diff --git a/.gitignore b/.gitignore
index bfe05739d4822fa33b071bdd21d39ac3cb90940e..16926746db9b8f735eaac10e5b5fbd44c367313f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -156,4 +156,7 @@ dmypy.json
# Cython debug symbols
cython_debug/
+# VSCode
+.vscode/
+
# End of https://www.toptal.com/developers/gitignore/api/python,git
\ No newline at end of file
diff --git a/plots/reads_plot_220106_1.svg b/plots/reads_plot_220106_1.svg
new file mode 100644
index 0000000000000000000000000000000000000000..96192c54ec6b97e79d4774868b612757ebc10303
--- /dev/null
+++ b/plots/reads_plot_220106_1.svg
@@ -0,0 +1,866 @@
+<?xml version="1.0" encoding="utf-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Created with matplotlib (https://matplotlib.org/) -->
+<svg height="345.6pt" version="1.1" viewBox="0 0 460.8 345.6" width="460.8pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+ <metadata>
+ <rdf:RDF xmlns:cc="http://creativecommons.org/ns#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+ <cc:Work>
+ <dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
+ <dc:date>2022-01-06T20:59:13.732146</dc:date>
+ <dc:format>image/svg+xml</dc:format>
+ <dc:creator>
+ <cc:Agent>
+ <dc:title>Matplotlib v3.3.2, https://matplotlib.org/</dc:title>
+ </cc:Agent>
+ </dc:creator>
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <defs>
+ <style type="text/css">*{stroke-linecap:butt;stroke-linejoin:round;}</style>
+ </defs>
+ <g id="figure_1">
+ <g id="patch_1">
+ <path d="M 0 345.6
+L 460.8 345.6
+L 460.8 0
+L 0 0
+z
+" style="fill:#ffffff;"/>
+ </g>
+ <g id="axes_1">
+ <g id="patch_2">
+ <path d="M 57.6 307.584
+L 414.72 307.584
+L 414.72 41.472
+L 57.6 41.472
+z
+" style="fill:#ffffff;"/>
+ </g>
+ <g id="patch_3">
+ <path clip-path="url(#p07942fdf52)" d="M 73.832727 307.584
+L 112.02738 307.584
+L 112.02738 307.584
+L 73.832727 307.584
+z
+" style="fill:#1f77b4;"/>
+ </g>
+ <g id="patch_4">
+ <path clip-path="url(#p07942fdf52)" d="M 169.319358 307.584
+L 207.514011 307.584
+L 207.514011 72.550257
+L 169.319358 72.550257
+z
+" style="fill:#1f77b4;"/>
+ </g>
+ <g id="patch_5">
+ <path clip-path="url(#p07942fdf52)" d="M 264.805989 307.584
+L 303.000642 307.584
+L 303.000642 281.532067
+L 264.805989 281.532067
+z
+" style="fill:#1f77b4;"/>
+ </g>
+ <g id="patch_6">
+ <path clip-path="url(#p07942fdf52)" d="M 360.29262 307.584
+L 398.487273 307.584
+L 398.487273 130.883933
+L 360.29262 130.883933
+z
+" style="fill:#1f77b4;"/>
+ </g>
+ <g id="patch_7">
+ <path clip-path="url(#p07942fdf52)" d="M 73.832727 307.584
+L 112.02738 307.584
+L 112.02738 307.584
+L 73.832727 307.584
+z
+" style="fill:#ff7f0e;"/>
+ </g>
+ <g id="patch_8">
+ <path clip-path="url(#p07942fdf52)" d="M 169.319358 307.584
+L 207.514011 307.584
+L 207.514011 137.113743
+L 169.319358 137.113743
+z
+" style="fill:#ff7f0e;"/>
+ </g>
+ <g id="patch_9">
+ <path clip-path="url(#p07942fdf52)" d="M 264.805989 307.584
+L 303.000642 307.584
+L 303.000642 303.902749
+L 264.805989 303.902749
+z
+" style="fill:#ff7f0e;"/>
+ </g>
+ <g id="patch_10">
+ <path clip-path="url(#p07942fdf52)" d="M 360.29262 307.584
+L 398.487273 307.584
+L 398.487273 54.144
+L 360.29262 54.144
+z
+" style="fill:#ff7f0e;"/>
+ </g>
+ <g id="patch_11">
+ <path clip-path="url(#p07942fdf52)" d="M 73.832727 307.584
+L 112.02738 307.584
+L 112.02738 307.584
+L 73.832727 307.584
+z
+" style="fill:#2ca02c;"/>
+ </g>
+ <g id="patch_12">
+ <path clip-path="url(#p07942fdf52)" d="M 169.319358 307.584
+L 207.514011 307.584
+L 207.514011 64.338235
+L 169.319358 64.338235
+z
+" style="fill:#2ca02c;"/>
+ </g>
+ <g id="patch_13">
+ <path clip-path="url(#p07942fdf52)" d="M 264.805989 307.584
+L 303.000642 307.584
+L 303.000642 286.912358
+L 264.805989 286.912358
+z
+" style="fill:#2ca02c;"/>
+ </g>
+ <g id="patch_14">
+ <path clip-path="url(#p07942fdf52)" d="M 360.29262 307.584
+L 398.487273 307.584
+L 398.487273 61.22333
+L 360.29262 61.22333
+z
+" style="fill:#2ca02c;"/>
+ </g>
+ <g id="matplotlib.axis_1">
+ <g id="xtick_1">
+ <g id="line2d_1">
+ <defs>
+ <path d="M 0 0
+L 0 3.5
+" id="mb3344cd381" style="stroke:#000000;stroke-width:0.8;"/>
+ </defs>
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="92.930053" xlink:href="#mb3344cd381" y="307.584"/>
+ </g>
+ </g>
+ <g id="text_1">
+ <!-- Read 1 -->
+ <g transform="translate(75.595678 322.182437)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 44.390625 34.1875
+Q 47.5625 33.109375 50.5625 29.59375
