v0.6.0

docs/changelog.rst

@@ -1,19 +1,27 @@
 Change Log
 ==========
 
-Inferelator v0.6.0 `June  14, 2022`
----------------------------------------
+Inferelator v0.6.0 `September  14, 2022`
+----------------------------------------
 
 New Functionality:
 
 - Support for grouping arbitrary genes from multiple tasks into learning groups
 - Workflow to learn homology groups together
+- Workflow to explicitly incorporate velocity and decay into learning
+- Added support for batching parallelization calls to reduce overhead when data is relatively small
 
 Code Refactoring:
 
 - Refactored multi-task learning to parameterize tfs and genes for each task
 - Refactored parallelization around joblib & dask
-- Removed pathos
+- Removed pathos and replaced with joblib
+- Optimized StARS-LASSO by replacing standalone LASSO with lasso_path
+
+Bug Fixes:
+
+- Fixed several messages to be more informative
+- use_no_prior is appropriately applied in multitask learning
 
 Inferelator v0.5.8 `February  23, 2022`
 ---------------------------------------

inferelator/workflows/tfa_workflow.py

@@ -246,6 +246,8 @@ def load_activity(self, file=None, file_type=None):
             file_format_settings=self._file_format_settings
         )
 
+        if file_type is None:
+            self.design = loader.load_data_tsv(file)
         if file_type.lower() == "h5ad":
             self.design = loader.load_data_h5ad(file)
         else:

inferelator/workflows/workflow_base.py

@@ -350,15 +350,14 @@ def set_network_data_flags(
         Set flags to skip using existing network data. Note that these
         flags will be ignored if network data is provided
 
-        :param use_no_prior: Flag to indicate the inferelator should
-            be run without existing prior data.
-            Will create a mock prior with no information.
-            Highly inadvisable. Defaults to False
+        :param use_no_prior: Flag to indicate the inferelator should be run
+            without existing prior data. Will create a mock prior with no
+            information. Highly inadvisable. Defaults to False
         :type use_no_prior: bool
-        :param use_no_gold_standard: Flag to indicate the inferelator
-        should be run without existing gold standard data.
-            Will create a mock gold standard with no information.
-            Highly inadvisable. Defaults to False
+        :param use_no_gold_standard: Flag to indicate the inferelator should
+            be run without existing gold standard data. Will create a mock
+            gold standard with no information. Highly inadvisable.
+            Defaults to False
         :type use_no_gold_standard: bool
         """