Merge pull request #11 from sbslee/1.7.0-dev

1.7.0 dev

Author: sbslee

CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## 1.7.0
+
+* Added a new command called `count-reads` which counts the number of sequence reads from FASTQ.
+* Updated the `summarize` command.
+* Updated the following methods:
+    * `taxa_abundance_box_plot()`
+    * `taxa_abundance_bar_plot()`
+    * `distance_matrix_plot()`
+    * `ordinate()`
+    * `barplot()`
+* See [#10](https://github.com/sbslee/dokdo/issues/10) for more details.
+
 ## 1.6.0
 
 * Added a new method called `pname()` which returns a prettified taxon name.

dokdo/__main__.py

@@ -172,7 +172,8 @@ def main():
                      "the following semantic types: "
                      "FeatureTable[Frequency], "
                      "FeatureTable[RelativeFrequency], "
-                     "FeatureData[Sequence], FeatureData[AlignedSequence].")
+                     "FeatureData[Sequence], FeatureData[AlignedSequence], "
+                     "FeatureData[Taxonomy], DistanceMatrix.")
     )
 
     summarize_parser._optionals.title = "Arguments"
@@ -288,6 +289,43 @@ def main():
         help=help_msg
     )
 
+    count_reads_parser = subparsers.add_parser(
+        "count-reads",
+        add_help=False,
+        help="Count the number of sequence reads from FASTQ.",
+        description=("Count the number of sequence reads from FASTQ. "
+                     "This command outputs two columns corresponding "
+                     "to the file name and read count, respectively.")
+    )
+
+    count_reads_parser._optionals.title = "Arguments"
+
+    count_reads_parser.add_argument(
+        "-i",
+        "--fastq-path",
+        metavar="PATH",
+        required=True,
+        help=("Path to the input FASTQ file or to the input "
+              "directory containing FASTQ files. [required]")
+    )
+
+    count_reads_parser.add_argument(
+        "-d",
+        "--delimiter",
+        metavar="TEXT",
+        default="\t",
+        help=("Delimiter used to separate the file name and read "
+              "count. [default: '\\t']")
+    )
+
+    count_reads_parser.add_argument(
+        "-h",
+        "--help",
+        action="help",
+        default=argparse.SUPPRESS,
+        help=help_msg
+    )
+
     args = parser.parse_args()
     command = args.command
     delattr(args, "command")

dokdo/api/__init__.py

@@ -4,6 +4,7 @@
 from .num2sig import num2sig
 from .wilcoxon import wilcoxon
 from .mannwhitneyu import mannwhitneyu
+from .count_reads_one_file import count_reads_one_file
 
 from .read_quality_plot import read_quality_plot
 from .denoising_stats_plot import denoising_stats_plot
@@ -32,4 +33,4 @@
            'beta_scree_plot', 'beta_parallel_plot', 'distance_matrix_plot',
            'taxa_abundance_bar_plot', 'taxa_abundance_box_plot',
            'ancom_volcano_plot', 'addsig', 'regplot', 'addbiplot',
-           'barplot', 'ordinate', 'pname', 'get_mf']
+           'barplot', 'ordinate', 'pname', 'get_mf', 'count_reads_one_file']

dokdo/api/barplot.py

@@ -151,9 +151,9 @@ def barplot(barplot_file,
 
     taxa_abundance_bar_plot(barplot_file,
                             ax=axbig,
+                            legend_short=True,
                             artist_kwargs={'legend_only': True,
                                            'legend_loc': 'center left',
-                                           'legend_short': True,
                                            **_artist_kwargs},
                             **plot_kwargs)
 

dokdo/api/common.py

@@ -23,7 +23,7 @@
 from qiime2 import Artifact
 from qiime2 import Metadata
 from qiime2 import Visualization
-
+import dokdo
 
 
 
@@ -187,7 +187,6 @@ def _artist(ax,
             legend_loc='best',
             legend_ncol=1,
             legend_labels=None,
-            legend_short=False,
             remove_duplicates=False,
             legend_only=False,
             legend_fontsize=None,
@@ -392,9 +391,6 @@ def _artist(ax,
     # Control the figure legend.
     h, l = ax.get_legend_handles_labels()
 