+Q 53.5625 26.078125 56.59375 19.921875
+L 66.609375 0
+L 56 0
+L 46.6875 18.703125
+Q 43.0625 26.03125 39.671875 28.421875
+Q 36.28125 30.8125 30.421875 30.8125
+L 19.671875 30.8125
+L 19.671875 0
+L 9.8125 0
+L 9.8125 72.90625
+L 32.078125 72.90625
+Q 44.578125 72.90625 50.734375 67.671875
+Q 56.890625 62.453125 56.890625 51.90625
+Q 56.890625 45.015625 53.6875 40.46875
+Q 50.484375 35.9375 44.390625 34.1875
+z
+M 19.671875 64.796875
+L 19.671875 38.921875
+L 32.078125 38.921875
+Q 39.203125 38.921875 42.84375 42.21875
+Q 46.484375 45.515625 46.484375 51.90625
+Q 46.484375 58.296875 42.84375 61.546875
+Q 39.203125 64.796875 32.078125 64.796875
+z
+" id="DejaVuSans-82"/>
+ <path d="M 56.203125 29.59375
+L 56.203125 25.203125
+L 14.890625 25.203125
+Q 15.484375 15.921875 20.484375 11.0625
+Q 25.484375 6.203125 34.421875 6.203125
+Q 39.59375 6.203125 44.453125 7.46875
+Q 49.3125 8.734375 54.109375 11.28125
+L 54.109375 2.78125
+Q 49.265625 0.734375 44.1875 -0.34375
+Q 39.109375 -1.421875 33.890625 -1.421875
+Q 20.796875 -1.421875 13.15625 6.1875
+Q 5.515625 13.8125 5.515625 26.8125
+Q 5.515625 40.234375 12.765625 48.109375
+Q 20.015625 56 32.328125 56
+Q 43.359375 56 49.78125 48.890625
+Q 56.203125 41.796875 56.203125 29.59375
+z
+M 47.21875 32.234375
+Q 47.125 39.59375 43.09375 43.984375
+Q 39.0625 48.390625 32.421875 48.390625
+Q 24.90625 48.390625 20.390625 44.140625
+Q 15.875 39.890625 15.1875 32.171875
+z
+" id="DejaVuSans-101"/>
+ <path d="M 34.28125 27.484375
+Q 23.390625 27.484375 19.1875 25
+Q 14.984375 22.515625 14.984375 16.5
+Q 14.984375 11.71875 18.140625 8.90625
+Q 21.296875 6.109375 26.703125 6.109375
+Q 34.1875 6.109375 38.703125 11.40625
+Q 43.21875 16.703125 43.21875 25.484375
+L 43.21875 27.484375
+z
+M 52.203125 31.203125
+L 52.203125 0
+L 43.21875 0
+L 43.21875 8.296875
+Q 40.140625 3.328125 35.546875 0.953125
+Q 30.953125 -1.421875 24.3125 -1.421875
+Q 15.921875 -1.421875 10.953125 3.296875
+Q 6 8.015625 6 15.921875
+Q 6 25.140625 12.171875 29.828125
+Q 18.359375 34.515625 30.609375 34.515625
+L 43.21875 34.515625
+L 43.21875 35.40625
+Q 43.21875 41.609375 39.140625 45
+Q 35.0625 48.390625 27.6875 48.390625
+Q 23 48.390625 18.546875 47.265625
+Q 14.109375 46.140625 10.015625 43.890625
+L 10.015625 52.203125
+Q 14.9375 54.109375 19.578125 55.046875
+Q 24.21875 56 28.609375 56
+Q 40.484375 56 46.34375 49.84375
+Q 52.203125 43.703125 52.203125 31.203125
+z
+" id="DejaVuSans-97"/>
+ <path d="M 45.40625 46.390625
+L 45.40625 75.984375
+L 54.390625 75.984375
+L 54.390625 0
+L 45.40625 0
+L 45.40625 8.203125
+Q 42.578125 3.328125 38.25 0.953125
+Q 33.9375 -1.421875 27.875 -1.421875
+Q 17.96875 -1.421875 11.734375 6.484375
+Q 5.515625 14.40625 5.515625 27.296875
+Q 5.515625 40.1875 11.734375 48.09375
+Q 17.96875 56 27.875 56
+Q 33.9375 56 38.25 53.625
+Q 42.578125 51.265625 45.40625 46.390625
+z
+M 14.796875 27.296875
+Q 14.796875 17.390625 18.875 11.75
+Q 22.953125 6.109375 30.078125 6.109375
+Q 37.203125 6.109375 41.296875 11.75
+Q 45.40625 17.390625 45.40625 27.296875
+Q 45.40625 37.203125 41.296875 42.84375
+Q 37.203125 48.484375 30.078125 48.484375
+Q 22.953125 48.484375 18.875 42.84375
+Q 14.796875 37.203125 14.796875 27.296875
+z
+" id="DejaVuSans-100"/>
+ <path id="DejaVuSans-32"/>
+ <path d="M 12.40625 8.296875
+L 28.515625 8.296875
+L 28.515625 63.921875
+L 10.984375 60.40625
+L 10.984375 69.390625
+L 28.421875 72.90625
+L 38.28125 72.90625
+L 38.28125 8.296875
+L 54.390625 8.296875
+L 54.390625 0
+L 12.40625 0
+z
+" id="DejaVuSans-49"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-82"/>
+ <use x="64.982422" xlink:href="#DejaVuSans-101"/>
+ <use x="126.505859" xlink:href="#DejaVuSans-97"/>
+ <use x="187.785156" xlink:href="#DejaVuSans-100"/>
+ <use x="251.261719" xlink:href="#DejaVuSans-32"/>
+ <use x="283.048828" xlink:href="#DejaVuSans-49"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_2">
+ <g id="line2d_2">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="188.416684" xlink:href="#mb3344cd381" y="307.584"/>
+ </g>
+ </g>
+ <g id="text_2">
+ <!-- Read 2 -->
+ <g transform="translate(171.082309 322.182437)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 19.1875 8.296875
+L 53.609375 8.296875
+L 53.609375 0
+L 7.328125 0
+L 7.328125 8.296875
+Q 12.9375 14.109375 22.625 23.890625
+Q 32.328125 33.6875 34.8125 36.53125
+Q 39.546875 41.84375 41.421875 45.53125
+Q 43.3125 49.21875 43.3125 52.78125
