def connect_all(matrix, need_log=False):
"""
introduction: Integrate index and data from the two-dimensional matrix.
:param matrix: Data from input.
Type: Two-dimensional list(int).
:param need_log:
:return new_matrix: Data for output.
Type: Two-dimensional list(int).
"""
m = monitor.Monitor()
index_binary_length = int(len(str(bin(len(matrix)))) - 2)
if need_log:
log.output(log.NORMAL, str(__name__),
str(sys._getframe().f_code.co_name),
"Add index in the binary matrix.")
new_matrix = []
for row in range(len(matrix)):
if need_log:
m.output(row, len(matrix))
new_matrix.append(connect(row, matrix[row], index_binary_length))
m.restore()
del matrix, m
return new_matrix
def divide_all(matrix, need_log=False):
"""
introduction: Separate data from indexes in binary strings.
:param matrix: The DNA sequence of len(matrix) rows.
Type: Two-dimensional list(int).
:param need_log: need output log.
:returns index, datas: Obtained data sets and index sets in corresponding locations.
Type: One-dimensional list(int), Two-dimensional list(int).
"""
m = monitor.Monitor()
index_binary_length = int(len(str(bin(len(matrix)))) - 2)
if need_log:
log.output(log.NORMAL, str(__name__),
str(sys._getframe().f_code.co_name),
"Divide index and data from binary matrix.")
indexs = []
datas = []
for row in range(len(matrix)):
if need_log:
m.output(row, len(matrix))
index, data = divide(matrix[row], index_binary_length)
indexs.append(index)
datas.append(data)
m.restore()
del matrix, m
return indexs, datas
def write_dna_file(path, dna_sequences, need_log=False):
"""
introduction: Writing DNA sequence set to documents.
:param path: File path.
Type: string
:param dna_sequences: Generated DNA sequences.
Type: one-dimensional list(string)
:param need_log: choose to output log file or not.
"""
m = monitor.Monitor()
try:
with open(path, "w") as file:
if need_log:
log.output(log.NORMAL, str(__name__), str(sys._getframe().f_code.co_name),
"Write DNA sequences to file: " + path)
for row in range(len(dna_sequences)):
if need_log:
m.output(row, len(dna_sequences))
file.write("".join(dna_sequences[row]) + "\n")
return dna_sequences
except IOError:
log.output(log.ERROR, str(__name__), str(sys._getframe().f_code.co_name),
"The file selection operation was not performed correctly. Please execute the operation again!")
def sort_order(indexes, data_set, need_log=False):
"""
introduction: Restore data in order of index.
:param indexes: The indexes of data set.
:param data_set: The disordered data set, the locations of this are corresponding to parameter "index".
:param need_log: need output log.
:returns matrix: Binary list in correct order.
Type: Two-dimensional list(int).
"""
m = monitor.Monitor()
if need_log:
log.output(log.NORMAL, str(__name__),
str(sys._getframe().f_code.co_name),
"Restore data order according to index.")
# noinspection PyUnusedLocal
matrix = [[0 for col in range(len(data_set[0]))]
for row in range(len(indexes))]
for row in range(len(indexes)):
if need_log:
m.output(row, len(indexes))
if 0 <= row < len(matrix):
matrix[indexes[row]] = data_set[row]
m.restore()
del indexes, data_set, m
return matrix
def get_yyc_rule_by_index(index, need_logs=False):
rules = []
temp_rule1 = ["".join(x) for x in itertools.product("01", repeat=4)]
temp_rule2 = ["".join(x) for x in itertools.product("01", repeat=16)]
m = monitor.Monitor()
if need_logs:
print("Find all the available Yin-Yang rules.")
count = 0
step = 0
for base in ["A", "T", "C", "G"]:
for rule1index in range(len(temp_rule1)):
for rule2index in range(len(temp_rule2)):
rule1 = list(map(int, list(temp_rule1[rule1index])))
rule2 = numpy.array(list(map(int, list(temp_rule2[rule2index])))).reshape(4, 4).tolist()
if _check(rule1, rule2):
rules.append(YYCRule(rule1, rule2, base, count))
count += 1
step += 1
if need_logs:
m.output(step, len(temp_rule1) * len(temp_rule2) * 4)
if index < 0 or index >= len(rules):
raise ValueError("We have " + str(len(rules)) + " rules, index " + str(index) + " is wrong!")
if need_logs:
print("Current Rule is " + str(rules[index].get_info()) + ".")
return rules[index].get_info()
def read_dna_file(path, need_log=False):
"""
introduction: Reading DNA sequence set from documents.
:param path: File path.
Type: string
:return dna_sequences: A corresponding DNA sequence string in which each row acts as a sequence.
Type: one-dimensional list(string)
:param need_log: need output log.
"""
m = monitor.Monitor()
dna_sequences = []
try:
with open(path, "r") as file:
if need_log:
log.output(log.NORMAL, str(__name__), str(sys._getframe().f_code.co_name),
"Read DNA sequences from file: " + path)
# Read current file by line
lines = file.readlines()
for index in range(len(lines)):
if need_log:
m.output(index, len(lines))
line = lines[index]
dna_sequences.append([line[col] for col in range(len(line) - 1)])
return dna_sequences
except IOError:
log.output(log.ERROR, str(__name__), str(sys._getframe().f_code.co_name),
"The file selection operation was not performed correctly. Please execute the operation again!")
def __init__(self,
homopolymer=4,
gc_content=0.2,
redundancy=0.5,
c_dist=0.1,
delta=0.5,
header_size=4,
recursion_depth=10000000,
decode_packets=None):
"""
introduction: The initialization method of FC.
