diff --git a/.gitignore b/.gitignore
index e67a40ec0cbb5aa7e77e9607e08a517dc1187296..42770ec5750d8d11f9d2c139003b8307d923f626 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,174 @@
.DS_Store
.idea/
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+ For a library or package, you might want to ignore these files since the code is
+ intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+
+# End of https://www.toptal.com/developers/gitignore/api/python
diff --git a/build/lib/read_sequencer_package/__init__.py b/build/lib/read_sequencer_package/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/build/lib/read_sequencer_package/cli.py b/build/lib/read_sequencer_package/cli.py
deleted file mode 100644
index e786d78de5391ea2b035c058f4de2cd16162a4d6..0000000000000000000000000000000000000000
--- a/build/lib/read_sequencer_package/cli.py
+++ /dev/null
@@ -1,23 +0,0 @@
-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
deleted file mode 100644
index 39a686616817f6b496328d460fe06931f9670da8..0000000000000000000000000000000000000000
--- a/build/lib/read_sequencer_package/modules.py
+++ /dev/null
@@ -1,148 +0,0 @@
-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
deleted file mode 100644
index 234b5227d12d9f5e410d26b2e131fed34c2596fc..0000000000000000000000000000000000000000
Binary files a/dist/read_sequencer-0.1.1-py3-none-any.whl and /dev/null differ
diff --git a/dist/read_sequencer-0.1.1.tar.gz b/dist/read_sequencer-0.1.1.tar.gz
deleted file mode 100644
index 7eb03d4a5f331e1050f6b5f6c8cb5ee356fc2595..0000000000000000000000000000000000000000
Binary files a/dist/read_sequencer-0.1.1.tar.gz and /dev/null differ
diff --git a/images/Git_Tutorial_CSerger.png b/images/Git_Tutorial_CSerger.png
deleted file mode 100644
index a80ebb2cff393ab5575bbb50804b42f9ba7ff77c..0000000000000000000000000000000000000000
Binary files a/images/Git_Tutorial_CSerger.png and /dev/null differ
diff --git a/images/Markdown_Tutorial_CSerger.png b/images/Markdown_Tutorial_CSerger.png
deleted file mode 100644
index 1146d19773186c648382ce4aa87681c0001b7a67..0000000000000000000000000000000000000000
Binary files a/images/Markdown_Tutorial_CSerger.png and /dev/null differ
diff --git a/images/Michael_Screenshot 2022-11-07 at 17.38.44.png b/images/Michael_Screenshot 2022-11-07 at 17.38.44.png
deleted file mode 100644
index 272acf066d23d8440b02356cfc2ebd579f2f9569..0000000000000000000000000000000000000000
Binary files a/images/Michael_Screenshot 2022-11-07 at 17.38.44.png and /dev/null differ
diff --git a/images/Michael_Screenshot 2022-11-08 at 13.35.22.png b/images/Michael_Screenshot 2022-11-08 at 13.35.22.png
deleted file mode 100644
index 2deedd0c2a642d492a959ce85733fbfdf2e508ed..0000000000000000000000000000000000000000
Binary files a/images/Michael_Screenshot 2022-11-08 at 13.35.22.png and /dev/null differ
diff --git a/images/Michael_Screenshot 2022-11-08 at 14.38.02.png b/images/Michael_Screenshot 2022-11-08 at 14.38.02.png
deleted file mode 100644
index 4bdbfdf333fcacdc043e990027dd232953d53b20..0000000000000000000000000000000000000000
Binary files a/images/Michael_Screenshot 2022-11-08 at 14.38.02.png and /dev/null differ
diff --git a/images/screenshot_git_tutorial_main_harmel.png b/images/screenshot_git_tutorial_main_harmel.png
deleted file mode 100644
index fcbb8fde4d7ee8cb4d61d2cf3ff62ccddf11ff53..0000000000000000000000000000000000000000
Binary files a/images/screenshot_git_tutorial_main_harmel.png and /dev/null differ
diff --git a/images/screenshot_git_tutorial_remote_harmel.png b/images/screenshot_git_tutorial_remote_harmel.png
deleted file mode 100644
index 76ff324be44e1e54447ae6fc09ecc62d50b48583..0000000000000000000000000000000000000000
Binary files a/images/screenshot_git_tutorial_remote_harmel.png and /dev/null differ
diff --git a/images/screenshot_markup_tutorial_harmel.png b/images/screenshot_markup_tutorial_harmel.png
deleted file mode 100644
index db3aaf02cb5ec285c3cf5f76fe1d25134df69907..0000000000000000000000000000000000000000
Binary files a/images/screenshot_markup_tutorial_harmel.png and /dev/null differ
diff --git a/read_sequencer.egg-info/PKG-INFO b/read_sequencer.egg-info/PKG-INFO
deleted file mode 100644
index ed2a2f723157a60010ad224e55406bda28f82255..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/PKG-INFO
+++ /dev/null
@@ -1,9 +0,0 @@
-Metadata-Version: 2.1
-Name: read-sequencer
-Version: 0.1.1
-Summary: Simulates sequencing with a specified read length from sequences specified by a FASTA file.