+Q 43.3125 58.59375 39.234375 62.25
+Q 35.15625 65.921875 28.609375 65.921875
+Q 23.96875 65.921875 18.8125 64.3125
+Q 13.671875 62.703125 7.8125 59.421875
+L 7.8125 69.390625
+Q 13.765625 71.78125 18.9375 73
+Q 24.125 74.21875 28.421875 74.21875
+Q 39.75 74.21875 46.484375 68.546875
+Q 53.21875 62.890625 53.21875 53.421875
+Q 53.21875 48.921875 51.53125 44.890625
+Q 49.859375 40.875 45.40625 35.40625
+Q 44.1875 33.984375 37.640625 27.21875
+Q 31.109375 20.453125 19.1875 8.296875
+z
+" id="DejaVuSans-50"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-82"/>
+ <use x="64.982422" xlink:href="#DejaVuSans-101"/>
+ <use x="126.505859" xlink:href="#DejaVuSans-97"/>
+ <use x="187.785156" xlink:href="#DejaVuSans-100"/>
+ <use x="251.261719" xlink:href="#DejaVuSans-32"/>
+ <use x="283.048828" xlink:href="#DejaVuSans-50"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_3">
+ <g id="line2d_3">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="283.903316" xlink:href="#mb3344cd381" y="307.584"/>
+ </g>
+ </g>
+ <g id="text_3">
+ <!-- Read 3 -->
+ <g transform="translate(266.568941 322.182437)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 40.578125 39.3125
+Q 47.65625 37.796875 51.625 33
+Q 55.609375 28.21875 55.609375 21.1875
+Q 55.609375 10.40625 48.1875 4.484375
+Q 40.765625 -1.421875 27.09375 -1.421875
+Q 22.515625 -1.421875 17.65625 -0.515625
+Q 12.796875 0.390625 7.625 2.203125
+L 7.625 11.71875
+Q 11.71875 9.328125 16.59375 8.109375
+Q 21.484375 6.890625 26.8125 6.890625
+Q 36.078125 6.890625 40.9375 10.546875
+Q 45.796875 14.203125 45.796875 21.1875
+Q 45.796875 27.640625 41.28125 31.265625
+Q 36.765625 34.90625 28.71875 34.90625
+L 20.21875 34.90625
+L 20.21875 43.015625
+L 29.109375 43.015625
+Q 36.375 43.015625 40.234375 45.921875
+Q 44.09375 48.828125 44.09375 54.296875
+Q 44.09375 59.90625 40.109375 62.90625
+Q 36.140625 65.921875 28.71875 65.921875
+Q 24.65625 65.921875 20.015625 65.03125
+Q 15.375 64.15625 9.8125 62.3125
+L 9.8125 71.09375
+Q 15.4375 72.65625 20.34375 73.4375
+Q 25.25 74.21875 29.59375 74.21875
+Q 40.828125 74.21875 47.359375 69.109375
+Q 53.90625 64.015625 53.90625 55.328125
+Q 53.90625 49.265625 50.4375 45.09375
+Q 46.96875 40.921875 40.578125 39.3125
+z
+" id="DejaVuSans-51"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-82"/>
+ <use x="64.982422" xlink:href="#DejaVuSans-101"/>
+ <use x="126.505859" xlink:href="#DejaVuSans-97"/>
+ <use x="187.785156" xlink:href="#DejaVuSans-100"/>
+ <use x="251.261719" xlink:href="#DejaVuSans-32"/>
+ <use x="283.048828" xlink:href="#DejaVuSans-51"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_4">
+ <g id="line2d_4">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="379.389947" xlink:href="#mb3344cd381" y="307.584"/>
+ </g>
+ </g>
+ <g id="text_4">
+ <!-- Read 4 -->
+ <g transform="translate(362.055572 322.182437)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 37.796875 64.3125
+L 12.890625 25.390625
+L 37.796875 25.390625
+z
+M 35.203125 72.90625
+L 47.609375 72.90625
+L 47.609375 25.390625
+L 58.015625 25.390625
+L 58.015625 17.1875
+L 47.609375 17.1875
+L 47.609375 0
+L 37.796875 0
+L 37.796875 17.1875
+L 4.890625 17.1875
+L 4.890625 26.703125
+z
+" id="DejaVuSans-52"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-82"/>
+ <use x="64.982422" xlink:href="#DejaVuSans-101"/>
+ <use x="126.505859" xlink:href="#DejaVuSans-97"/>
+ <use x="187.785156" xlink:href="#DejaVuSans-100"/>
+ <use x="251.261719" xlink:href="#DejaVuSans-32"/>
+ <use x="283.048828" xlink:href="#DejaVuSans-52"/>
+ </g>
+ </g>
+ </g>
+ </g>
+ <g id="matplotlib.axis_2">
+ <g id="ytick_1">
+ <g id="line2d_5">
+ <defs>
+ <path d="M 0 0
+L -3.5 0
+" id="mcadcbacc21" style="stroke:#000000;stroke-width:0.8;"/>
+ </defs>
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="57.6" xlink:href="#mcadcbacc21" y="307.584"/>
+ </g>
+ </g>
+ <g id="text_5">
+ <!-- 0 -->
+ <g transform="translate(44.2375 311.383219)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 31.78125 66.40625
+Q 24.171875 66.40625 20.328125 58.90625
+Q 16.5 51.421875 16.5 36.375
+Q 16.5 21.390625 20.328125 13.890625
+Q 24.171875 6.390625 31.78125 6.390625
+Q 39.453125 6.390625 43.28125 13.890625
+Q 47.125 21.390625 47.125 36.375
+Q 47.125 51.421875 43.28125 58.90625
+Q 39.453125 66.40625 31.78125 66.40625
+z
+M 31.78125 74.21875
+Q 44.046875 74.21875 50.515625 64.515625
+Q 56.984375 54.828125 56.984375 36.375
