Merge branch 'main' into 26_change_read_in_text

README.md

@@ -39,8 +39,6 @@ find an overview of actions available in the plugin.
 | annotate-mags-card         | Annotate MAGs with antimicrobial resistance gene information from CARD.              | [rgi](https://github.com/arpcard/rgi) | main, load                           |
 | annotate-reads-card        | Annotate metagenomic reads with antimicrobial resistance gene information from CARD. | [rgi](https://github.com/arpcard/rgi) | bwt, load                            |
 | heatmap                    | Create a heatmap from annotate-mags-card output files.                               | [rgi](https://github.com/arpcard/rgi) | heatmap                              |
-| visualize-annotation-stats | Plot annotate-reads-card annotation statistics.                                      |                                       |                                      |
-
 
 ## Dev environment
 This repository follows the _black_ code style. To make the development slightly easier

ci/recipe/meta.yaml

@@ -24,7 +24,6 @@ requirements:
     - q2templates {{ qiime2_epoch }}.*
     - q2cli {{ qiime2_epoch }}.*
     - rgi
-    - altair
 
 test:
   requires:

q2_amr/card/reads.py

@@ -2,13 +2,9 @@
 import shutil
 import subprocess
 import tempfile
-from distutils.dir_util import copy_tree
 from typing import Union
 
-import altair as alt
 import pandas as pd
-import pkg_resources
-import q2templates
 from q2_types.per_sample_sequences import (
     SingleLanePerSamplePairedEndFastqDirFmt,
     SingleLanePerSampleSingleEndFastqDirFmt,
@@ -149,93 +145,3 @@ def run_rgi_bwt(
             f"(return code {e.returncode}), please inspect "
             "stdout and stderr to learn more."
         )
-
-
-def plot_sample_stats(sample_stats: dict, output_dir: str):
-    sample_stats_df = pd.DataFrame.from_dict(sample_stats, orient="index")
-    sample_stats_df.reset_index(inplace=True)
-
-    mapped_reads_plot = (
-        alt.Chart(sample_stats_df)
-        .mark_bar()
-        .encode(
-            x=alt.X(
-                "index:N",
-                title=None,
-                axis=alt.Axis(labels=False, ticks=False),
-                bandPosition=0.1,
-            ),
-            y=alt.Y(
-                "mapped_reads",
-                title="Mapped Reads",
-                scale=alt.Scale(
-                    domain=(0, sample_stats_df["mapped_reads"].max() * 1.1)
-                ),
-            ),
-            tooltip=[
-                alt.Tooltip("index", title="Sample"),
-                alt.Tooltip("mapped_reads", title="Mapped Reads"),
-                alt.Tooltip("total_reads", title="Total Reads"),
-            ],
-        )
-        .properties(width=alt.Step(80), height=200)
-    )
-
-    percentage_plot = (
-        alt.Chart(sample_stats_df)
-        .mark_bar()
-        .encode(
-            x=alt.X(
-                "index:N", title=None, axis=alt.Axis(labelAngle=15), bandPosition=0.1
-            ),
-            y=alt.Y(
-                "percentage",
-                title="Mapped Reads (%)",
-                scale=alt.Scale(domain=(0, sample_stats_df["percentage"].max() * 1.1)),
-            ),
-            tooltip=[
-                alt.Tooltip("index", title="Sample"),
-                alt.Tooltip("percentage", title="Mapped Reads (%)"),
-                alt.Tooltip("total_reads", title="Total Reads"),
-            ],
-        )
-        .properties(width=alt.Step(80), height=200)
-    )
-    combined_chart = alt.vconcat(mapped_reads_plot, percentage_plot, spacing=0)
-    combined_chart.save(os.path.join(output_dir, "sample_stats_plot.html"))
-
-
-def extract_sample_stats(samp_dir: str):
-    with open(os.path.join(samp_dir, "overall_mapping_stats.txt"), "r") as f:
-        for line in f:
-            if "Total reads:" in line:
-                total_reads = int(line.split()[2])
-            elif "Mapped reads:" in line:
-                mapped_reads = int(line.split()[2])
-                percentage = float(line.split()[3].strip("()").strip("%"))
-        sample_stats_dict = {
-            "total_reads": total_reads,
-            "mapped_reads": mapped_reads,
-            "percentage": percentage,
-        }
-    return sample_stats_dict
-
-
-def visualize_annotation_stats(
-    output_dir: str,
-    amr_reads_annotation: Union[
-        CARDGeneAnnotationDirectoryFormat, CARDAlleleAnnotationDirectoryFormat
-    ],
-):
-    directory = str(amr_reads_annotation)
-    sample_stats = {}
-    for samp in os.listdir(directory):
-        samp_dir = os.path.join(directory, samp)
-        sample_stats[samp] = extract_sample_stats(samp_dir)
-    plot_sample_stats(sample_stats, output_dir)
-    TEMPLATES = pkg_resources.resource_filename("q2_amr", "assets")
-    copy_tree(os.path.join(TEMPLATES, "rgi", "annotation_stats"), output_dir)
-    context = {"tabs": [{"title": "Mapped Reads", "url": "index.html"}]}
-    index = os.path.join(TEMPLATES, "rgi", "annotation_stats", "index.html")
-    templates = [index]
-    q2templates.render(templates, output_dir, context=context)