-Home-page: https://git.scicore.unibas.ch/zavolan_group/tools/read-sequencer
-Author: Clara Serger, Michael Sandholzer and Christoph Harmel
-Author-email: christoph.harmel@unibas.ch
-License: MIT
-License-File: LICENSE.txt
diff --git a/read_sequencer.egg-info/SOURCES.txt b/read_sequencer.egg-info/SOURCES.txt
deleted file mode 100644
index 9b093f4ab2fab7288a29384742947a5405d68517..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/SOURCES.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-LICENSE.txt
-README.md
-setup.py
-read_sequencer.egg-info/PKG-INFO
-read_sequencer.egg-info/SOURCES.txt
-read_sequencer.egg-info/dependency_links.txt
-read_sequencer.egg-info/entry_points.txt
-read_sequencer.egg-info/requires.txt
-read_sequencer.egg-info/top_level.txt
-read_sequencer_package/__init__.py
-read_sequencer_package/cli.py
-read_sequencer_package/modules.py
\ No newline at end of file
diff --git a/read_sequencer.egg-info/dependency_links.txt b/read_sequencer.egg-info/dependency_links.txt
deleted file mode 100644
index 8b137891791fe96927ad78e64b0aad7bded08bdc..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/dependency_links.txt
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/read_sequencer.egg-info/entry_points.txt b/read_sequencer.egg-info/entry_points.txt
deleted file mode 100644
index 569e8154320e35d343a621996abf05109990fec6..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/entry_points.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-[console_scripts]
-read_sequencer = read_sequencer_package.cli:main
diff --git a/read_sequencer.egg-info/requires.txt b/read_sequencer.egg-info/requires.txt
deleted file mode 100644
index d9ca6c64cbd4a8ce3229966dd400911a7f626665..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/requires.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-random
-textwrap
-argparse
diff --git a/read_sequencer.egg-info/top_level.txt b/read_sequencer.egg-info/top_level.txt
deleted file mode 100644
index a5c49290c04dc99c11fd0696381a1287c34af400..0000000000000000000000000000000000000000
--- a/read_sequencer.egg-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-read_sequencer_package
diff --git a/read_sequencer_package/cli.py b/read_sequencer_package/cli.py
index 9a68267c115d328afa32e582d8c03e4aede2a076..c6dce09b4e30a35520040220358e868ea99e8081 100644
--- a/read_sequencer_package/cli.py
+++ b/read_sequencer_package/cli.py
@@ -1,5 +1,5 @@
import argparse
-from modules import ReadSequencer
+from read_sequencer import ReadSequencer
import logging
parser = argparse.ArgumentParser(prog='read_sequencer',
diff --git a/read_sequencer_package/modules.py b/read_sequencer_package/read_sequencer.py
similarity index 100%
rename from read_sequencer_package/modules.py
rename to read_sequencer_package/read_sequencer.py
diff --git a/read_sequencer_package/fasta_testfile/50_seqs_50_1000_bp.fasta b/tests/fasta_testfile/50_seqs_50_1000_bp.fasta
similarity index 100%
rename from read_sequencer_package/fasta_testfile/50_seqs_50_1000_bp.fasta
rename to tests/fasta_testfile/50_seqs_50_1000_bp.fasta
diff --git a/read_sequencer_package/fasta_testfile/result.fasta b/tests/fasta_testfile/result.fasta
similarity index 100%
rename from read_sequencer_package/fasta_testfile/result.fasta
rename to tests/fasta_testfile/result.fasta