+Q 56.984375 17.96875 50.515625 8.265625
+Q 44.046875 -1.421875 31.78125 -1.421875
+Q 19.53125 -1.421875 13.0625 8.265625
+Q 6.59375 17.96875 6.59375 36.375
+Q 6.59375 54.828125 13.0625 64.515625
+Q 19.53125 74.21875 31.78125 74.21875
+z
+" id="DejaVuSans-48"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-48"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_2">
+ <g id="line2d_6">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="57.6" xlink:href="#mcadcbacc21" y="250.949363"/>
+ </g>
+ </g>
+ <g id="text_6">
+ <!-- 200 -->
+ <g transform="translate(31.5125 254.748582)scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-50"/>
+ <use x="63.623047" xlink:href="#DejaVuSans-48"/>
+ <use x="127.246094" xlink:href="#DejaVuSans-48"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_3">
+ <g id="line2d_7">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="57.6" xlink:href="#mcadcbacc21" y="194.314726"/>
+ </g>
+ </g>
+ <g id="text_7">
+ <!-- 400 -->
+ <g transform="translate(31.5125 198.113945)scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-52"/>
+ <use x="63.623047" xlink:href="#DejaVuSans-48"/>
+ <use x="127.246094" xlink:href="#DejaVuSans-48"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_4">
+ <g id="line2d_8">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="57.6" xlink:href="#mcadcbacc21" y="137.680089"/>
+ </g>
+ </g>
+ <g id="text_8">
+ <!-- 600 -->
+ <g transform="translate(31.5125 141.479308)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 33.015625 40.375
+Q 26.375 40.375 22.484375 35.828125
+Q 18.609375 31.296875 18.609375 23.390625
+Q 18.609375 15.53125 22.484375 10.953125
+Q 26.375 6.390625 33.015625 6.390625
+Q 39.65625 6.390625 43.53125 10.953125
+Q 47.40625 15.53125 47.40625 23.390625
+Q 47.40625 31.296875 43.53125 35.828125
+Q 39.65625 40.375 33.015625 40.375
+z
+M 52.59375 71.296875
+L 52.59375 62.3125
+Q 48.875 64.0625 45.09375 64.984375
+Q 41.3125 65.921875 37.59375 65.921875
+Q 27.828125 65.921875 22.671875 59.328125
+Q 17.53125 52.734375 16.796875 39.40625
+Q 19.671875 43.65625 24.015625 45.921875
+Q 28.375 48.1875 33.59375 48.1875
+Q 44.578125 48.1875 50.953125 41.515625
+Q 57.328125 34.859375 57.328125 23.390625
+Q 57.328125 12.15625 50.6875 5.359375
+Q 44.046875 -1.421875 33.015625 -1.421875
+Q 20.359375 -1.421875 13.671875 8.265625
+Q 6.984375 17.96875 6.984375 36.375
+Q 6.984375 53.65625 15.1875 63.9375
+Q 23.390625 74.21875 37.203125 74.21875
+Q 40.921875 74.21875 44.703125 73.484375
+Q 48.484375 72.75 52.59375 71.296875
+z
+" id="DejaVuSans-54"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-54"/>
+ <use x="63.623047" xlink:href="#DejaVuSans-48"/>
+ <use x="127.246094" xlink:href="#DejaVuSans-48"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_5">
+ <g id="line2d_9">
+ <g>
+ <use style="stroke:#000000;stroke-width:0.8;" x="57.6" xlink:href="#mcadcbacc21" y="81.045453"/>
+ </g>
+ </g>
+ <g id="text_9">
+ <!-- 800 -->
+ <g transform="translate(31.5125 84.844671)scale(0.1 -0.1)">
+ <defs>
+ <path d="M 31.78125 34.625
+Q 24.75 34.625 20.71875 30.859375
+Q 16.703125 27.09375 16.703125 20.515625
+Q 16.703125 13.921875 20.71875 10.15625
+Q 24.75 6.390625 31.78125 6.390625
+Q 38.8125 6.390625 42.859375 10.171875
+Q 46.921875 13.96875 46.921875 20.515625
+Q 46.921875 27.09375 42.890625 30.859375
+Q 38.875 34.625 31.78125 34.625
+z
+M 21.921875 38.8125
+Q 15.578125 40.375 12.03125 44.71875
+Q 8.5 49.078125 8.5 55.328125
+Q 8.5 64.0625 14.71875 69.140625
+Q 20.953125 74.21875 31.78125 74.21875
+Q 42.671875 74.21875 48.875 69.140625
+Q 55.078125 64.0625 55.078125 55.328125
+Q 55.078125 49.078125 51.53125 44.71875
+Q 48 40.375 41.703125 38.8125
+Q 48.828125 37.15625 52.796875 32.3125
+Q 56.78125 27.484375 56.78125 20.515625
+Q 56.78125 9.90625 50.3125 4.234375
+Q 43.84375 -1.421875 31.78125 -1.421875
+Q 19.734375 -1.421875 13.25 4.234375
+Q 6.78125 9.90625 6.78125 20.515625
+Q 6.78125 27.484375 10.78125 32.3125
+Q 14.796875 37.15625 21.921875 38.8125
+z
+M 18.3125 54.390625
+Q 18.3125 48.734375 21.84375 45.5625
+Q 25.390625 42.390625 31.78125 42.390625
+Q 38.140625 42.390625 41.71875 45.5625
+Q 45.3125 48.734375 45.3125 54.390625
+Q 45.3125 60.0625 41.71875 63.234375
+Q 38.140625 66.40625 31.78125 66.40625
+Q 25.390625 66.40625 21.84375 63.234375
+Q 18.3125 60.0625 18.3125 54.390625
+z
+" id="DejaVuSans-56"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-56"/>
