Merge pull request #1082 from fls-bioinformatics-core/transfer_data.py-improvements

Improvements to 'transfer_data.py' utility

Author: pjbriggs

auto_process_ngs/cli/transfer_data.py

@@ -912,13 +912,15 @@ def add_cellranger_count_outputs(self,qc_dir=None,cellranger='cellranger',
                     reference_data_path,
                     prefix="cellranger_count")
             else:
-                MockQCOutputs.cellranger_count(
-                    sample.name,
-                    self._project.qc_dir,
-                    cellranger=cellranger,
-                    reference_data_path=
-                    reference_data_path,
-                    prefix=prefix)
+                for dirn in (self._project.dirn, self._project.qc_dir):
+                    # Put outputs in project directory and QC dir
+                    MockQCOutputs.cellranger_count(
+                        sample.name,
+                        dirn,
+                        cellranger=cellranger,
+                        reference_data_path=
+                        reference_data_path,
+                        prefix=prefix)
         # Build ZIP archive
         if legacy:
             analysis_dir = os.path.basename(self._parent_dir())
@@ -982,10 +984,12 @@ def add_cellranger_multi_outputs(self,config_csv=None,sample_names=None,
             sample_names = [s for s in config.sample_names]
             reference_data_path = config.reference_data_path
         # Add outputs
-        MockQCOutputs.cellranger_multi(sample_names,
-                                       self._project.qc_dir,
-                                       config_csv=config_csv,
-                                       prefix=prefix)
+        for dirn in (self._project.dirn, self._project.qc_dir):
+            # Put outputs in project directory and QC dir
+            MockQCOutputs.cellranger_multi(sample_names,
+                                           dirn,
+                                           config_csv=config_csv,
+                                           prefix=prefix)
         # Update cellranger reference data in qc.info
         qc_info = self._project.qc_info(self._project.qc_dir)
         qc_info['cellranger_refdata'] = reference_data_path

auto_process_ngs/mock.py

@@ -407,23 +407,26 @@ def cellranger_count(self,sample,qc_dir,cellranger='cellranger',
                       % reference_data_path
             metrics_data = mock10xdata.METRICS_SUMMARY
             cellranger_output_files = ("web_summary.html",
-                                       "metrics_summary.csv")
+                                       "metrics_summary.csv",
+                                       "cloupe.cloupe")
         elif cellranger == 'cellranger-atac':
             if not version:
                 version = '2.0.0'
             cmdline = "cellranger-atac --reference %s" \
                       % reference_data_path
             metrics_data = mock10xdata.ATAC_SUMMARY_2_0_0
             cellranger_output_files = ("web_summary.html",
-                                       "summary.csv")
+                                       "summary.csv",
+                                       "cloupe.cloupe")
         elif cellranger == 'cellranger-arc':
             if not version:
                 version = '2.0.0'
             cmdline = "cellranger-arc --reference %s" \
                       % reference_data_path
             metrics_data = mock10xdata.MULTIOME_SUMMARY_2_0_0
             cellranger_output_files = ("web_summary.html",
-                                       "summary.csv")
+                                       "summary.csv",
+                                       "cloupe.cloupe")
         # Create and populate the directory for the sample
         sample_dir = os.path.join(qc_dir,
                                   prefix,

auto_process_ngs/mockqc.py

@@ -1038,7 +1038,8 @@ def __init__(self, settings_file=None, resolve_undefined=True):
                              'rseqc': jobrunner,
                              'rsync': jobrunner,
                              'star': jobrunner,
-                             'stats': jobrunner },
+                             'stats': jobrunner,
+                             'transfer_data': jobrunner },
                 "archive": { "dirn": str,
                              "log": str,
                              "group": str,
@@ -1129,7 +1130,8 @@ def __init__(self, settings_file=None, resolve_undefined=True):
                 "runners.picard": "runners.qc",
                 "runners.qualimap": "runners.qc",
                 "runners.rseqc": "runners.qc",
-                "runners.star": "runners.qc" },
+                "runners.star": "runners.qc",
+                "runners.transfer_data": "runners.rsync" },
             # Parameters where variables can be expanded
             # e.g. $HOME/auto_process -> /home/user/auto_process
             expand_vars = ["conda.env_dir"],