def generate_files4blast_xen(dict_in, fasta_in, path_for_files):
"""
Inputs:
dict_in - the dictionary where the keys are the xenopus reference names that have phosphrylated residue
fasta_in - the fasta file that has the xenopus reference information
path_for_files
Outputs:
Nothing is returned
"""
# read the fasta file into a dictionary
fasta_dict = {}
with open(fasta_in) as fasta_file:
parser = fastaparser.Reader(fasta_file)
for seq in parser:
# seq is a FastaSequence object
fasta_dict[seq.id] = seq.sequence_as_string()
for key in dict_in.keys():
if key in fasta_dict.keys():
# generate the file
#file_name_1 = row[col_ref] + ".fa"
file_name = pathlib.Path(path_for_files, key + ".fa")
# use fastaparser to write the single entry
with open(file_name, 'w') as fasta_file:
writer = fastaparser.Writer(fasta_file)
writer.writefasta((key,fasta_dict[key]))
def read_fasta_file(self, fasta_file):
with open(fasta_file) as fasta_file:
parser = fastaparser.Reader(fasta_file)
for seq in parser:
sequence = seq.sequence_as_string()
return sequence
def open_genome_file():
dna_string = ""
with open(genome_directory + genome_file_name) as fasta_file:
parser = fastaparser.Reader(fasta_file)
for seq in parser:
dna_string += seq.sequence_as_string()
return dna_string
def test_design_crispr_grnas(
self,
discover_client: DISCOVERClient,
):
# Fasta file
seq_filepath = get_project_root(
) / 'teselagen/examples/pytested/dummy_organism.fasta'
# Load file
with open(seq_filepath) as fasta_file:
parser = fastaparser.Reader(fasta_file)
for seq in parser:
fasta_seq: str = cast(FastaSequence, seq).sequence_as_string()
break
# Call method to be tested
res = discover_client.design_crispr_grnas(
sequence=fasta_seq,
target_indexes=(500, 600),
)
assert isinstance(res, dict)
assert 'guides' in res
assert 'target_indexes' in res
assert len(res['guides']) == 7
def generate_sequences(path, chr_=''):
import fastaparser
if chr_ != '':
with open("data/genomes/hg19_hard_50.fa") as fasta_file:
parser = fastaparser.Reader(fasta_file, parse_method='quick')
for seq in parser:
if seq.header == chr_:
print(seq.header)
main_funct(path, seq.sequence)
else:
main_funct(path)
def fasta_for(path_to_zipfile):
'''
Return fasta parser for RefSeq CDS.
path_to_zipfile: The relative path to the zipfile containing the virus data report
'''
fasta = {}
with zipfile.ZipFile(path_to_zipfile, 'r') as zip:
with io.TextIOWrapper(zip.open('ncbi_dataset/data/cds.fna')) as fh:
for seq in fastaparser.Reader(fh):
fasta[seq.id] = seq.sequence_as_string()
return fasta
def fasta_to_json(fasta_path: Path) -> None:
benchmark_dct = {}
with fasta_path.open() as fasta_file:
parser = fastaparser.Reader(fasta_file, parse_method="quick")
for sequence in parser:
protein_id = sequence.header.split("|")[1]
sequence_str = sequence.sequence
benchmark_dct[protein_id] = sequence_str
benchmark_dct = {"inputs": benchmark_dct}
with BENCHMARK_FILEPATH.open("w") as fp:
json.dump(benchmark_dct, fp)
def fasta_parser(path):
fasta_df = pd.DataFrame()
print("Done")
with gzip.open(path, 'rt') as fasta_file:
reader = fastaparser.Reader(fasta_file)
print("File loaded")
fasta_df['ID'] = [seq.id for seq in reader]
print("Column 1 of 3 added")
fasta_df['Description'] = [seq.description for seq in reader]
print("Column 2 of 3 added")
fasta_df['Sequence'] = [seq.sequence_as_string() for seq in reader]
print("Column 3 of 3 added")
return fasta_df
def filter_fasta(fasta_in, rem_str, fasta_out):
"""
INPUTS:
fasta_in - name with path from current folder for the input fasta file
rem_str - the regular expression string to find what we want to remove from sequence ids