+ <use x="63.623047" xlink:href="#DejaVuSans-48"/>
+ <use x="127.246094" xlink:href="#DejaVuSans-48"/>
+ </g>
+ </g>
+ </g>
+ </g>
+ <g id="patch_15">
+ <path d="M 57.6 307.584
+L 57.6 41.472
+" style="fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;stroke-width:0.8;"/>
+ </g>
+ <g id="patch_16">
+ <path d="M 414.72 307.584
+L 414.72 41.472
+" style="fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;stroke-width:0.8;"/>
+ </g>
+ <g id="patch_17">
+ <path d="M 57.6 307.584
+L 414.72 307.584
+" style="fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;stroke-width:0.8;"/>
+ </g>
+ <g id="patch_18">
+ <path d="M 57.6 41.472
+L 414.72 41.472
+" style="fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;stroke-width:0.8;"/>
+ </g>
+ <g id="text_10">
+ <!-- Counts for GENE3 -->
+ <g transform="translate(182.614688 35.472)scale(0.12 -0.12)">
+ <defs>
+ <path d="M 64.40625 67.28125
+L 64.40625 56.890625
+Q 59.421875 61.53125 53.78125 63.8125
+Q 48.140625 66.109375 41.796875 66.109375
+Q 29.296875 66.109375 22.65625 58.46875
+Q 16.015625 50.828125 16.015625 36.375
+Q 16.015625 21.96875 22.65625 14.328125
+Q 29.296875 6.6875 41.796875 6.6875
+Q 48.140625 6.6875 53.78125 8.984375
+Q 59.421875 11.28125 64.40625 15.921875
+L 64.40625 5.609375
+Q 59.234375 2.09375 53.4375 0.328125
+Q 47.65625 -1.421875 41.21875 -1.421875
+Q 24.65625 -1.421875 15.125 8.703125
+Q 5.609375 18.84375 5.609375 36.375
+Q 5.609375 53.953125 15.125 64.078125
+Q 24.65625 74.21875 41.21875 74.21875
+Q 47.75 74.21875 53.53125 72.484375
+Q 59.328125 70.75 64.40625 67.28125
+z
+" id="DejaVuSans-67"/>
+ <path d="M 30.609375 48.390625
+Q 23.390625 48.390625 19.1875 42.75
+Q 14.984375 37.109375 14.984375 27.296875
+Q 14.984375 17.484375 19.15625 11.84375
+Q 23.34375 6.203125 30.609375 6.203125
+Q 37.796875 6.203125 41.984375 11.859375
+Q 46.1875 17.53125 46.1875 27.296875
+Q 46.1875 37.015625 41.984375 42.703125
+Q 37.796875 48.390625 30.609375 48.390625
+z
+M 30.609375 56
+Q 42.328125 56 49.015625 48.375
+Q 55.71875 40.765625 55.71875 27.296875
+Q 55.71875 13.875 49.015625 6.21875
+Q 42.328125 -1.421875 30.609375 -1.421875
+Q 18.84375 -1.421875 12.171875 6.21875
+Q 5.515625 13.875 5.515625 27.296875
+Q 5.515625 40.765625 12.171875 48.375
+Q 18.84375 56 30.609375 56
+z
+" id="DejaVuSans-111"/>
+ <path d="M 8.5 21.578125
+L 8.5 54.6875
+L 17.484375 54.6875
+L 17.484375 21.921875
+Q 17.484375 14.15625 20.5 10.265625
+Q 23.53125 6.390625 29.59375 6.390625
+Q 36.859375 6.390625 41.078125 11.03125
+Q 45.3125 15.671875 45.3125 23.6875
+L 45.3125 54.6875
+L 54.296875 54.6875
+L 54.296875 0
+L 45.3125 0
+L 45.3125 8.40625
+Q 42.046875 3.421875 37.71875 1
+Q 33.40625 -1.421875 27.6875 -1.421875
+Q 18.265625 -1.421875 13.375 4.4375
+Q 8.5 10.296875 8.5 21.578125
+z
+M 31.109375 56
+z
+" id="DejaVuSans-117"/>
+ <path d="M 54.890625 33.015625
+L 54.890625 0
+L 45.90625 0
+L 45.90625 32.71875
+Q 45.90625 40.484375 42.875 44.328125
+Q 39.84375 48.1875 33.796875 48.1875
+Q 26.515625 48.1875 22.3125 43.546875
+Q 18.109375 38.921875 18.109375 30.90625
+L 18.109375 0
+L 9.078125 0
+L 9.078125 54.6875
+L 18.109375 54.6875
+L 18.109375 46.1875
+Q 21.34375 51.125 25.703125 53.5625
+Q 30.078125 56 35.796875 56
+Q 45.21875 56 50.046875 50.171875
+Q 54.890625 44.34375 54.890625 33.015625
+z
+" id="DejaVuSans-110"/>
+ <path d="M 18.3125 70.21875
+L 18.3125 54.6875
+L 36.8125 54.6875
+L 36.8125 47.703125
+L 18.3125 47.703125
+L 18.3125 18.015625
+Q 18.3125 11.328125 20.140625 9.421875
+Q 21.96875 7.515625 27.59375 7.515625
+L 36.8125 7.515625
+L 36.8125 0
+L 27.59375 0
+Q 17.1875 0 13.234375 3.875
+Q 9.28125 7.765625 9.28125 18.015625
+L 9.28125 47.703125
+L 2.6875 47.703125
+L 2.6875 54.6875
+L 9.28125 54.6875
+L 9.28125 70.21875
+z
+" id="DejaVuSans-116"/>
+ <path d="M 44.28125 53.078125
+L 44.28125 44.578125
+Q 40.484375 46.53125 36.375 47.5
+Q 32.28125 48.484375 27.875 48.484375
+Q 21.1875 48.484375 17.84375 46.4375
+Q 14.5 44.390625 14.5 40.28125
+Q 14.5 37.15625 16.890625 35.375
+Q 19.28125 33.59375 26.515625 31.984375
+L 29.59375 31.296875
+Q 39.15625 29.25 43.1875 25.515625
+Q 47.21875 21.78125 47.21875 15.09375
+Q 47.21875 7.46875 41.1875 3.015625
+Q 35.15625 -1.421875 24.609375 -1.421875
+Q 20.21875 -1.421875 15.453125 -0.5625
+Q 10.6875 0.296875 5.421875 2
+L 5.421875 11.28125
+Q 10.40625 8.6875 15.234375 7.390625
+Q 20.0625 6.109375 24.8125 6.109375
+Q 31.15625 6.109375 34.5625 8.28125
