From c279468e880f63b780d96a8fc86ea933c304732a Mon Sep 17 00:00:00 2001
From: Madan Mukundan <madan.mukundan@gmail.com>
Date: Sat, 18 Dec 2021 15:55:50 +0100
Subject: [PATCH] build: unencapsulated working version with tests
---
src/plot_read_counts.py | 218 +++++++++++++++++++++++++
tests/resources/Transcript2.csv | 20 +++
tests/resources/Transcript3.csv | 19 +++
tests/resources/Transcript4.csv | 19 +++
tests/resources/Transcript5.csv | 19 +++
tests/resources/Transcript6.csv | 19 +++
tests/resources/Transcript7negctrl.csv | 8 +
tests/test_plot_read_counts.py | 32 ++++
8 files changed, 354 insertions(+)
create mode 100644 src/plot_read_counts.py
create mode 100644 tests/resources/Transcript2.csv
create mode 100644 tests/resources/Transcript3.csv
create mode 100644 tests/resources/Transcript4.csv
create mode 100644 tests/resources/Transcript5.csv
create mode 100644 tests/resources/Transcript6.csv
create mode 100644 tests/resources/Transcript7negctrl.csv
create mode 100644 tests/test_plot_read_counts.py
diff --git a/src/plot_read_counts.py b/src/plot_read_counts.py
new file mode 100644
index 0000000..20af36a
--- /dev/null
+++ b/src/plot_read_counts.py
@@ -0,0 +1,218 @@
+"""Plots read counts of gene expression data."""
+
+import logging
+import sys
+from pathlib import Path
+from tkinter import Tk, ttk, filedialog, StringVar
+from typing import Union
+
+import pandas
+import matplotlib.pyplot as plt
+
+"""Given a GeneID, construct the histogram of read counts per cell."""
+
+
+def plot_read_counts(
+ dir_path: Union[str, Path] = None,
+ gene_id: str = None
+) -> None:
+ """Plots histogram of gene ID and read counts from .csv files.
+
+ This function reads .csv files from a directory formatted
+ "GeneID, Counts" and plots a histogram of read counts for a
+ chosen geneID.
+
+ Args:
+ dir_path: Path of directory containing .csv files of read counts.
+ gene_id: Name of gene to plot.
+
+ Raises:
+ ValueError: No value is passed for path and/or gene ID.
+ ValueError: Path passed in does not exist.
+ ValueError: Gene not found in selection of .csv files.
+ TypeError: Gene ID parameter passed is not a String.
+ AttributeError: No .csv files in chosen directory
+ """
+ # Initialize logger
+ logging.basicConfig(
+ format='[%(asctime)s: %(levelname)s] "%(module)s" %(message)s',
+ level=logging.INFO)
+ LOGGER = logging.getLogger(__name__)
+
+ try:
+ dir_path = Path(dir_path)
+
+ if not dir_path.exists():
+ LOGGER.critical("Invalid path")
+ raise ValueError("Invalid Path")
+
+ elif not isinstance(gene_id, str):
+ LOGGER.critical("Invalid gene ID, please enter as string")
+ raise TypeError("Invalid gene ID")
+
+ # identify csv files from directory, formatted ['Gene', 'Count']
+ # if this is not immediately cast as list, on some python versions
+ # it sets file_paths to null after a single call which is big sad
+ file_paths = list(dir_path.glob("*.csv"))
+ file_paths.sort()
+
+ if file_paths == 0:
+ LOGGER.warning('No csv files found in current directory, exiting')
+ raise AttributeError("No .csv files found in chosen directory")
+
+ gene_count_dict = {}
+ file_counter = 1
+
+ LOGGER.info("Run with %s and gene %s" % (dir_path, gene_id))
+
+ for file_path in file_paths:
+ # read in csv here and transform to pandas dataframe
+ df_read_counts = pandas.read_csv(str(file_path),
+ header=None, names=['Gene', 'Count'])
+
+ # find gene_id within dataframe
+ gene_count = df_read_counts.loc[df_read_counts.Gene == gene_id,
+ 'Count'].tolist()
+
+ if len(gene_count) > 1:
+ LOGGER.warning(
+ "%s.csv contains more than one entry for chosen gene - these will be summed"
+ % (file_path.stem)
+ )
+
+ elif not gene_count:
+ LOGGER.warning(
+ "%s.csv does not contain read of chosen gene, this is interpreted as 0"
+ % (file_path.stem))
+ gene_count = [0]
+
+ # in case count entry is missing, interpreted as 0
+ if not gene_count:
+ gene_count = [0]
+ LOGGER.warning(
+ "File %s contains an entry for this gene but is missing a count number \
+ this is interpreted as 0" % (file_path.stem)
+ )
+
+ file_counter += 1
+ gene_count_dict[file_path.stem] = sum(gene_count)
+
+ except AttributeError:
+ LOGGER.fatal("Invalid selection, please verify input")
+ raise ValueError("Either the path, gene ID, or both were not properly specified")
+
+ if sum(gene_count_dict.values()) == 0:
+ LOGGER.warning(
+ "Gene not found -> Please check for correct spelling or ID"
+ )
+ raise ValueError("Gene not found")
+
+ else:
+ LOGGER.info('Read complete from %s files' % (file_counter-1))
+
+ # read in dictionary from read_counts and plot counts on the same histogram
+ file_names = list(gene_count_dict.keys())
+ counts = list(gene_count_dict.values())
+
+ # create and show bar plot of read counts for chosen gene
+ plt.bar(range(len(gene_count_dict)), counts, tick_label=file_names)
+ plt.title('Counts for %s' % (gene_id))
+ plt.show()
+
+
+def prc_dialog() -> None:
+ """Creates a GUI to select directory and enter gene."""
