Merge pull request #5 from antgonza/single-control

adding "single" control type
biocore · Jun 1, 2022 · 44979ab · 44979ab
2 parents 22157e6 + 0282cc2
commit 44979ab
Show file tree

Hide file tree

Showing 5 changed files with 49 additions and 41 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,2 +1,3 @@
 q2_katharoseq.egg-info/
 q2_katharoseq/__pycache__/
+__pycache__/
diff --git a/README.md b/README.md
@@ -10,7 +10,7 @@ Installation assumes a working QIIME 2 environment with a minimum version of 202
 git clone https://github.com/biocore/q2-katharoseq.git
 cd q2-katharoseq
 pip install -e .
-``` 
+```
 
 ## Use
 
@@ -24,6 +24,7 @@ classification, and the [`q2-taxa`](https://docs.qiime2.org/2021.11/plugins/avai
 ```
 qiime katharoseq read_count_threshold \
     --i-table a_genus_level_table.qza \
+    --p-threshold 80 \
     --p-control classic \
     --p-positive-control-value name_of_controls_in_metadata \
     --m-positive-control-column-file your_metadata.tsv \
@@ -32,4 +33,3 @@ qiime katharoseq read_count_threshold \
     --m-cell-count-column-column cell_count_variable_in_metadata \
     --o-visualization result.qzv
 ```
-
diff --git a/q2_katharoseq/__init__.py b/q2_katharoseq/__init__.py
@@ -6,8 +6,9 @@
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
 from . import _version
-from ._methods import read_count_threshold, estimating_biomass
+from ._methods import read_count_threshold, estimating_biomass, control_type
 from ._methods import biomass_plot
 
 __version__ = _version.get_versions()['version']
-__all__ = ['read_count_threshold', 'estimating_biomass', 'biomass_plot']
+__all__ = ['read_count_threshold', 'estimating_biomass', 'biomass_plot',
+           'control_type']
diff --git a/q2_katharoseq/_methods.py b/q2_katharoseq/_methods.py
@@ -10,6 +10,46 @@
 from sklearn.linear_model import LinearRegression
 
 
+control_type = {
+    'atcc': [
+        'd__Bacteria;p__Firmicutes;c__Clostridia;o__Clostridiales;'
+        'f__Clostridiaceae;g__Clostridium',
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Enterobacterales;f__Enterobacteriaceae;__',
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Enterobacterales;f__Enterobacteriaceae;'
+        'g__Escherichia-Shigella',
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Staphylococcales;'
+        'f__Staphylococcaceae;g__Staphylococcus'],
+    'zymobiomics': [
+        'd__Bacteria;p__Firmicutes;c__Bacilli;'
+        'o__Lactobacillales;f__Listeriaceae;g__Listeria',
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas',
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Bacillales;'
+        'f__Bacillaceae;g__Bacillus',
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Enterobacterales;f__Enterobacteriaceae;__',
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Enterobacterales;f__Enterobacteriaceae;'
+        'g__Escherichia-Shigella',
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;'
+        'f__Lactobacillaceae;g__Lactobacillus',
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;'
+        'f__Enterococcaceae;g__Enterococcus',
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Staphylococcales'
+        ';f__Staphylococcaceae;g__Staphylococcus'],
+    'classic': [
+        'd__Bacteria;p__Firmicutes;c__Bacilli;o__Bacillales;'
+        'f__Bacillaceae;g__Bacillus',
+        'd__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;'
+        'o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus'],
+    'single': [
+        'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
+        'o__Burkholderiales;f__Comamonadaceae;g__Variovorax']
+}
+
+
 # Define the allosteric sigmoid equation
 def allosteric_sigmoid(x, h, k_prime):
     y = x ** h / (k_prime + x ** h)
@@ -65,41 +105,6 @@ def read_count_threshold(
     max_input = df.loc[max_cell_counts]
     max_inputT = max_input.T
     max_inputT = max_inputT.sort_values(ascending=False).head(10)
-    control_type = {
-        'atcc': [
-            'd__Bacteria;p__Firmicutes;c__Clostridia;o__Clostridiales;'
-            'f__Clostridiaceae;g__Clostridium',
-            'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
-            'o__Enterobacterales;f__Enterobacteriaceae;__',
-            'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
-            'o__Enterobacterales;f__Enterobacteriaceae;'
-            'g__Escherichia-Shigella',
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Staphylococcales;'
-            'f__Staphylococcaceae;g__Staphylococcus'],
-        'zymobiomics': [
-            'd__Bacteria;p__Firmicutes;c__Bacilli;'
-            'o__Lactobacillales;f__Listeriaceae;g__Listeria',
-            'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
-            'o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas',
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Bacillales;'
-            'f__Bacillaceae;g__Bacillus',
-            'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
-            'o__Enterobacterales;f__Enterobacteriaceae;__',
-            'd__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;'
-            'o__Enterobacterales;f__Enterobacteriaceae;'
-            'g__Escherichia-Shigella',
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;'
-            'f__Lactobacillaceae;g__Lactobacillus',
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;'
-            'f__Enterococcaceae;g__Enterococcus',
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Staphylococcales'
-            ';f__Staphylococcaceae;g__Staphylococcus'],
-        'classic': [
-            'd__Bacteria;p__Firmicutes;c__Bacilli;o__Bacillales;'
-            'f__Bacillaceae;g__Bacillus',
-            'd__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;'
-            'o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus']
-    }
 
     # Calculate the total number of reads per sample
     df['asv_reads'] = df.sum(axis=1)

diff --git a/q2_katharoseq/plugin_setup.py b/q2_katharoseq/plugin_setup.py
@@ -2,7 +2,8 @@
 from qiime2.plugin import (Plugin, Citations, Str, Int,
                            MetadataColumn, Categorical, Numeric, Choices)
 from q2_types.feature_table import (FeatureTable, Frequency)
-from . import read_count_threshold, estimating_biomass, biomass_plot
+from . import (read_count_threshold, estimating_biomass, biomass_plot,
+               control_type)
 import q2_katharoseq
 from q2_katharoseq._type import EstimatedBiomass
 from q2_katharoseq._format import EstimatedBiomassFmt, EstimatedBiomassDirFmt
@@ -34,7 +35,7 @@
         'table': FeatureTable[Frequency]
     },
     parameters={
-        'control': Str % Choices(['zymobiomics', 'classic', 'atcc']),
+        'control': Str % Choices(control_type.keys()),
         'threshold': Int,
         'positive_control_value': Str,
         'positive_control_column': MetadataColumn[Categorical],