+Q 37.984375 10.453125 37.984375 14.40625
+Q 37.984375 18.0625 35.515625 20.015625
+Q 33.0625 21.96875 24.703125 23.78125
+L 21.578125 24.515625
+Q 13.234375 26.265625 9.515625 29.90625
+Q 5.8125 33.546875 5.8125 39.890625
+Q 5.8125 47.609375 11.28125 51.796875
+Q 16.75 56 26.8125 56
+Q 31.78125 56 36.171875 55.265625
+Q 40.578125 54.546875 44.28125 53.078125
+z
+" id="DejaVuSans-115"/>
+ <path d="M 37.109375 75.984375
+L 37.109375 68.5
+L 28.515625 68.5
+Q 23.6875 68.5 21.796875 66.546875
+Q 19.921875 64.59375 19.921875 59.515625
+L 19.921875 54.6875
+L 34.71875 54.6875
+L 34.71875 47.703125
+L 19.921875 47.703125
+L 19.921875 0
+L 10.890625 0
+L 10.890625 47.703125
+L 2.296875 47.703125
+L 2.296875 54.6875
+L 10.890625 54.6875
+L 10.890625 58.5
+Q 10.890625 67.625 15.140625 71.796875
+Q 19.390625 75.984375 28.609375 75.984375
+z
+" id="DejaVuSans-102"/>
+ <path d="M 41.109375 46.296875
+Q 39.59375 47.171875 37.8125 47.578125
+Q 36.03125 48 33.890625 48
+Q 26.265625 48 22.1875 43.046875
+Q 18.109375 38.09375 18.109375 28.8125
+L 18.109375 0
+L 9.078125 0
+L 9.078125 54.6875
+L 18.109375 54.6875
+L 18.109375 46.1875
+Q 20.953125 51.171875 25.484375 53.578125
+Q 30.03125 56 36.53125 56
+Q 37.453125 56 38.578125 55.875
+Q 39.703125 55.765625 41.0625 55.515625
+z
+" id="DejaVuSans-114"/>
+ <path d="M 59.515625 10.40625
+L 59.515625 29.984375
+L 43.40625 29.984375
+L 43.40625 38.09375
+L 69.28125 38.09375
+L 69.28125 6.78125
+Q 63.578125 2.734375 56.6875 0.65625
+Q 49.8125 -1.421875 42 -1.421875
+Q 24.90625 -1.421875 15.25 8.5625
+Q 5.609375 18.5625 5.609375 36.375
+Q 5.609375 54.25 15.25 64.234375
+Q 24.90625 74.21875 42 74.21875
+Q 49.125 74.21875 55.546875 72.453125
+Q 61.96875 70.703125 67.390625 67.28125
+L 67.390625 56.78125
+Q 61.921875 61.421875 55.765625 63.765625
+Q 49.609375 66.109375 42.828125 66.109375
+Q 29.4375 66.109375 22.71875 58.640625
+Q 16.015625 51.171875 16.015625 36.375
+Q 16.015625 21.625 22.71875 14.15625
+Q 29.4375 6.6875 42.828125 6.6875
+Q 48.046875 6.6875 52.140625 7.59375
+Q 56.25 8.5 59.515625 10.40625
+z
+" id="DejaVuSans-71"/>
+ <path d="M 9.8125 72.90625
+L 55.90625 72.90625
+L 55.90625 64.59375
+L 19.671875 64.59375
+L 19.671875 43.015625
+L 54.390625 43.015625
+L 54.390625 34.71875
+L 19.671875 34.71875
+L 19.671875 8.296875
+L 56.78125 8.296875
+L 56.78125 0
+L 9.8125 0
+z
+" id="DejaVuSans-69"/>
+ <path d="M 9.8125 72.90625
+L 23.09375 72.90625
+L 55.421875 11.921875
+L 55.421875 72.90625
+L 64.984375 72.90625
+L 64.984375 0
+L 51.703125 0
+L 19.390625 60.984375
+L 19.390625 0
+L 9.8125 0
+z
+" id="DejaVuSans-78"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-67"/>
+ <use x="69.824219" xlink:href="#DejaVuSans-111"/>
+ <use x="131.005859" xlink:href="#DejaVuSans-117"/>
+ <use x="194.384766" xlink:href="#DejaVuSans-110"/>
+ <use x="257.763672" xlink:href="#DejaVuSans-116"/>
+ <use x="296.972656" xlink:href="#DejaVuSans-115"/>
+ <use x="349.072266" xlink:href="#DejaVuSans-32"/>
+ <use x="380.859375" xlink:href="#DejaVuSans-102"/>
+ <use x="416.064453" xlink:href="#DejaVuSans-111"/>
+ <use x="477.246094" xlink:href="#DejaVuSans-114"/>
+ <use x="518.359375" xlink:href="#DejaVuSans-32"/>
+ <use x="550.146484" xlink:href="#DejaVuSans-71"/>
+ <use x="627.636719" xlink:href="#DejaVuSans-69"/>
+ <use x="690.820312" xlink:href="#DejaVuSans-78"/>
+ <use x="765.625" xlink:href="#DejaVuSans-69"/>
+ <use x="828.808594" xlink:href="#DejaVuSans-51"/>
+ </g>
+ </g>
+ </g>
+ </g>
+ <defs>
+ <clipPath id="p07942fdf52">
+ <rect height="266.112" width="357.12" x="57.6" y="41.472"/>
+ </clipPath>
+ </defs>
+</svg>
diff --git a/requirements.txt b/requirements.txt
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..6ccafc3f904ba0d6ffda0fdc2802e0d6a59a3832 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1 @@
+matplotlib
diff --git a/requirements_dev.txt b/requirements_dev.txt
index 6352bb595442a949b538aad7e88324dede15c7b9..1240dae7dc476182f595151f5ac823a9e2bdddf4 100644
--- a/requirements_dev.txt
+++ b/requirements_dev.txt
@@ -3,4 +3,5 @@ flake8
flake8-docstrings
mypy
pandas
-pytest
\ No newline at end of file
+pytest
+matplotlib
diff --git a/src/cli_plot_read_counts.py b/src/cli_plot_read_counts.py
new file mode 100644
index 0000000000000000000000000000000000000000..915075d191c1790267698d2bc5391567ca10aa70
--- /dev/null
+++ b/src/cli_plot_read_counts.py
@@ -0,0 +1,35 @@
+"""CLI for plot_read_counts function."""