fasta_out - name with path from curret folder for the output fasta file
OUTPUTS:
fasta_dict - the dictionary of non-isofrm fasta sequences to use to defined
the human motif
** fasta_out is written
"""
# create the dictionary for the non-isoform references in the input
# human references that we are going to store
fasta_dict = {}
# read in the sequences from the fasta file with fastaparser
with open(fasta_in) as fasta_file:
parser = fastaparser.Reader(fasta_file)
# seq is a FastaSequence object
for seq in parser:
# check to see if the sequence id includes "iso"
# if it does then don't add it to the fasta_dict
if(re.search(rem_str,seq.id)):
pass
# if it doesn't have iso then do add it to eh dictionary
else:
fasta_dict[seq.id] = seq.sequence_as_string()
# now right the fasta sequences stored in the dictionary to a text file
with open(fasta_out, 'w') as fasta_file:
writer = fastaparser.Writer(fasta_file)
for seq_id in fasta_dict.keys():
writer.writefasta((seq_id, fasta_dict[seq_id]))
# return the dictionary of non-isoform fast sequences so that the human
# motifs can be found
return fasta_dict
def winnow_fasta(fasta_fp, base_empress_df, out_stringent_fp):
with open(out_stringent_fp, 'w') as stringent_file:
with open(fasta_fp) as fasta_file:
parser = fastaparser.Reader(fasta_file)
for seq in parser:
# match header to consensus_seq_name column of metadata
# and get the usable_for value for it
seq_metadata_df = base_empress_df.loc[
base_empress_df[CONS_NAME] == seq.id]
if len(seq_metadata_df) == 0:
continue
elif len(seq_metadata_df) > 1:
raise ValueError(f"More than one metadata row with"
f"consensus sequence name "
f"'{seq.id}' found")
else:
seq_stringent_test_val = \
seq_metadata_df.loc[:, STRINGENT_TEST_COL].iat[0]
fasta_str = seq.formatted_fasta() + '\n'
if seq_stringent_test_val == STRINGENT_INCLUDE_VAL:
stringent_file.write(fasta_str)
#!/usr/bin/env python3
#https://github.com/mor16fsu/bch5884
#Mitchell Roth
from DNALib import *
import fastaparser
from matplotlib import pyplot as plt
print("")
print("The DNA input sequence is:")
#Parse FASTA file
with open("mEGFP2.fa") as fasta_file:
parser = fastaparser.Reader(fasta_file, parse_method='quick')
for seq in parser:
print(seq.sequence)
print()
print("")
print("If error in sequence print False, if no errors print None")
print(checkseq(seq.sequence))
print("")
print("The frequency of each nucleotide is:")
print(countnuc(seq.sequence))
print("")
print("The transcript of the sequence is:")
print(transcribe(seq.sequence))
def memGraph(seqeunce, N):
memFuncArray = memFunction(seqeunce, N)
x = []
for i in range(1, N + 1):
x.append(i)
plt.plot(x, memFuncArray)
plt.xlabel("r")
plt.ylabel("F")
plt.show()
root = tk.Tk()
root.withdraw()
filepath = filedialog.askopenfilename()
with open(filepath) as fasta_file:
reader = fp.Reader(fasta_file)
for seq in reader:
#print ('ID: ', seq.id)
#print ('Description:', seq.description)
#print ('Sequence: ', seq.sequence_as_string())
sequence = seq.sequence_as_string()
#print (len(sequence))
#corGraph("A", "G", 20, seq.sequence_as_string())
#dispGraph(len(sequence), subsum(sequenceToBinary("A", "G", "", sequence)))
corGraph("1", "1", 40, sequenceToBinary("A", "G", "", sequence))
#memGraph(sequenceToBinary("A", "G", "", sequence), 60)
print("\n")
fasta_file.close()
import fastaparser
import sys
seq_dict={}
with open(sys.argv[1]) as fasta_file:
parser=fastaparser.Reader(fasta_file)
for seq in parser:
seq_dict[seq.id]=seq.sequence_as_string()
pairs=[]
for s in seq_dict.keys():
suffix=seq_dict[s][-3:]
for k in seq_dict.keys():
if s==k:
continue
prefix=seq_dict[k][:3]
if suffix==prefix:
pairs.append([s,k])
for pair in pairs:
print(pair[0]+" "+pair[1])