+ # Create dialog window
+ dialog = Tk()
+ dialog.title("Plot Gene Read Counts")
+ dialog.resizable(False, False)
+ dialog.geometry("380x210+20+20")
+ dialog.configure(background="black")
+
+ # Create and attach welcome message to GUI
+ wlcom_text = "Welcome to Plot Read Counts "
+ wlcom_msg = ttk.Label(dialog,
+ text=wlcom_text,
+ font=("Helvetica", 12, "bold"),
+ foreground="white",
+ background="black",
+ padding=5)
+ wlcom_msg.grid(column=1, row=0, columnspan=2, pady=5)
+
+ # Create and attach instruction message to GUI
+ inst_msg = ttk.Label(dialog,
+ text="Select a directory of .csv files and a gene ID to plot",
+ font=("Helvetica", 12),
+ foreground="white",
+ background="black",
+ padding=5)
+ inst_msg.grid(column=1, row=1, columnspan=2, padx=10, pady=5)
+
+ # Create and attach directory selection elements
+ # Either globals are needed or all functions
+ # need to be encapsulated
+ global dir_str_var
+ dir_str_var = StringVar()
+ dir_lbl = ttk.Label(dialog,
+ textvariable=dir_str_var,
+ font=("Courier", 10, "bold"),
+ background="black",
+ foreground="green")
+ dir_lbl.grid(column=1, row=4, padx=5, pady=1, sticky="e")
+ dir_btn = ttk.Button(dialog, text="Select Directory",
+ command=lambda: get_dir())
+ dir_btn.grid(column=1, row=6, padx=5, pady=1)
+
+ # Create and attach gene selection elements
+ global gene_lbl
+ gene_lbl = StringVar()
+ gene_entry = ttk.Entry(dialog)
+ gene_entry.grid(column=2, row=5, pady=1)
+ gene_entry_lbl = ttk.Label(anchor="center",
+ textvariable=gene_lbl,
+ font=("Courier", 10, "bold"),
+ background="black",
+ foreground="green")
+ gene_entry_lbl.grid(column=2, row=4, pady=1)
+ gene_entry_btn = ttk.Button(dialog,
+ text="Confirm Gene (Case Sensitive)",
+ command=lambda: get_gene_id(gene_entry))
+ gene_entry_btn.grid(column=2, row=6, padx=2, pady=2)
+
+ # Create and attach confirm and close element
+ kill_btn = ttk.Button(dialog, text="Exit and Plot",
+ command=lambda: dialog.destroy())
+ kill_btn.grid(column=1, row=8, columnspan=2, padx=5, pady=15)
+
+ dialog.mainloop()
+
+ if 'gui_path' in globals() and 'gui_gene_id' in globals():
+ plot_read_counts(gui_path, gui_gene_id)
+ else:
+ sys.exit()
+
+
+def get_dir() -> Path:
+ """Support function to retrieve dir from GUI."""
+ global gui_path
+ gui_path = Path(filedialog.askdirectory(
+ title='Please select the directory containing \
+ gene reads'))
+ short_dir = ("%s/.../%s/" % (gui_path.drive, gui_path.name))
+ dir_str_var.set(short_dir)
+
+
+def get_gene_id(gene_entry: StringVar) -> str:
+ """Support function to retrieve gene ID from GUI."""
+ global gui_gene_id
+ gui_gene_id = gene_entry.get()
+ gene_lbl.set(gene_entry.get())
+
+
+def main() -> None:
+ """Main opens GUI for dir and gene ID selection."""