-    if legend_short:
-        l = [_pretty_taxa(x) for x in l]
-
     if legend_labels:
         a = len(legend_labels)
         b = len(l)

dokdo/api/count_reads_one_file.py

@@ -0,0 +1,20 @@
+import gzip
+
+def count_reads_one_file(fastq_file):
+    """Count the number of sequence reads from a single FASTQ file.
+
+    Parameters
+    ----------
+    fastq_file : str
+        Path to the FASTQ file.
+
+    Returns
+    -------
+    int
+        Number of sequence reads in the FASTQ file.
+    """
+    n = 0
+    with gzip.open(fastq_file, 'rb') as f:
+        for line in f:
+            n += 1
+    return int(n / 4)

dokdo/api/distance_matrix_plot.py

@@ -3,19 +3,22 @@
 import pandas as pd
 import skbio as sb
 import matplotlib.pyplot as plt
+from qiime2 import Artifact
 
 def distance_matrix_plot(distance_matrix,
                          bins=100,
                          pairs=None,
                          ax=None,
                          figsize=None,
+                         density=False,
                          artist_kwargs=None):
     """Create a histogram from a distance matrix.
 
     Parameters
     ----------
     distance_matrix : str or qiime2.Artifact
-        Artifact file or object from the q2-diversity-lib plugin.
+        Artifact file or object with the semantic type
+        `DistanceMatrix`.
     bins : int, optional
         Number of bins to be displayed.
     pairs : list, optional
@@ -24,31 +27,28 @@ def distance_matrix_plot(distance_matrix,
         Axes object to draw the plot onto, otherwise uses the current Axes.
     figsize : tuple, optional
         Width, height in inches. Format: (float, float).
+    density : bool, default: False
+        If True, draw and return a probability density.
     artist_kwargs : dict, optional
         Keyword arguments passed down to the _artist() method.
 
     Returns
     -------
     matplotlib.axes.Axes
         Axes object with the plot drawn onto it.
-
-    Notes
-    -----
-    Example usage of the q2-diversity-lib plugin:
-        CLI -> qiime diversity-lib jaccard [OPTIONS]
-        API -> from qiime2.plugins.diversity_lib.methods import jaccard
     """
-    with tempfile.TemporaryDirectory() as t:
-        _parse_input(distance_matrix, t)
-        df = pd.read_table(f'{t}/distance-matrix.tsv', index_col=0)
+    if isinstance(distance_matrix, str):
+        _distance_matrix = Artifact.load(distance_matrix)
+    else:
+        _distance_matrix = distance_matrix
 
-    dist = sb.stats.distance.DistanceMatrix(df, ids=df.columns)
+    dist = _distance_matrix.view(sb.DistanceMatrix)
     cdist = dist.condensed_form()
 
     if ax is None:
         fig, ax = plt.subplots(figsize=figsize)
 
-    ax.hist(cdist, bins=bins)
+    ax.hist(cdist, bins=bins, density=density)
 
     # https://stackoverflow.com/a/36867493/7481899
     def square_to_condensed(i, j, n):

dokdo/api/ordinate.py

@@ -5,14 +5,8 @@
 from qiime2.plugins import diversity
 import pandas as pd
 
-def ordinate(table,
-             metadata=None,
-             where=None,
-             metric='jaccard',
-             sampling_depth=-1,
-             phylogeny=None,
-             number_of_dimensions=None,
-             biplot=False):
+def ordinate(table, metadata=None, metric='jaccard', sampling_depth=-1,
+             phylogeny=None, number_of_dimensions=None, biplot=False):
     """Perform ordination using principal coordinate analysis (PCoA).
 
     This method wraps multiple QIIME 2 methods to perform ordination and
@@ -22,17 +16,16 @@ def ordinate(table,
     rarefying of the feature table (if requested), computes distance matrix,
     and then runs PCoA.
 
