Merge branch '4.0.0' of github.com:deeptools/deepTools into filtering

Author: WardDeb

docs/content/advanced_features.rst

@@ -9,5 +9,4 @@ Some of the features of deepTools are not self-explanatory. Below, we provide li
  * :doc:`feature/unscaled_regions`
  * :doc:`feature/read_offsets`
  * :doc:`feature/plotFingerprint_QC_metrics`
- * :doc:`feature/plotly`
  * :doc:`feature/effectiveGenomeSize`

docs/content/changelog.rst

@@ -1,49 +1,50 @@
 Changes in deepTools4.0
 =======================
 
-# Changes
-
-## bamCoverage
-
- - --no_collapse flag to not merge bins with equal coverage values together.
- 
-## computeMatrix
-
- - --sortRegions 'no' option no longer exists
- - Sorting ascend / descend no longer has subsorting by position.
- - --quiet / -q option no longer exists.
- - bed files in computeMatrix no longer support '#' to define groups.
- - 'chromosome matching' i.e. chr1 <-> 1, chrMT <-> MT is no longer performed.
-
-## normalization
-
- - Exactscaling is no longer an option, it's always performed.
-
-## alignmentSieve
-
-- options label, smartLabels, genomeChunkLength are removed.
-- ignoreDuplicates is removed, and (if wanted) should be set by the SamFlagExclude setting.
-
-# Testing
+Plotting
+--------
+
+* Plots in general:
+    - Removed Plotly for all graphics.
+	- Optional ggplot theme (--ggplot).
+	- Using standard Matplotlib color scheme.
+
+* plotHeatmap and plotProfile:
+	- Adjusted the legend position to be outside the plot area, preventing overlap with the subplots.
+	- Split and wrapped longer sample names to avoid overlap with other labels.
+	- Eliminated overlapping x and y-axis ticks for improved readability.
+	- Removed the file extensions from input files when using them as labels in the plots.
+
+* plotEnrichment:
+	- Added spacing between bars in bar plots for improved visual clarity.
+	- Retained only sample names, when provided with the complete file path and name.
+
+* plotPCA:
+    - Using scikit-learn for computing PCA.
+	- New option to add labels for each point (--addLabels).
+	- Expander for colors and markers, for example ``--colors red:3 blue:3`` is expanded as ``[red, red, red, blue, blue, blue]``.
+	- Scree plot is showing lines for individual and accumulated variation.
+	- Points are by default rainbow colored circles.
+
+Core
+----
+
+* bamCoverage
+    - --no_collapse flag to not merge bins with equal coverage values together.
 
-## computeMatrix
- - referencePoint: TSS, center, TES
- - sortRegions: descend, ascend, keep
- - sortUsing: mean, median, max, min, sum, region_length
- - averageTypeBins: mean, median, min, max ,std, sum
- - skipZeros
- - duplicate renaming _r1, _r2, ...
- - GTF, BED3, BED6, BED12, mixedBED (?)
- - scaleRegions, un5, un3, regionbodylength, metagene
-
- ## alignmentSieve
-
- - unmapped reads to unfiltered_out
-
-## multiBamSummary
- - npz output has labels encoded as u8s, no longer strings.
-
-# Todo
-
-- AlignmentSieve: Shift, Bed, Optimization.
-- bamCoverage / bamCompare: filtering, extend.
+* computeMatrix
+    - --sortRegions 'no' option no longer exists
+    - Sorting ascend / descend no longer has subsorting by position.
+    - --quiet / -q option no longer exists.
+    - bed files in computeMatrix no longer support '#' to define groups.
+    - 'chromosome matching' i.e. chr1 <-> 1, chrMT <-> MT is no longer performed.
+
+* normalization
+    - Exactscaling is no longer an option, it's always performed.
+
+* alignmentSieve
+    - options label, smartLabels, genomeChunkLength are removed.
+    - ignoreDuplicates is removed, and (if wanted) should be set by the SamFlagExclude setting.
+
+Testing
+-------

pydeeptools/deeptools/bamPEFragmentSize.py

@@ -9,18 +9,13 @@
 matplotlib.use('Agg')
 matplotlib.rcParams['pdf.fonttype'] = 42
 matplotlib.rcParams['svg.fonttype'] = 'none'
-from deeptools import cm  # noqa: F401
 import matplotlib.pyplot as plt
 