q2_amr/tests/card/test_database.py → q2_amr/card/tests/test_database.py

@@ -12,7 +12,7 @@
 
 
 class TestAnnotateMagsCard(TestPluginBase):
-    package = "q2_amr.tests"
+    package = "q2_amr.card.tests"
 
     def mock_preprocess(self, dir, operation):
         if operation == "card":

q2_amr/tests/card/test_heatmap.py → q2_amr/card/tests/test_heatmap.py

@@ -14,7 +14,7 @@
 
 
 class TestHeatmap(TestPluginBase):
-    package = "q2_amr.tests"
+    package = "q2_amr.card.tests"
 
     def test_heatmap(self):
         amr_annotation = CARDAnnotationDirectoryFormat()

q2_amr/tests/card/test_mags.py → q2_amr/card/tests/test_mags.py

@@ -11,7 +11,7 @@
 
 
 class TestAnnotateMagsCard(TestPluginBase):
-    package = "q2_amr.tests"
+    package = "q2_amr.card.tests"
 
     def mock_run_rgi_main(
         self,

q2_amr/tests/card/test_reads.py → q2_amr/card/tests/test_reads.py

@@ -1,7 +1,6 @@
 import os
 import shutil
 import subprocess
-import tempfile
 from unittest.mock import ANY, MagicMock, call, patch
 
 from q2_types.per_sample_sequences import (
@@ -10,13 +9,7 @@
 )
 from qiime2.plugin.testing import TestPluginBase
 
-from q2_amr.card.reads import (
-    annotate_reads_card,
-    extract_sample_stats,
-    plot_sample_stats,
-    run_rgi_bwt,
-    visualize_annotation_stats,
-)
+from q2_amr.card.reads import annotate_reads_card, run_rgi_bwt
 from q2_amr.types import (
     CARDAlleleAnnotationDirectoryFormat,
     CARDDatabaseDirectoryFormat,
@@ -25,7 +18,7 @@
 
 
 class TestAnnotateReadsCARD(TestPluginBase):
-    package = "q2_amr.tests"
+    package = "q2_amr.card.tests"
 