+ prc_dialog()
+
+
+if __name__ == '__main__':
+ main()
diff --git a/tests/resources/Transcript2.csv b/tests/resources/Transcript2.csv
new file mode 100644
index 0000000..2a3dc0c
--- /dev/null
+++ b/tests/resources/Transcript2.csv
@@ -0,0 +1,20 @@
+GENE1,624
+GENE2,895
+GENE3,870
+GENE4,428
+GENE5,449
+GENE6,696
+GENE7,544
+GENE8,338
+GENE9,159
+GENE10,267
+GENE11,268
+GENE12,879
+GENE13,556
+GENE14,613
+GENE15,629
+GENE16,116
+GENE17,762
+GENE18,67
+GENE19,405
+GENE20,3
diff --git a/tests/resources/Transcript3.csv b/tests/resources/Transcript3.csv
new file mode 100644
index 0000000..2473e67
--- /dev/null
+++ b/tests/resources/Transcript3.csv
@@ -0,0 +1,19 @@
+GENE1,830
+GENE2,602
+GENE3,859
+GENE4,174
+GENE5,525
+GENE6,606
+,
+GENE8,910
+GENE9,194
+GENE10,415
+GENE11,953
+GENE12,299
+GENE13,127
+GENE14,750
+GENE15,968
+GENE16,282
+GENE17,868
+GENE18,688
+GENE19,650
diff --git a/tests/resources/Transcript4.csv b/tests/resources/Transcript4.csv
new file mode 100644
index 0000000..ff000bd
--- /dev/null
+++ b/tests/resources/Transcript4.csv
@@ -0,0 +1,19 @@
+GENE1,629
+GENE2,803
+GENE3,106
+GENE4,378
+GENE5,728
+GENE6,783
+GENE7,353
+GENE8,747
+GENE9,253
+GENE10,883
+GENE11,552
+GENE12,655
+GENE13,309
+GENE14,133
+GENE15,131
+GENE16,626
+GENE17,669
+GENE18,493
+GENE19,304
diff --git a/tests/resources/Transcript5.csv b/tests/resources/Transcript5.csv
new file mode 100644
index 0000000..34613ca
--- /dev/null
+++ b/tests/resources/Transcript5.csv
@@ -0,0 +1,19 @@
+GENE1,830
+GENE2,602
+GENE3,859
+GENE4,174
+GENE5,525
+GENE6,606
+GENE7,851
+GENE8,910
+GENE9,194
+GENE10,415
+GENE11,953
+GENE12,299
+GENE13,127
+GENE14,750
+GENE15,968
+GENE16,282
+GENE17,868
+GENE18,688
+GENE19,650
diff --git a/tests/resources/Transcript6.csv b/tests/resources/Transcript6.csv
new file mode 100644
index 0000000..794d1c1
--- /dev/null
+++ b/tests/resources/Transcript6.csv
@@ -0,0 +1,19 @@
+GENE1,676
+GENE2,787
+GENE3,876
+GENE4,368
+GENE5,676
+GENE6,896
+GENE7,865
+GENE8,585
+GENE9,853
+GENE10,447
+GENE11,583
+GENE12,573
+GENE13,895
+GENE14,207
+GENE15,562
+GENE16,411
+GENE17,635
+GENE18,469
+GENE19,128
diff --git a/tests/resources/Transcript7negctrl.csv b/tests/resources/Transcript7negctrl.csv
new file mode 100644
index 0000000..72cb6bf
--- /dev/null
+++ b/tests/resources/Transcript7negctrl.csv
@@ -0,0 +1,8 @@
+Random,Data,for
+This,is,a
+negative,control,test
+some,numbers,
+234,,
+,432,
+,,
+32,,
diff --git a/tests/test_plot_read_counts.py b/tests/test_plot_read_counts.py
new file mode 100644
index 0000000..add8572
--- /dev/null
+++ b/tests/test_plot_read_counts.py
@@ -0,0 +1,32 @@
+"Test for plot_read_counts module"
+
+import pytest
+from pathlib import Path
+from src.plot_read_counts import plot_read_counts
+
+class TestPlotReadCounts ():
+
+ @pytest.mark.parametrize(
+ "dir_path, gene_id, expected",
+ [
+ ('a', 'GENE1', ValueError),
+ ('Path.home()', 5, TypeError),
+ (None, None, ValueError),
+ ('Path.home()', 'GENE1', AttributeError),
+ ]
+ )
+ def test_invalid_input(self, dir_path, gene_id, expected):
+ with pytest.raises(expected):
+ plot_read_counts(dir_path, gene_id)
+
+ def validate_input():
+
+ pass
+
+ #plot_dir = PurePath('H:/My Drive/PhD/PLS/PLS scRNAseq Repo/scrna-seq-simulation/tests/resources')
+ #plot_dir = 'H:/My Drive/PhD/PLS scRNAseq Repo/scrna-seq-simulation/'
+ # plot_dir = PurePath(filedialog.askdirectory(title='Please select the directory containing \
+ # gene reads'))
+ # gene_of_interest = input('\nPlease type a gene ID to sample: ').upper()
+ #gene_of_interest = 'GENE1'
+
\ No newline at end of file
--
GitLab