:param homopolymer: maximum length of homopolymer, type = int.
:param gc_content: the fraction of gc content above/below 0.5 (0.1 means 0.4-0.6).
:param redundancy: artificial redundancy for decode successfully (0.5 generate 50% more fragments),type = float.
:param c_dist: Degree distribution tuning parameter,type = float.
:param delta: Degree distribution tuning parameter,type = float.
:param header_size: number of bytes for the header, type = int.
:param decode_packets: bit segments in the encoding process, type = int.
"""
self.homopolymer = homopolymer
self.gc_content = gc_content
self.redundancy = redundancy
self.header_size = header_size
self.recursion_depth = recursion_depth
self.c_dist = c_dist
self.delta = delta
self.decode_packets = decode_packets
self._init_check()
self.prng = None
self.file_size = 0
self.monitor = monitor.Monitor()
def read_binary_from_all(path, segment_length=120, need_log=False):
"""
introduction: Reading binary matrix from document.
:param path: File path.
Type: string
:param segment_length: The binary segment length used for DNA sequence generation.
Considering current DNA synthesis technique limitation,
we usually set 120 as default segment length.
:param need_log: choose to output log file or not.
:return matrix: A matrix in which each row represents a binary segment that will be used for DNA sequence generation.
Type: two-dimensional list(int)
"""
m = monitor.Monitor()
try:
# Open selected file
with open(path, mode="rb") as file:
if need_log:
log.output(log.NORMAL, str(__name__), str(sys._getframe().f_code.co_name),
"Read binary matrix from file: " + path)
size = os.path.getsize(path)
# Set init storage matrix
matrix = [[0 for _ in range(segment_length)] for _ in range(math.ceil(size * 8 / segment_length))]
row = 0
col = 0
for byte_index in range(size):
if need_log:
m.output(byte_index, size)
# Read a file as bytes
one_byte = file.read(1)
element = list(map(int, list(str(bin(struct.unpack("B", one_byte)[0]))[2:].zfill(8))))
for bit_index in range(8):
matrix[row][col] = element[bit_index]
col += 1
if col == segment_length:
col = 0
row += 1
if int(len(str(bin(len(matrix)))) - 2) * 7 > segment_length:
if need_log:
log.output(log.WARN, str(__name__), str(sys._getframe().f_code.co_name),
"The proportion of index in whole sequence may be high. \n"
"It is recommended to increase the length of output DNA sequences "
"or to divide the file into more segment pools")
return matrix, size
except IOError:
log.output(log.ERROR, str(__name__), str(sys._getframe().f_code.co_name),
"The file selection operation was not performed correctly. Please execute the operation again!")
def __init__(self, fixed_huffman=True):
"""
introduction: The initialization method of Huffman Codec.
:param fixed_huffman: Declare whether to use the Huffman dictionary in Goldman's paper.
In order to reduce the possible loss of function storage, we recommend using this dictionary.
"""
self.huffman_tree = None
self.segment_length = 0
self.fixed_huffman = fixed_huffman
self.file_size = 0
self.m = monitor.Monitor()
def __init__(self, mapping_rule=None):
"""
introduction: The initialization method of Simple Codec.
:param mapping_rule: Mapping between bases and numbers.
There can be two settings:
(1) Two bases correspond to a number (0 or 1): i.e. AT-0, CG-1.
(2) Each base corresponds to a number: i.e. A-00, T-01, C-10, G-11.
"""
if not mapping_rule:
mapping_rule = [0, 1, 1, 0]
self.mapping_rule = mapping_rule
self._init_check()
self.file_size = 0
self.m = monitor.Monitor()
def write_all_from_binary(path, matrix, size, need_log=False):
"""
introduction: Writing binary matrix to document.
:param path: File path.
Type: string
:param matrix: A matrix in which each row represents a binary segment that will be used for DNA sequence generation.
Type: two-dimensional list(int)
:param size: This refers to file size, to reduce redundant bits when transferring DNA to binary files.
Type: int
:param need_log: choose to output log file or not.
"""
m = monitor.Monitor()
try:
with open(path, "wb+") as file:
if need_log:
log.output(log.NORMAL, str(__name__), str(sys._getframe().f_code.co_name),
"Write file from binary matrix: " + path)
# Change bit to byte (8 -> 1), and write a file as bytes
bit_index = 0
temp_byte = 0
for row in range(len(matrix)):
if need_log:
m.output(row, len(matrix))
for col in range(len(matrix[0])):
bit_index += 1
temp_byte *= 2
temp_byte += matrix[row][col]
if bit_index == 8:
if size >= 0:
file.write(struct.pack("B", int(temp_byte)))
bit_index = 0
temp_byte = 0
size -= 1
except IOError:
log.output(log.ERROR, str(__name__), str(sys._getframe().f_code.co_name),
"The file selection operation was not performed correctly. Please execute the operation again!")
def __init__(self, base_values=None, need_log=False):
"""
introduction: The initialization method of Grass Codec.
:param base_values: Assignment of 48 base triplets (0-47).
Other values and their corresponding triplets will be discarded.
One-dimensional list containing all values of 0-46, 47 will be discarded.
"""
if base_values is None:
base_values = [index for index in range(48)]
temp_keys = []
temp_values = []
for index in range(len(base_values)):
if 0 <= base_values[index] < 47:
temp_keys.append(inherent.gc_codes[index])
temp_values.append(base_values[index])
self.mapping_rule = [temp_keys, temp_values]
self.segment_length = 0
self.file_size = 0
self.m = monitor.Monitor()