sequence9 = util.get_matching_sequence(sequences9,
strain_name=strain_name)
sequence10 = util.get_matching_sequence(sequences10,
strain_name=strain_name)
if (sequence2 and sequence3 and sequence4 and sequence5 and sequence6
and sequence7 and sequence8 and sequence9 and sequence10):
complete_sequence = []
complete_sequence.append(util.get_strain_name(sequence1))
complete_sequence.append(sequence1.seq + sequence2.seq +
sequence3.seq + sequence4.seq +
sequence5.seq + sequence6.seq +
sequence7.seq + sequence8.seq +
sequence9.seq + sequence10.seq)
complete_sequences.append(complete_sequence)
return complete_sequences
def combine_2_fastas(file1, file2):
sequences1 = AlignIO.read(file1, 'fasta')
sequences2 = AlignIO.read(file2, 'fasta')
records = []
seq_id = 1
for sequence1 in sequences1:
strain_name = util.get_strain_name(sequence1)
sequence2 = util.get_matching_sequence(sequences2,
strain_name=strain_name)
if sequence2 is not None:
records.append(
SeqRecord(Seq(str(sequence1.seq + sequence2.seq)),
id=str(seq_id),
name='HA_NA',
description='HA_NA'))
seq_id += 1
print(len(records))
with open("ha_na.fasta", "w") as handle:
SeqIO.write(records, handle, "fasta")
handle.close()
def update_year_counts(record):
strain_name = util.get_strain_name(record)
year = strain_name.split('/')[-1]
if year in strains_by_year:
strains_by_year[year].append(strain_name)
else:
strains_by_year[year] = [strain_name]
def create_unique_sequences(fasta_file, unique_strains_file):
sequences = AlignIO.read(fasta_file, 'fasta')
strains = list(util.read_file(unique_strains_file))[0]
new_fasta_sequences = []
for sequence in sequences:
strain_name = util.get_strain_name(sequence)
if strain_name in strains:
new_fasta_sequences.append(sequence)
strains.remove(strain_name)
return new_fasta_sequences
def create_unique_sequences(fasta_file, unique_strains_file):
sequences = AlignIO.read(fasta_file, 'fasta')
strains = list(util.read_file(unique_strains_file))[0]
new_fasta_sequences = []
for sequence in sequences:
strain_name = util.get_strain_name(sequence)
if strain_name in strains:
new_fasta_sequences.append(sequence)
strains.remove(strain_name)
return new_fasta_sequences
def get_strain_names(fasta_file, k, max_year):
strain_names = []
strains_by_year = {}
for record in SeqIO.parse(fasta_file, "fasta"):
description_list = record.description.split('|')
if (len(description_list)<4):
print("protein description too short ", record.description)
continue
if 'HA' in description_list[5]:
strain_name = gau.get_strain_name(record)
year = strain_name.split('/')[-1]
if year in strains_by_year:
strains_by_year[year].append(strain_name)
else:
strains_by_year[year] = [strain_name]
# what are the counts per year?
for key, value in strains_by_year.items():
print(key, len(value))
for key, value in strains_by_year.items():
try:
year = int(key)
except Exception:
year = 0
if year < max_year:
print(key + ' is less than ' + str(max_year))
if len(value) > k:
small_list = random.sample(value, k=k)
for strain_name in small_list:
strain_names.append(strain_name)
else:
for strain_name in value:
strain_names.append(strain_name)
else:
print(key + ' is greater than ' + str(max_year))
return strain_names
def get_strain_names(fasta_file, k, max_year):
strain_names = []
strains_by_year = {}
for record in SeqIO.parse(fasta_file, "fasta"):
description_list = record.description.split('|')
if (len(description_list) < 4):
print("protein description too short ", record.description)
continue
if 'HA' in description_list[5]:
strain_name = gau.get_strain_name(record)
year = strain_name.split('/')[-1]
if year in strains_by_year:
strains_by_year[year].append(strain_name)
else:
strains_by_year[year] = [strain_name]
