* When running differential expression, RNAlysis session reports will…

… automatically include the auto-generated R script, as well as the sanitized design matrix used.

* Added optional parameters to all differential expression samples, allowing users to return a path to the auto-generated R script and data sanitized design matrix used.

HISTORY.rst

@@ -31,6 +31,8 @@ Changed
 * RNAlysis now offers default values for differential expression tables' column names.
 * Functions that average replicates now display clearer group names by default.
 * The RNAlysis interface to ShortStack now uses the most recent API (replace 'knownRNAs' with 'known_miRNAs').
+* When running differential expression, RNAlysis session reports will automatically include the auto-generated R script, as well as the sanitized design matrix used.
+* Added optional parameters to all differential expression samples, allowing users to return a path to the auto-generated R script and data sanitized design matrix used.
 
 Fixed
 *******

rnalysis/gui/gui.py

@@ -331,7 +331,8 @@ def __init__(self, parent=None):
 
 
 class DiffExpWindow(gui_windows.FuncExternalWindow):
-    EXCLUDED_PARAMS = {'self', 'comparisons', 'covariates', 'lrt_factors', 'model_factors'}
+    EXCLUDED_PARAMS = {'self', 'comparisons', 'covariates', 'lrt_factors', 'model_factors', 'return_design_matrix',
+                       'return_code'}
     IGNORED_WIDGETS = gui_windows.FuncExternalWindow.IGNORED_WIDGETS | {'load_design'}
 
     __slots__ = {'comparisons': 'list of comparisons to make',
@@ -438,6 +439,9 @@ def init_lrt_ui(self):
 
     def get_analysis_kwargs(self):
         kwargs = super().get_analysis_kwargs()
+        kwargs['return_design_matrix'] = True
+        kwargs['return_code'] = True
+
         kwargs['comparisons'] = self.comparisons_widgets['picker'].get_comparison_values()
         if not self.simplified:
             kwargs['covariates'] = self.covariates_widgets['picker'].get_comparison_values()
@@ -1610,6 +1614,9 @@ def process_outputs(self, outputs, job_id: int, source_name: str = ''):
             tab_name = self.get_tab_name()
             for this_src_name, output in outputs.items():
                 self.process_outputs(output, job_id, f"{this_src_name} {tab_name}")
+        elif isinstance(outputs, Path):
+            new_id = JOB_COUNTER.get_id()
+            self.itemSpawned.emit(f"'{source_name}'\noutput", new_id, job_id, outputs)
 
     def _multi_keep_window_accepted(self, dialog: 'MultiKeepWindow', source_name: str):
         kept_outputs = dialog.result()
@@ -3492,7 +3499,7 @@ def update_report_spawn(self, name: str, spawn_id: int, predecessor_id: int,
     def is_valid_spawn(spawn: object):
         if validation.isinstanceinh(spawn, filtering.Filter) \
             or validation.isinstanceinh(spawn, enrichment.FeatureSet) \
-            or isinstance(spawn, (pd.Series, pd.DataFrame, plt.Figure)) \
+            or isinstance(spawn, (pd.Series, pd.DataFrame, plt.Figure, Path)) \
             or validation.isinstanceinh(spawn, generic.GenericPipeline):
             return True
         return False
@@ -3503,7 +3510,7 @@ def _get_spawn_type(spawn: Union[filtering.Filter, enrichment.FeatureSet, pd.Dat
             spawn_type = FILTER_OBJ_TYPES_INV.get(type(spawn).__name__, 'Other table')
         elif validation.isinstanceinh(spawn, enrichment.FeatureSet):
             spawn_type = 'Gene set'
-        elif isinstance(spawn, (pd.Series, pd.DataFrame, plt.Figure)):
+        elif isinstance(spawn, (pd.Series, pd.DataFrame, plt.Figure, Path)):
             spawn_type = 'Other output'
         elif validation.isinstanceinh(spawn, generic.GenericPipeline):
             spawn_type = 'Pipeline'
@@ -3526,6 +3533,8 @@ def _cache_spawn(spawn: Union[filtering.Filter, enrichment.FeatureSet, pd.DataFr
         elif validation.isinstanceinh(spawn, generic.GenericPipeline):
             filename = parsing.slugify(suffix) + '.yaml'
             obj = spawn.export_pipeline(None)
+        elif isinstance(spawn, Path):
+            filename = parsing.slugify(suffix) + spawn.suffix
         else:
             raise TypeError(f"Invalid spawn type '{type(spawn)}' for spawn '{spawn}'!")
         io.cache_gui_file(obj, filename)
@@ -3554,6 +3563,9 @@ def _format_report_desc(obj: Union[filtering.Filter, enrichment.FeatureSet, pd.D
             desc = f'<img src="data/{filename}" alt="Figure" height="400">'
         elif validation.isinstanceinh(obj, generic.GenericPipeline):
             desc = str(obj).replace('\n', '<br>')
+        elif isinstance(obj, Path):
+            data = io.load_cached_gui_file(obj)
+            desc = f'<pre><code>{data}</code></pre>'.replace('\n', '<br>')
         else:
             raise TypeError(f"Invalid object type '{type(obj)}' of object '{obj}'.")
 

rnalysis/utils/io.py

@@ -140,6 +140,9 @@ def load_cached_gui_file(filename: Union[str, Path], load_as_obj: bool = True) -
             with open(file_path) as f:
                 return {item.strip() for item in f.readlines()}
 
+        elif file_path.suffix in {'.R'} and load_as_obj:
+            with open(file_path) as f:
+                return f.read()
         else:
             with open(file_path, 'rb') as f:
                 return f.read()
@@ -156,6 +159,9 @@ def cache_gui_file(item: Union[pd.DataFrame, set, str], filename: str):
         save_table(item, file_path, index=True)
     elif isinstance(item, set):
         save_gene_set(item, file_path)
+    elif isinstance(item, Path) and item.suffix == '.R':
+        assert item.exists(), f"File '{item}' flagged for caching does not exist!"
+        shutil.copy(item, file_path)
     elif isinstance(item, str):
         with open(file_path, 'w') as f:
             f.write(item)