uses SampleSheet() in _fetch_sex and bead_array to suport legacy samp…

…le_sheets with headers (#65)

docs/quality-control-example.ipynb

@@ -218,7 +218,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "INFO:methylcheck.reports.bead_array:Predicting Sex...\n",
+      "INFO:methylcheck.reports.controls_report:Predicting Sex...\n",
       "INFO:methylprep.files.manifests:Reading manifest file: MethylationEPIC_v-1-0_B4.CoreColumns.csv\n"
      ]
     },
@@ -835,7 +835,7 @@
     "```\n",
     "\n",
     "#### Notes:\n",
-    "- 'on_lambda': if you are running this within an AWS lambda function in the cloud, the default paths of your manifest and other files will change. When True, `on_lambda` will allow you to specify and override paths to your intput, output, and manifest files.\n",
+    "- 'on_lambda': if you are running this within an AWS lambda function in the cloud, the default paths of your manifest and other files will change. When True, `on_lambda` will allow you to specify and override paths to your input, output, and manifest files.\n",
     "- 'path': where to read files from.\n",
     "- 'outpath': in this example, `working.name` is a python `tempdir` folder in a lambda virtual environment. Everything is processed there but saved by moving to an S3 bucket. \n",
     "- 'poobah': whether the QC should run on samples that have failed probes removed (recommended)\n",

docs/release-history.md

@@ -1,5 +1,9 @@
 # Release History
 
+## v0.8.2
+- added support for sample sheets with the legacy Illumina [Header] ... [Data] format. This requires `methylprep`
+be installed for the controls report to run now.
+
 ## v0.8.1
 - .load gives clearer error when loading beta values from CSVs ('beta_csv') if probe names are not unique,
 and returns a list of series for each sample when indeces fail to merge (pandas.concat)

methylcheck/predict/sex.py

@@ -319,7 +319,13 @@ def _fetch_actual_sex_from_sample_sheet_meta_data(filepath, output):
                 loaded_files['meta'] = pd.read_pickle(filename)
                 break
             if '.csv' in filename.suffixes:
-                loaded_files['meta'] = pd.read_csv(filename)
+                try:
+                    from methylprep.files import SampleSheet
+                except ImportError:
+                    raise ImportError("parsing a sample sheet CSV requires `methylprep` be installed first.")
+                #uses methylprep.files.SampleSheet() instead of --- loaded_files['meta'] = pd.read_csv(filename) --- to support legacy [header] format(s).
+                sample_sheet = SampleSheet(filename, filepath)
+                loaded_files['meta'] = sample_sheet._SampleSheet__data_frame
                 break
     if len(loaded_files) == 1:
         # methylprep v1.5.4-6 was creating meta_data files with two Sample_ID columns. Check and fix here:

methylcheck/reports/bead_array.py

@@ -124,7 +124,13 @@ def __init__(self, filepath, outfilepath=None, bg_offset=3000, cutoff_adjust=1.0
                 if '.pkl' in filename.suffixes:
                     setattr(self, 'samplesheet', pd.read_pickle(filename))
                 elif '.csv' in filename.suffixes:
-                    setattr(self, 'samplesheet', pd.read_csv(filename))
+                    try:
+                        from methylprep.files import SampleSheet
+                    except ImportError:
+                        raise ImportError("parsing a sample sheet CSV requires `methylprep` be installed first.")
+                    #uses methylprep.files.SampleSheet() instead of --- pd.read_csv(filename) --- to support legacy [header] format(s).
+                    sample_sheet = SampleSheet(filename, filepath)
+                    setattr(self, 'samplesheet', sample_sheet._SampleSheet__data_frame)
                 break
 
         if not hasattr(self,'control'):

methylcheck/samples/sklearn_mds.py

@@ -1,10 +1,39 @@
 """
 Multi-dimensional Scaling (MDS)
 Copied from scikit-learn v0.22.1 without changes (just all of the functions in one place for MDS to work)
+
+author: Nelle Varoquaux <nelle.varoquaux@gmail.com>
+License: BSD 3-Clause License
+
+Copyright (c) 2007-2021 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 """
 
-# author: Nelle Varoquaux <nelle.varoquaux@gmail.com>
-# License: BSD
 __version__ = '0.22.1'
 
 import numpy as np

methylcheck/version.py

@@ -2,4 +2,4 @@
 # 1) we don't load dependencies by storing it in __init__.py
 # 2) we can import it in setup.py for the same reason
 # 3) we can import it into your module module
-__version__ = '0.8.1'
+__version__ = '0.8.2'