Create fastq sorting script

.gitignore

@@ -1 +1,175 @@
 FAP012345
+
+# Files generated by invoking Julia with --code-coverage
+*.jl.cov
+*.jl.*.cov
+
+# Files generated by invoking Julia with --track-allocation
+*.jl.mem
+
+# System-specific files and directories generated by the BinaryProvider and BinDeps packages
+# They contain absolute paths specific to the host computer, and so should not be committed
+deps/deps.jl
+deps/build.log
+deps/downloads/
+deps/usr/
+deps/src/
+
+# Build artifacts for creating documentation generated by the Documenter package
+docs/build/
+docs/site/
+
+# File generated by Pkg, the package manager, based on a corresponding Project.toml
+# It records a fixed state of all packages used by the project. As such, it should not be
+# committed for packages, but should be committed for applications that require a static
+# environment.
+Manifest.toml
+
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/
+
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+*.code-workspace
+
+# Local History for Visual Studio Code
+.history/

illumina/Project.toml

@@ -0,0 +1,10 @@
+name = "illumina"
+uuid = "312f6f2e-1d90-4382-8764-8510b154b64c"
+authors = ["Thomas A. Christensen II <25492070+MillironX@users.noreply.github.com>"]
+version = "0.1.0"
+
+[deps]
+DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+Missings = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
+Tk = "4225ea8a-3324-57e7-9ddc-5798a2cb9eab"
+XLSX = "fdbf4ff8-1666-58a4-91e7-1b58723a45e0"

illumina/rename-fastqs.jl

@@ -0,0 +1,59 @@
+#!/usr/bin/julia
+# Renames the FASTQ files in a directory by prepending the well number
+
+# Activate the proper packages
+using Tk
+import XLSX
+using DataFrames
+using Missings
+
+# Prompt for the folder containing the FASTQs
+fastq_folder = ChooseDirectory()
+
+# Prompt for the Illumina workbook containing the well info
+illumina_workbook = GetOpenFile()
+
+# Read in the excel file
+xf = XLSX.readdata(illumina_workbook, "IEM_SampleSheet!B19:D300")
+fastq_ids = DataFrame(xf, :auto)
+rename!(fastq_ids, Symbol.(["SampleId", "RunName", "WellNum"]))
+dropmissing!(fastq_ids)
+fastq_ids = string.(fastq_ids)
+
+# Get all of the files
+fastqs = readdir(fastq_folder)
+
+# Iterate through each file
+for fastq in fastqs
+    # Get the full path
+    fastq_path = joinpath(fastq_folder, fastq)
+
+    # Delete if this is a JSON file
+    if last(fastq,5) == ".json"
+        rm(fastq_path)
+        println(string("Deleting ", fastq_path))
+        continue
+    end
+
+    # Pull the id based on the file name
+    id = first(fastq,21)
+
+    # Find this id in the workbook
+    id_row = fastq_ids[fastq_ids.SampleId .== id,:]
+
+    # If there are no matches, keep going
+    if size(id_row)[1] < 1
+        continue
+    end
+
+    # Swap the column and row
+    well_num = string(last(id_row.WellNum[1],1), first(id_row.WellNum[1],1))
+
+    # Construct the new filename
+    fastq_newname = string(well_num, "_", fastq)
+
+    # Rename the file
+    mv(fastq_path, joinpath(fastq_folder, fastq_newname))
+    println(string("Renaming ", fastq_path, " to ", joinpath(fastq_folder, fastq_newname)))
+
+end