Initial commit.

Finished program with additional functions such as:
* Custom search string
* Custom search location

.gitignore

@@ -0,0 +1,195 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,visualstudiocode
+
+### 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
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/python,visualstudiocode

.vscode/launch.json

@@ -0,0 +1,21 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Run Fasta Filter",
+            "type": "python",
+            "request": "launch",
+            "program": "fasta_filter.py",
+            "args": [
+                "reference_standards.fas",
+                "reference_stasndards_filtered.fas",
+                "-c", "rt"
+            ],
+            "console": "integratedTerminal",
+            "justMyCode": true
+        }
+    ]
+}

README.md

@@ -0,0 +1,18 @@
+# Fasta Filter
+
+A simple program to remove sequences in a fasta file containing specific strings.
+
+## Usage
+
+ 0. Install python3.
+
+ 1. Run `pip install -r ./requirements.txt` if `biopython` is not installed. If installed, skip to step 2.
+
+ 2. Run `./fasta_filter.py -h` if on Linux, or on Windows `python3 ./fasta_filter -h`. See help for more information.
+
+### Example Usage
+
+ 1. Pretend `input.fasta` exists in the same folder as `fasta_filter.py` (the program file).
+
+ 2. To remove all sequences in `input.fasta` that contain `rt` in the header and output to a new file called `input_filtered.fasta`, run: `python3 ./fasta_filter input.fasta input_filtered.fasta -c rt`
+

fasta_filter.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+
+import os
+from Bio import SeqIO
+import argparse
+
+
+def main(args):
+    kept_records = []
+    for s_record in SeqIO.parse(args.input, "fasta"):
+        if args.property != "all" and not (
+                    args.contains in getattr(s_record, args.property)
+                ):
+            kept_records.append(s_record)
+        elif args.property == "all" and not (
+            args.contains in s_record.id
+            and args.contains in s_record.name
+                and args.contains in s_record.description):
+            kept_records.append(s_record)
+    SeqIO.write(
+        kept_records,
+        os.path.abspath(args.output),
+        "fasta"
+    )
+
+
+if __name__ == "__main__":
+    argparser = argparse.ArgumentParser(
+        "Removes sequences where id contains certain string.")
+    argparser.add_argument(
+        "input",
+        type=str,
+        metavar="i",
+        help="The input fasta file."
+    )
+
+    argparser.add_argument(
+        "output",
+        type=str,
+        metavar="o",
+        help="The output file path."
+    )
+
+    argparser.add_argument(
+        "-c",
+        "--contains",
+        type=str,
+        default=None,
+        required=False,
+        help="The string to search for."
+    )
+
+    argparser.add_argument(
+        "-p",
+        "--property",
+        type=str,
+        default="all",
+        required=False,
+        help="""
+        The part of the fasta file to look through. Valid options are: id,
+        name, description, or all.
+        """
+    )
+
+    main(argparser.parse_args())