+
+import argparse
+import logging
+
+from plot_read_counts import plot_read_counts
+
+
+def main():
+ r"""CLI for plot_read_counts.
+
+ This cli is used to access the functionality of plot_read_counts,
+ taking in a path of csv files, a gene ID, and an optional save
+ file name.
+
+ Typical example usage:
+
+ cli_plot_read_counts.py '../tests/resources' GENE1 '../test/PLSe1writeTarget.test'
+ """
+ parser = argparse.ArgumentParser(
+ description='number of transcripts to sample')
+ parser.add_argument('file_path', action='store',
+ type=str, help='path to gene count .csv files')
+ parser.add_argument('gene_id', action='store',
+ type=str, help='gene ID of which to plot counts')
+ argsin = parser.parse_args()
+
+ logging.basicConfig(format='[%(asctime)s: %(levelname)s] "%(module)s" %(message)s',
+ level=logging.INFO)
+
+ plot_read_counts(argsin.file_path, argsin.gene_id)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/src/plot_read_counts.py b/src/plot_read_counts.py
index c32d160f11cf6201741005cf99858577fd766265..31fae3c0f08f6332a56db557441f7cb775245a0b 100644
--- a/src/plot_read_counts.py
+++ b/src/plot_read_counts.py
@@ -3,19 +3,19 @@
import logging
from pathlib import Path
from typing import Union
+from datetime import datetime
+
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
-) -> bool:
+ dir_path: Union[str, Path],
+ gene_id: str
+) -> str:
"""Plots histogram of gene ID and read counts from .csv files.
- This function reads .csv files from a directory formatted
+ This function reads .csv files from a directory formatted
"GeneID, Counts" and plots a histogram of read counts for a
chosen geneID.
@@ -23,96 +23,126 @@ def plot_read_counts(
dir_path: Path of directory containing .csv files of read counts.
gene_id: Name of gene to plot.
+ Returns:
+ String representing path to .svg plot file.
+
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
+ FileNotFoundError: File path does not contain any .csv files.
+ KeyError: A file containing an entry of the chosen gene is missing
+ a count entry for it.
+ TypeError: A file containing an entry of the chosen gene has a count
+ that is not a number.
"""
+ LOGGER = logging.getLogger(__name__)
+
+ dir_path = Path(dir_path)
+
+ if not dir_path.exists():
+ raise ValueError("Invalid Path")
+
+ if not isinstance(gene_id, str):
+ 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
+ file_paths = list(dir_path.glob("*.csv"))
+ file_paths.sort()
+
+ if len(file_paths) == 0:
+ raise FileNotFoundError("No .csv files found in chosen directory")
+
+ gene_count_dict = {}
+ file_counter = 0
+
+ LOGGER.info("Running with %s and gene %s" % (dir_path, gene_id))
+
+ for file_path in file_paths:
+ # read in csv here via pandas
+ df_read_counts = pandas.read_csv(str(file_path),
+ header=None, names=['Gene', 'Count'])
+
+ # confirm that gene entry exists for edge case where count may be deleted
+ confirm_gene_presence = df_read_counts.loc[df_read_counts.Gene == gene_id,
+ 'Gene'].tolist()
+
+ # find gene_id within dataframe
+ gene_count = df_read_counts.loc[df_read_counts.Gene == gene_id,
+ 'Count'].tolist()
+
+ # # If an entry exists for the gene, but the count is missing, a KeyError is thrown
+ if confirm_gene_presence and not gene_count:
+ raise KeyError("%s.csv contains an entry for %s, but is "
+ "missing a count." % (file_path.stem, gene_id))
+
+ # If an entry exists for the gene, but the count is not a number, a TypeError is thrown
+ if confirm_gene_presence:
+ try:
+ for i, count in enumerate(gene_count):
+ gene_count[i] = int(count)
+
+ except ValueError:
+ raise TypeError("%s.csv contains an entry for %s, but is "
+ "not a number." % (file_path.stem, gene_id))
+
+ if not gene_count:
+ LOGGER.warning(f"File {file_path.stem}.csv does not contain an entry for {gene_id}, "
+ "this is interpreted as 0")
+ gene_count = [0]
+
+ if len(gene_count) > 1:
+ LOGGER.warning(
+ "%s.csv contains more than one entry for chosen gene - these will be summed"
+ % (file_path.stem)
+ )
+
+ file_counter += 1
+ # Uncomment to use file name as label -> does not autoscale pyplot
+ # gene_count_dict[file_path.stem] = sum(gene_count)
+ gene_count_dict[f"Read {file_counter}"] = sum(gene_count)
+
+ LOGGER.info('Read complete from %s files' % (file_counter))
+
+ # 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, width=0.4)
+ plt.title('Counts for %s' % (gene_id))
+ plt.autoscale(axis='both')
+ plot_file_path = Path(f"{Path.cwd()}/plots/{get_file_name()}.svg")
+ plt.savefig(plot_file_path)
+ LOGGER.info(f"Plot successfully generated and saved at {plot_file_path}")
+
+ return(plot_file_path)
+
+
+def get_file_name() -> str:
+ """Helper function to determine output filename."""
+ datetime_str = datetime.now().strftime("%y%m%d")
+ file_name_index = 1
+ plot_file_name = f"reads_plot_{datetime_str}_{file_name_index}"
+ # while(Path.exists(Path(f"{Path.cwd()}/plots/{plot_file_name}"))):
+ # file_name_index += 1
+ # plot_file_name = f"reads_plot_{datetime_str}_{file_name_index}"
+ return plot_file_name
+
+
+def main():
+ """Prompts user in cl to enter path and gene to plot."""