-import plotly.offline as py
-import plotly.graph_objs as go
-
 # own tools
 from deeptools.parserCommon import writableFile
 from deeptools.getFragmentAndReadSize import get_read_and_fragment_length
 from importlib.metadata import version
 
-
 def parse_arguments():
     parser = argparse.ArgumentParser(
         description='This tool calculates the fragment sizes for read pairs given a BAM file from paired-end sequencing.'
@@ -51,8 +46,11 @@ def parse_arguments():
                         'ending. The available options are: png, '
                         'eps, pdf, svg and plotly.',
                         default=None,
-                        choices=['png', 'pdf', 'svg', 'eps', 'plotly'])
-
+                        choices=['png', 'pdf', 'svg', 'eps'])
+    parser.add_argument('--ggplot',
+                        help='Use ggplot theme for figures',
+                        action='store_true')
+    
     parser.add_argument('--numberOfProcessors', '-p',
                         help='Number of processors to use. The default is '
                         'to use 1. (Default: %(default)s)',
@@ -311,6 +309,9 @@ def main(args=None):
     if args.table is not None:
         printTable(args, fraglengths, readlengths)
 
+    if args.ggplot:
+        plt.style.use('ggplot')
+
     if args.histogram:
         if args.samplesLabel:
             if len(args.bamfiles) != len(args.samplesLabel):
@@ -331,38 +332,18 @@ def main(args=None):
             else:
                 maxVal = d['mean'] * 2
 
-            if args.plotFileFormat == 'plotly':
-                trace = go.Histogram(x=d['lengths'],
-                                     histnorm='probability',
-                                     opacity=0.5,
-                                     name=labels[i],
-                                     nbinsx=100,
-                                     xbins=dict(start=d['min'], end=maxVal))
-                data.append(trace)
-            else:
-                plt.bar(d['lengths'][1][:-1], height=d['lengths'][0],
-                        width=d['lengths'][1][1:] - d['lengths'][1][:-1],
-                        align='edge', log=args.logScale,
-                        alpha=0.5, label=labels[i])
+            plt.bar(d['lengths'][1][:-1], height=d['lengths'][0],
+                    width=d['lengths'][1][1:] - d['lengths'][1][:-1],
+                    align='edge', log=args.logScale,
+                    alpha=0.5, label=labels[i])
             i += 1
 
-        if args.plotFileFormat == 'plotly':
-            fig = go.Figure()
-            fig.add_traces(data)
-            fig['layout']['yaxis1'].update(title='Frequency')
-            fig['layout']['xaxis1'].update(title='Fragment Length')
-            fig['layout'].update(title=args.plotTitle)
-            fig['layout'].update(showlegend=True)
-            if args.logScale:
-                fig['layout']['yaxis1'].update(type='log')
-            py.plot(fig, filename=args.histogram, auto_open=False)
-        else:
-            plt.xlabel('Fragment Length')
-            plt.ylabel('Frequency')
-            plt.legend(loc='upper right')
-            plt.title(args.plotTitle)
-            plt.savefig(args.histogram, bbox_inches=0, format=args.plotFileFormat)
-            plt.close()
+        plt.xlabel('Fragment Length')
+        plt.ylabel('Frequency')
+        plt.legend(loc='upper right')
+        plt.title(args.plotTitle)
+        plt.savefig(args.histogram, bbox_inches=0, format=args.plotFileFormat)
+        plt.close()
 
 
 if __name__ == "__main__":