     @classmethod
     def setUpClass(cls):
@@ -204,43 +197,3 @@ def test_exception_raised(self):
             mock_run_command.side_effect = subprocess.CalledProcessError(1, "cmd")
             run_rgi_bwt()
             self.assertEqual(str(cm.exception), expected_message)
-
-    def test_extract_sample_stats(self):
-        with tempfile.TemporaryDirectory() as tmp:
-            mapping_stats_path = self.get_data_path("output.overall_mapping_stats.txt")
-            new_mapping_stats_path = os.path.join(tmp, "overall_mapping_stats.txt")
-            shutil.copy(mapping_stats_path, new_mapping_stats_path)
-            sample_stats = extract_sample_stats(tmp)
-
-            self.assertEqual(sample_stats, self.sample_stats["sample1"])
-
-    def test_plot_sample_stats(self):
-        with tempfile.TemporaryDirectory() as tmp:
-            plot_sample_stats(self.sample_stats, tmp)
-            self.assertTrue(os.path.exists(os.path.join(tmp, "sample_stats_plot.html")))
-
-    def mock_plot_sample_stats(self, sample_stats, output_dir):
-        # Create a dummy HTML file and copy it to the output_dir
-        with open(os.path.join(output_dir, "sample_stats_plot.html"), "w") as file:
-            file.write("file")
-
-    def test_visualize_annotation_stats(self):
-        # Create a CARDGeneAnnotation object
-        amr_reads_annotation = CARDGeneAnnotationDirectoryFormat()
-
-        # Create two sample directories in the CARDGeneAnnotation object
-        for num in range(1, 3):
-            os.makedirs(os.path.join(str(amr_reads_annotation), f"sample{num}"))
-
-        # Patch extract_sample_stats and plot_sample_stats with side effect
-        # mock_plot_sample_stats
-        with patch("q2_amr.card.reads.extract_sample_stats"), patch(
-            "q2_amr.card.reads.plot_sample_stats",
-            side_effect=self.mock_plot_sample_stats,
-        ), tempfile.TemporaryDirectory() as tmp:
-            # Run visualize_annotation_stats function
-            visualize_annotation_stats(tmp, amr_reads_annotation)
-
-            # Assert if all expected files are created
-            for file in ["sample_stats_plot.html", "index.html", "q2templateassets"]:
-                self.assertTrue(os.path.exists(os.path.join(tmp, file)))

q2_amr/tests/card/test_utils.py → q2_amr/card/tests/test_utils.py

@@ -11,7 +11,7 @@
 
 
 class TestAnnotateReadsCARD(TestPluginBase):
-    package = "q2_amr.tests"
+    package = "q2_amr.card.tests"
 
     @classmethod
     def setUpClass(cls):

q2_amr/plugin_setup.py

@@ -21,7 +21,7 @@
 from q2_amr.card.database import fetch_card_db
 from q2_amr.card.heatmap import heatmap
 from q2_amr.card.mags import annotate_mags_card
-from q2_amr.card.reads import annotate_reads_card, visualize_annotation_stats
+from q2_amr.card.reads import annotate_reads_card
 from q2_amr.types import (
     CARDAnnotationJSONFormat,
     CARDAnnotationTXTFormat,
@@ -167,9 +167,9 @@
         "allelic variants available in CARD's Resistomes & Variants"
         " data set. This is highly recommended for non-clinical "
         "samples .",
-        "include_other_models": "The default settings for will align reads against "
+        "include_other_models": "The default settings will align reads against "
         "CARD's protein homolog models. With include_other_"
-        "models set to True reads are additionally aligned to "
+        "models set to True, reads are additionally aligned to "
         "protein variant models, rRNA mutation models, and "
         "protein over-expression models. These three model "
         "types require comparison to CARD's curated lists of "
@@ -210,18 +210,7 @@
         "frequency": "Represent samples based on resistance profile.",
     },
     name="Create heatmap from annotate-mags-card output.",
-    description=("Create heatmap from annotate-mags-card output."),
-    citations=[citations["alcock_card_2023"]],
-)
-
-plugin.visualizers.register_function(
-    function=visualize_annotation_stats,
-    inputs={"amr_reads_annotation": SampleData[CARDAlleleAnnotation]},
-    parameters={},
-    input_descriptions={"amr_reads_annotation": "AMR annotations on the allele level."},
-    parameter_descriptions={},
-    name="Visualize mapping statistics.",
-    description="Visualize mapping statistics of an annotate-reads-card output.",
+    description="Create heatmap from annotate-mags-card output.",
     citations=[citations["alcock_card_2023"]],
 )
 

setup.py

@@ -25,7 +25,6 @@
     package_data={
         "q2_amr": [
             "citations.bib",
-            "tests/data/*",
             "assets/rgi/annotation_stats/*",
             "assets/rgi/heatmap/*",
         ],
@@ -34,7 +33,7 @@
             "data/annotate_mags_output/*/*/*",
             "data/annotate_reads_output/*/*",
         ],
-        "q2_amr.tests": ["data/*"],
+        "q2_amr.card.tests": ["data/*"],
     },
     zip_safe=False,
 )