# 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()
- return True
+ # Prompt user for input
+ csv_path = input("\nPlease enter a path: ")
+ gene_of_interest = input("\nPlease enter a gene name to plot: ")
+ plot_read_counts(csv_path, gene_of_interest)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tests/resources/Transcript4.csv b/tests/resources/Transcript4.csv
deleted file mode 100644
index ff000bdfaa5e13bfc431addf9f8be3a9c1a1fe99..0000000000000000000000000000000000000000
--- a/tests/resources/Transcript4.csv
+++ /dev/null
@@ -1,19 +0,0 @@
-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
deleted file mode 100644
index 34613ca7b1bd45581fc5c22affd989f5034f5cff..0000000000000000000000000000000000000000
--- a/tests/resources/Transcript5.csv
+++ /dev/null
@@ -1,19 +0,0 @@
-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
deleted file mode 100644
index 794d1c1005fe5591f2bedca91087d3cf6f008ec2..0000000000000000000000000000000000000000
--- a/tests/resources/Transcript6.csv
+++ /dev/null
@@ -1,19 +0,0 @@
-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
deleted file mode 100644
index 72cb6bffa9a8786e7d0ae0fdcee0eeb9740cc9a1..0000000000000000000000000000000000000000
--- a/tests/resources/Transcript7negctrl.csv
+++ /dev/null
@@ -1,8 +0,0 @@
-Random,Data,for
-This,is,a
-negative,control,test
-some,numbers,
-234,,
-,432,
-,,
-32,,
diff --git a/tests/resources/Transcript_read_counts_invalid.csv b/tests/resources/Transcript_read_counts_invalid.csv
new file mode 100644
index 0000000000000000000000000000000000000000..6f947976489e7c1d7a381f99a31d091708025843
--- /dev/null
+++ b/tests/resources/Transcript_read_counts_invalid.csv
@@ -0,0 +1,2 @@
+Improper,Data
+GENE6,nan
diff --git a/tests/resources/Transcript3.csv b/tests/resources/Transcript_read_counts_missing-gene7.csv
similarity index 96%
rename from tests/resources/Transcript3.csv
rename to tests/resources/Transcript_read_counts_missing-gene7.csv
index 2473e6708c09eb374563f0215f2edbbb9ea64785..a6d95f3bb891a4fee14cdfb3ef6446239d82c74c 100644
--- a/tests/resources/Transcript3.csv
+++ b/tests/resources/Transcript_read_counts_missing-gene7.csv
@@ -4,7 +4,7 @@ GENE3,859
GENE4,174
GENE5,525
GENE6,606
-,
+GENE7,
GENE8,910
GENE9,194
GENE10,415
diff --git a/tests/resources/Transcript1.csv b/tests/resources/Transcript_read_counts_valid.csv
similarity index 91%
rename from tests/resources/Transcript1.csv
rename to tests/resources/Transcript_read_counts_valid.csv
index 4ae4a987b2287f1265121692e0dbd873e9ebc0e5..798fa196c9dd54278cc4d06433c29ae098ec9e3d 100644
--- a/tests/resources/Transcript1.csv
+++ b/tests/resources/Transcript_read_counts_valid.csv
@@ -1,7 +1,7 @@
-GENE1,92
-GENE2,13
-GENE3,73
-GENE4,83
-GENE5,32
-GENE6,136
+GENE1,92
+GENE2,13
+GENE3,73
+GENE4,83
+GENE5,32
+GENE6,136
GENE7,36
\ No newline at end of file
diff --git a/tests/resources/Transcript2.csv b/tests/resources/Transcript_read_counts_valid2.csv
similarity index 100%
rename from tests/resources/Transcript2.csv
rename to tests/resources/Transcript_read_counts_valid2.csv
diff --git a/tests/test_plot_read_counts.py b/tests/test_plot_read_counts.py
index 293b450183c97f9aa14b9e101674628d03edc6af..8ca0e9de5cf1300dc3d557a600374600fe3d693d 100644
--- a/tests/test_plot_read_counts.py
+++ b/tests/test_plot_read_counts.py
@@ -12,11 +12,10 @@ class TestPlotReadCounts ():
"dir_path, gene_id, expected",
[
('a', 'GENE1', ValueError),
- ('Path.home()', 5, TypeError),
- (None, None, ValueError),
- ('Path.home()', 'GENE1', AttributeError),
- (Path(str(Path.parent())+"/tests/resources/"), 'GENE25', ValueError),
-
+ (Path(f"{Path.cwd()}/tests/"), 'GENE1', FileNotFoundError),
+ (Path(f"{Path.cwd()}/tests/resources/"), 5, TypeError),
+ (Path(f"{Path.cwd()}/tests/resources/"), 'GENE6', TypeError),
+ (Path(f"{Path.cwd()}/tests/resources/"), 'GENE7', TypeError),
]
)
def test_invalid_input(self, dir_path, gene_id, expected):
@@ -25,13 +24,13 @@ class TestPlotReadCounts ():
plot_read_counts(dir_path, gene_id)
@pytest.mark.parametrize(
- "dir_path, gene_id, expected",
+ "dir_path, gene_id",
[
- (Path(str(Path.parent())+"/tests/resources/"), 'GENE1', True),
- (Path(str(Path.parent())+"/tests/resources/"), 'GENE1', True),
- (Path(str(Path.parent())+"/tests/resources/"), 'GENE7', True),
+ (Path(f"{Path.cwd()}/tests/resources/"), 'GENE1'),
+ (Path(f"{Path.cwd()}/tests/resources/"), 'GENE2'),
+ (Path(f"{Path.cwd()}/tests/resources/"), 'GENE3'),
]
)
- def validate_input(self, dir_path, gene_id):
+ def test_valid_input(self, dir_path, gene_id):
"""Tests valid input with return value boolean."""
- assert plot_read_counts(dir_path, gene_id) is True
+ assert Path.exists(plot_read_counts(dir_path, gene_id))