# what are the counts per year?
for key, value in strains_by_year.items():
print(key, len(value))
for key, value in strains_by_year.items():
try:
year = int(key)
except Exception:
year = 0
if year < max_year:
print(key + ' is less than ' + str(max_year))
if len(value) > k:
small_list = random.sample(value, k=k)
for strain_name in small_list:
strain_names.append(strain_name)
else:
for strain_name in value:
strain_names.append(strain_name)
else:
print(key + ' is greater than ' + str(max_year))
return strain_names
def custom_split():
fasta_file = sys.argv[1]
strain_names = get_strain_names(fasta_file, k=100, max_year=2020)
ha_sequences = []
na_sequences = []
np_sequences = []
m1_sequences = []
m2_sequences = []
pb1_sequences = []
pb2_sequences = []
ns1_sequences = []
ns2_sequences = []
pa_sequences = []
for record in SeqIO.parse(fasta_file, "fasta"):
description_list = record.description.split('|')
if (len(description_list) < 4):
print("protein description too short ", record.description)
continue
if 'HA' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ha_sequences.append(record)
if 'NA' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
na_sequences.append(record)
if 'NP' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
np_sequences.append(record)
if 'M1' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
m1_sequences.append(record)
if 'M2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
m2_sequences.append(record)
if 'PB1 Polymerase (basic) protein 1' in description_list[5] or 'PB1 Polymerase (basic) protein 1' in \
description_list[4]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pb1_sequences.append(record)
if 'PB2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pb2_sequences.append(record)
if 'NS1 Non-structural protein 1' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ns1_sequences.append(record)
if 'NS2 Non-structural protein 2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ns2_sequences.append(record)
if 'PA Polymerase (acidic) protein' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pa_sequences.append(record)
output_handle = open("ha.fasta", "w")
print("length of ha sequences ", len(ha_sequences))
SeqIO.write(ha_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("na.fasta", "w")
print("length of na sequences ", len(na_sequences))
SeqIO.write(na_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("m1.fasta", "w")
print("length of m1 sequences ", len(m1_sequences))
SeqIO.write(m1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("m2.fasta", "w")
print("length of m2 sequences ", len(m2_sequences))
SeqIO.write(m2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("np.fasta", "w")
print("length of np sequences ", len(np_sequences))
SeqIO.write(np_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pb1.fasta", "w")
print("length of pb1 sequences ", len(pb1_sequences))
SeqIO.write(pb1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pb2.fasta", "w")
print("length of pb2 sequences ", len(pb2_sequences))
SeqIO.write(pb2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("ns1.fasta", "w")
print("length of ns1 sequences ", len(ns1_sequences))
SeqIO.write(ns1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("ns2.fasta", "w")
print("length of ns2 sequences ", len(ns2_sequences))
SeqIO.write(ns2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pa.fasta", "w")
print("length of pa sequences ", len(pa_sequences))
SeqIO.write(pa_sequences, output_handle, "fasta")
output_handle.close()
def custom_split():
fasta_file = sys.argv[1]
strain_names = get_strain_names(fasta_file, k=100, max_year=2020)
ha_sequences = []
na_sequences = []
np_sequences = []
m1_sequences = []
m2_sequences = []
pb1_sequences = []
pb2_sequences = []
ns1_sequences = []
ns2_sequences = []
pa_sequences = []
for record in SeqIO.parse(fasta_file, "fasta"):
description_list = record.description.split('|')
if (len(description_list) < 4):
print("protein description too short ", record.description)
continue
if 'HA' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ha_sequences.append(record)
if 'NA' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
na_sequences.append(record)
if 'NP' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
np_sequences.append(record)
if 'M1' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
m1_sequences.append(record)
if 'M2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
m2_sequences.append(record)
if 'PB1 Polymerase (basic) protein 1' in description_list[5] or 'PB1 Polymerase (basic) protein 1' in \
description_list[4]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pb1_sequences.append(record)
if 'PB2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pb2_sequences.append(record)
if 'NS1 Non-structural protein 1' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ns1_sequences.append(record)
if 'NS2 Non-structural protein 2' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
ns2_sequences.append(record)
if 'PA Polymerase (acidic) protein' in description_list[5]:
strain_name = gau.get_strain_name(record)
if strain_name in strain_names:
pa_sequences.append(record)
output_handle = open("ha.fasta", "w")
print("length of ha sequences ", len(ha_sequences))
SeqIO.write(ha_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("na.fasta", "w")
print("length of na sequences ", len(na_sequences))
SeqIO.write(na_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("m1.fasta", "w")
print("length of m1 sequences ", len(m1_sequences))
SeqIO.write(m1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("m2.fasta", "w")
print("length of m2 sequences ", len(m2_sequences))
SeqIO.write(m2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("np.fasta", "w")
print("length of np sequences ", len(np_sequences))
SeqIO.write(np_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pb1.fasta", "w")
print("length of pb1 sequences ", len(pb1_sequences))
SeqIO.write(pb1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pb2.fasta", "w")
print("length of pb2 sequences ", len(pb2_sequences))
SeqIO.write(pb2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("ns1.fasta", "w")
print("length of ns1 sequences ", len(ns1_sequences))
SeqIO.write(ns1_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("ns2.fasta", "w")
print("length of ns2 sequences ", len(ns2_sequences))
SeqIO.write(ns2_sequences, output_handle, "fasta")
output_handle.close()
output_handle = open("pa.fasta", "w")
print("length of pa sequences ", len(pa_sequences))
SeqIO.write(pa_sequences, output_handle, "fasta")
output_handle.close()
