Merge pull request #97 from bigbio/dev

first attempt to change from csv to parquet

.github/workflows/python-package.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.7, 3.8, 3.9, 3.11]
+        python-version: [3.8, 3.9, 3.11]
 
     steps:
     - uses: actions/checkout@v2

.gitignore

@@ -133,3 +133,4 @@ dmypy.json
 .pyre/
 
 .idea
+/quantms.db

environment.yml

@@ -0,0 +1,15 @@
+name: pmultiqc
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - multiqc==1.23
+  - pandas
+  - pyteomics
+  - pyopenms
+  - sdrf-pipelines >= 0.0.28
+  - lxml
+  - numpy == 1.24.3
+  - pyarrow
+

pmultiqc/main.py

@@ -6,7 +6,7 @@
 from __future__ import print_function
 from pkg_resources import get_distribution
 import logging
-from multiqc.utils import config
+from multiqc import config
 
 # Initialise the main MultiQC logger
 log = logging.getLogger('pmultiqc')
@@ -44,7 +44,7 @@ def pmultiqc_plugin_execution_start():
         config.update_dict(config.sp, {'quantms/mzML': {'fn': '*.mzML', 'num_lines': 0}})
 
     if 'quantms/ms_info' not in config.sp:
-        config.update_dict(config.sp, {'quantms/ms_info': {'fn': '*_ms_info.tsv', 'num_lines': 0}})
+        config.update_dict(config.sp, {'quantms/ms_info': {'fn': '*_ms_info.parquet', 'num_lines': 0}})
 
     if 'quantms/idXML' not in config.sp:
         config.update_dict(config.sp, {'quantms/idXML': {'fn': '*.idXML', 'num_lines': 0}})

pmultiqc/modules/quantms/histogram.py

@@ -155,12 +155,5 @@ def to_dict(self, percentage = False, cats = None):
             for i in self.bins:
                 self.cats[i] = dict()
                 self.cats[i]['name'] = i
-                if self.plot_category == 1:
-                    self.cats[i]['description'] = self.description + ' ' + \
-                        (self.bins[-1] if i == self.bins[-1] else 'is ' + i)
-                elif self.plot_category == 2:
-                    self.cats[i]['description'] = self.description + ' ' + \
-                        (self.bins[-1] if i == self.bins[-1] else 'is between ' + \
-                        i.split(' ~ ')[0] + ' and ' + i.split(' ~ ')[1])
 
         self.dict['cats'] = self.cats

pmultiqc/modules/quantms/ms_functions.py

@@ -20,7 +20,7 @@ def get_ms_qc_info(ms_info: pd.DataFrame):
     Note that here I am using min and not mean for purely qc reasons.
     Since the diagnostic aspect here is mainly to see major fluctuations
     in the intensity, and usually these are scans with very low intensity
-    due to bubbles or ionization issues, thus the mean would hide that.
+    due to bubbles or ionization issues; thus the mean would hide that.
 
     @param ms_info:
     @return:

requirements.txt

@@ -1,7 +1,8 @@
-multiqc==1.19.0
+multiqc==1.23
 pandas
 pyteomics
 pyopenms
-sdrf-pipelines >= 0.0.18
+sdrf-pipelines >= 0.0.28
 lxml
-numpy
+numpy==1.24.3
+pyarrow

setup.py

@@ -6,8 +6,7 @@
 """
 
 from setuptools import setup, find_packages
-
-version = '0.0.24'
+version = '0.0.25'
 
 
 def readme():
@@ -31,11 +30,11 @@ def readme():
     include_package_data=True,
     install_requires=[
         'lxml',
-        'multiqc==1.19.0',
+        'multiqc==1.23',
         'pandas',
         'pyteomics',
-        'sdrf-pipelines >= 0.0.18',
-        'numpy',
+        'sdrf-pipelines >= 0.0.28',
+        'numpy == 1.24.3',
         'pyopenms'
     ],
     entry_points={

tests/test_proteomicslfq.py

@@ -7,3 +7,4 @@ class TestMultiqcModule(TestCase):
   path_mztab1 = 'resources/PXD005942-Sample-25-out.mzTab'
   def test_parse_out_mz_tab(self):
     print("Improve tests here")
+