Merge pull request #97 from ArcInstitute/dev

bug fixes in `buildPhenotypeData`

environment.yml

@@ -19,6 +19,7 @@ dependencies:
   - mscorefonts
   - rust>=1.72
   - polars>0.20
+  - pycairo
   - pip
   - pip:
       - pyarrow

screenpro/assays/__init__.py

@@ -345,16 +345,6 @@ def buildPhenotypeData(self, run_name='auto',db_rate_col='pop_doubling', **kwarg
             raise ValueError('Only `compare_reps` run_name is supported for now!')
 
         untreated = self.phenotypes[run_name]['config']['untreated']
-        treated = self.phenotypes[run_name]['config']['treated']
-
-        if type(treated) != list: treated = [treated]
-
-        if db_rate_col:
-            #TODO: fix `_calculateGrowthFactor` and `_getTreatmentDoublingRate`
-            growth_factor_table = self._calculateGrowthFactor(
-                untreated = untreated, treated = treated, 
-                db_rate_col = db_rate_col
-            )
 
         pdata_list = []
 
@@ -363,10 +353,16 @@ def buildPhenotypeData(self, run_name='auto',db_rate_col='pop_doubling', **kwarg
             score_tag, comparison = phenotype_name.split(':')
             cond_test, cond_ref = comparison.split('_vs_')
 
+            #TODO: fix `_calculateGrowthFactor` and `_getTreatmentDoublingRate`
             if db_rate_col:
-                growth_rate_reps=growth_factor_table.query(
+                growth_rate_reps = self._calculateGrowthFactor(
+                    untreated = untreated, 
+                    treated = cond_test, # should be part of "treated" list!
+                    db_rate_col = db_rate_col
+                ).query(
                     f'score=="{score_tag}"'
                 ).set_index('replicate')['growth_factor'].to_dict()
+
             else:
                 growth_rate_reps=None
 
@@ -376,7 +372,6 @@ def buildPhenotypeData(self, run_name='auto',db_rate_col='pop_doubling', **kwarg
                 growth_rate_reps=growth_rate_reps,
                 **kwargs
             )
-            # obs = growth_factor_table.loc[pdata_df.index,:],
 
             pdata_list.append(pdata)
 

screenpro/phenoscore/__init__.py

@@ -25,8 +25,9 @@
 from .phenostat import matrixStat, multipleTestsCorrection
 
 
-def runPhenoScore(adata, cond_ref, cond_test, score_level, var_names='target', test='ttest',
-                  growth_rate=1, n_reps='auto', keep_top_n = None, collapse_var=False,
+def runPhenoScore(adata, cond_ref, cond_test, score_level, 
+                  var_names='target', collapse_var=False,
+                  test='ttest', growth_rate=1, n_reps='auto', keep_top_n = None, 
                   num_pseudogenes='auto', pseudogene_size='auto',
                   count_layer=None, count_filter_type='mean', count_filter_threshold=40,
                   ctrl_label='negative_control'
@@ -39,6 +40,7 @@ def runPhenoScore(adata, cond_ref, cond_test, score_level, var_names='target', t
         cond_test (str): condition test
         score_level (str): score level
         var_names (str): variable names to use as index in the result dataframe
+        collapse_var (str): variable to use for `getBestTargetByTSS` function, default is False
         test (str): test to use for calculating p-value ('MW': Mann-Whitney U rank; 'ttest' : t-test)
         growth_rate (int): growth rate
         n_reps (int): number of replicates
@@ -127,7 +129,7 @@ def runPhenoScore(adata, cond_ref, cond_test, score_level, var_names='target', t
             filter_threshold=count_filter_threshold
         )
 
-        # get best best transcript as lowest p-value for each target
+        # get the best transcript as lowest p-value for each target
         if collapse_var not in [False, None]:
             if collapse_var not in result.columns:
                 raise ValueError(f'collapse_var "{collapse_var}" not found in result columns.')