-    By default, the method returns PCoAResults. For creating a biplot, make
-    sure to use `biplot=True` which returns PCoAResults % Properties('biplot').
+    By default, the method returns PCoAResults. For creating a biplot,
+    use `biplot=True` which returns PCoAResults % Properties('biplot').
 
     Parameters
     ----------
     table : str or qiime2.Artifact
         Artifact file or object corresponding to FeatureTable[Frequency].
     metadata : str or qiime2.Metadata, optional
-        Metadata file or object.
-    where : str, optional
-        SQLite WHERE clause specifying sample metadata criteria.
+        Metadata file or object. All samples in 'metadata' that are also in
+        the feature table will be retained.
     metric : str, default: 'jaccard'
         Metric used for distance matrix computation ('jaccard',
         'bray_curtis', 'unweighted_unifrac', or 'weighted_unifrac').
@@ -71,21 +64,14 @@ def ordinate(table,
     else:
         raise TypeError(f"Incorrect feature table type: {type(table)}")
 
-    # Perform sample filtration.
-    if where:
-        if metadata is None:
-            m = "To use 'where' argument, you must provide metadata"
-            raise ValueError(m)
-        elif isinstance(metadata, str):
-            _metadata = Metadata.load(metadata)
-        elif isinstance(metadata, qiime2.Metadata):
+    # If metadata is provided, perform sample filtration.
+    if metadata is not None:
+        if isinstance(metadata, Metadata):
             _metadata = metadata
         else:
-            raise TypeError(f"Incorrect metadata type: {type(metadata)}")
-
-        filter_result = feature_table.methods.filter_samples(
-            table=table, metadata=_metadata, where=where)
-        _table = filter_result.filtered_table
+            _metadata = Metadata.load(metadata)
+        _table = feature_table.methods.filter_samples(
+            table=table, metadata=_metadata).filtered_table
     else:
         _table = table
 

dokdo/api/taxa_abundance_bar_plot.py

@@ -28,6 +28,7 @@ def taxa_abundance_bar_plot(taxa,
                             sort_by_mean3=True,
                             show_others=True,
                             cmap_name='Accent',
+                            legend_short=False,
                             artist_kwargs=None):
     """Create a taxa abundance plot.
 
@@ -92,6 +93,8 @@ def taxa_abundance_bar_plot(taxa,
         Include the 'Others' category.
     cmap_name : str, default: 'Accent'
         Name of the colormap passed to `matplotlib.cm.get_cmap()`.
+    legend_short : bool, default: False
+        If true, only display the smallest taxa rank in the legend.
     artist_kwargs : dict, optional
         Keyword arguments passed down to the _artist() method.
 
@@ -206,17 +209,20 @@ def taxa_abundance_bar_plot(taxa,
 
     df = df * 100
 
+    # If provided, output the dataframe as a .csv file.
+    if csv_file is not None:
+        df.to_csv(csv_file)
+
+    if legend_short:
+        df.columns = [dokdo.pname(x) for x in df.columns]
+
     df.plot.bar(stacked=True,
                 legend=False,
                 ax=ax,
                 width=width,
                 color=c,
                 linewidth=0)
 
-    # If provided, output the dataframe as a .csv file.
-    if csv_file is not None:
-        df.to_csv(csv_file)
-
     if label_columns is not None:
         f = lambda row: ' : '.join(row.values.astype(str))
         xticklabels = mf[label_columns].apply(f, axis=1).tolist()

dokdo/api/taxa_abundance_box_plot.py

@@ -1,5 +1,5 @@
 import tempfile
-from .common import (_parse_input, _artist, _pretty_taxa,
+from .common import (_parse_input, _artist,
     _get_mf_cols, _filter_samples, _sort_by_mean, _get_others_col)
 import dokdo
 import pandas as pd
@@ -229,7 +229,7 @@ def taxa_abundance_box_plot(taxa,
         df3.to_csv(csv_file)
 
     if brief_xlabels:
-        xticklabels = [_pretty_taxa(x) for x in ax.get_xticklabels()]
+        xticklabels = [dokdo.pname(x.get_text()) for x in ax.get_xticklabels()]
     else:
         xticklabels = None