diff --git a/build/lib/read_sequencer_package/__init__.py b/build/lib/read_sequencer_package/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/build/lib/read_sequencer_package/cli.py b/build/lib/read_sequencer_package/cli.py
new file mode 100644
index 0000000000000000000000000000000000000000..e786d78de5391ea2b035c058f4de2cd16162a4d6
--- /dev/null
+++ b/build/lib/read_sequencer_package/cli.py
@@ -0,0 +1,23 @@
+import argparse
+from modules import read_sequencer as rs
+
+parser = argparse.ArgumentParser(prog='read_sequencer',
+ description='Simulates sequencing of DNA sequences specified by an FASTA file.')
+parser.add_argument('--input_file_path',
+ help='path to FASTA file')
+parser.add_argument('--output_file_path',
+ help='path to FASTA file')
+parser.add_argument('--read_length',
+ help='read length for sequencing',
+ type=int)
+
+args = parser.parse_args()
+
+def main():
+ read_sequencer = rs()
+ read_sequencer.read_fasta(args.input_file_path)
+ read_sequencer.run_sequencing(args.read_length)
+ read_sequencer.write_fasta(args.output_file_path)
+
+if __name__ == '__main__':
+ main()
diff --git a/build/lib/read_sequencer_package/modules.py b/build/lib/read_sequencer_package/modules.py
new file mode 100644
index 0000000000000000000000000000000000000000..39a686616817f6b496328d460fe06931f9670da8
--- /dev/null
+++ b/build/lib/read_sequencer_package/modules.py
@@ -0,0 +1,148 @@
+def generate_sequences(n, mean, sd):
+ """
+ Generates random sequences.
+
+ Args:
+ n (int): Amount of sequences to generate.
+ mean (int): mean length of sequence (gaussian distribution).
+ sd (float): standard deviation of length of sequence (gaussian distribution).
+
+ Returns:
+ list: of n sequences
+ """
+ from random import gauss, choice
+ dict = {}
+ for i in range(n):
+ keys = range(n)
+ seq = ""
+ nt = ["A", "T", "C", "G"]
+ for value in range(abs(round(gauss(mean, sd)))):
+ seq = seq + choice(nt)
+ dict[keys[i]] = seq
+ return dict
+
+
+def read_in_fasta(file_path):
+ '''
+ This function reads in FASTA files.
+
+ Args:
+ file_path (str): A file path directing to the fasta file.
+
+ Returns:
+ Dict: It returns a dictionary with sequences.
+
+ '''
+ sequences = {}
+ f = open(file_path)
+ for line in f:
+ if line[0] == '>':
+ defline = line.strip()
+ defline = defline.replace('>', '')
+ else:
+ if defline not in sequences:
+ sequences[defline] = ''
+ sequences[defline] += line.strip()
+ f.close()
+ return sequences
+
+def read_sequence(seq, read_length):
+ '''
+ This function reads a sequence of a specific read length and adds additional nucleotides if the sequence is
+ smaller then the requested length or cuts the sequence if its longer.
+
+ Args:
+ seq (str): the sequence to read
+ read_length (int): length of reads
+
+ Returns:
+ str: returns sequenced element
+
+ '''
+ from random import choice
+ bases = ["A", "T", "C", "G"]
+ sequenced = ''
+ if read_length >= len(seq):
+ for nt in range(len(seq)):
+ sequenced += seq[nt]
+ for nt in range(len(seq), read_length):
+ sequenced += choice(bases)
+ else:
+ for nt in range(read_length):
+ sequenced += seq[nt]
+
+ return sequenced
+
+def simulate_sequencing(sequences, read_length):
+ """
+ Simulates sequencing.
+
+ Args:
+ sequences (dict): Dictionary of sequences to sequence.
+ read_length (int): length of reads
+
+ Returns:
+ dict: of n sequences as values
+ """
+ results = {}
+ for index, key in enumerate(sequences):
+ results[key] = read_sequence(sequences[key], read_length=read_length)
+
+ return results
+
+import random
+def generate_sequences(n, mean, sd):
+ """
+ Generates random sequences.
+
+ Args:
+ n (int): Amount of sequences to generate.
+ mean (int): mean length of sequence (gaussian distribution).
+ sd (float): standart deviation of length of sequence (gaussian distribution).
+
+ Returns:
+ dict: of n sequences
+ """
+ dict1 = {}
+ for i in range(n):
+ keys = range(n)
+ seq = ""
+ nt = ["A", "T", "C", "G"]
+ for value in range(round(random.gauss(mean, sd))):
+ seq = seq + random.choice(nt)
+ dict1[keys[i]] = seq
+ return dict1
+
+def write_fasta(sequences, file_path):
+ """
+ Takes a dictionary and writes it to a fasta file.
+ Must specify the filename when calling the function.
+
+ Args:
+ sequences (dict): Dictionary of sequence.
+ file_path (str): A file path directing to the output folder.
+
+ """
+ from textwrap import wrap
+ with open(file_path, "w") as outfile:
+ for key, value in sequences.items():
+ outfile.write(key + "\n")
+ outfile.write("\n".join(wrap(value, 60)))
+ outfile.write("\n")
+
+class read_sequencer:
+ def __init__(self):
+ self.sequences = {}
+ self.reads = {}
+
+ def add_random_sequences(self, n, mean, sd):
+ self.sequences = generate_sequences(n, mean, sd)
+
+ def read_fasta(self, input_file):
+ self.sequences = read_in_fasta(input_file)
+
+ def run_sequencing(self, read_length):
+ self.reads = simulate_sequencing(self.sequences, read_length)
+
+ def write_fasta(self, output_file_path):
+ write_fasta(self.reads, output_file_path)
diff --git a/dist/read_sequencer-0.1.1-py3-none-any.whl b/dist/read_sequencer-0.1.1-py3-none-any.whl
new file mode 100644
index 0000000000000000000000000000000000000000..234b5227d12d9f5e410d26b2e131fed34c2596fc
Binary files /dev/null and b/dist/read_sequencer-0.1.1-py3-none-any.whl differ
diff --git a/dist/read_sequencer-0.1.1.tar.gz b/dist/read_sequencer-0.1.1.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7eb03d4a5f331e1050f6b5f6c8cb5ee356fc2595
Binary files /dev/null and b/dist/read_sequencer-0.1.1.tar.gz differ