bumping to 1.4.1

callingcardstools/Analysis/yeast/chipexo_promoter_sig.py

@@ -30,11 +30,34 @@ def read_in_chipexo_data(
     Returns:
             pandas.DataFrame: A pandas DataFrame containing the chipexo
                 allevents data
+
+    Raises:
+            AttributeError: If the chipexo table does not contain at least the
+                following columns: `chr`, `start`, `end`, `YPD_log2Fold`,
+                `YPD_log2P`. Note that the `start` column is the original
+                `coord` column from the yeastepigenome.org data and `end` is
+                simply `coord` + 1. It is in this format to make it somewhat
+                easier to input to other processes that accept bed-like files.
     """
     df = pd.read_csv(chipexo_data_path,
                      header=0,
                      index_col=False)
 
+    if not {'chr', 'start', 'end',
+            'YPD_log2Fold', 'YPD_log2P'}.issubset(df.columns):
+        raise AttributeError('The chipexo table must contain at least the '
+                             'following columns: `chr`, `start`, `end`, '
+                             '`YPD_log2Fold`, `YPD_log2P`. Note that the '
+                             '`start` column is the original `coord` column '
+                             'from the yeastepigenome.org data and `end` '
+                             'is simply `coord` + 1. It is in this format '
+                             'to make it somewhat easier to input to other '
+                             'processes that accept bed-like files.')
+
+    df.rename(columns={'start': 'chipexo_start',
+                       'end': 'chipexo_end'},
+              inplace=True)
+
     return relabel_chr_column(df,
                               chrmap_df,
                               curr_chr_convention,
@@ -110,7 +133,7 @@ def chipexo_promoter_sig(chipexo_data_path: str,
     return pd.merge(promoter_df, chipexo_df,
                     on='chr',
                     how='inner')\
-        .query('start <= coord <= end')\
+        .query('start <= chipexo_start <= end')\
         .groupby(['chr', 'start', 'end', 'name', 'strand'])\
         .agg(
         n_sig_peaks=pd.NamedAgg(column='chr',

docs/home/changelog.md

@@ -1,5 +1,14 @@
 # Change Log
 
+## Version 1.4.1
+
+### Changes
+
+- chipexo_promoter_sig now checks the columns and expects the original
+  yeastepigenome.org allevents `coord` column to be split into `start` 
+  and `end` where `end` is simply coord + 1. This is to be consistent
+  with the other bed-type files.
+
 ## Version 1.4.0
 
 ### Additions

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "callingCardsTools"
-version = "1.4.0"
+version = "1.4.1"
 description = "A collection of objects and functions to work with calling cards sequencing tools"
 authors = ["chase mateusiak <[email protected]>"]
 license = "MIT"

tests/Analysis/yeast/test_chipexo_promoter_sig.py

@@ -1,17 +1,20 @@
 import argparse
 import os
+
 import pandas as pd
-from callingcardstools.Analysis.yeast.chipexo_promoter_sig \
-    import chipexo_promoter_sig
-from callingcardstools.Analysis.yeast.chipexo_promoter_sig \
-    import main as chipexo_main
+
+from callingcardstools.Analysis.yeast.chipexo_promoter_sig import \
+    chipexo_promoter_sig
+from callingcardstools.Analysis.yeast.chipexo_promoter_sig import \
+    main as chipexo_main
 
 
 def test_chipexo_promoter_sig(tmp_path):
     # Create DataFrames
     chipexo_df = pd.DataFrame({
         'chr': ['chr1'],
-        'coord': [150],
+        'start': [150],
+        'end': [151],
         'YPD_log2Fold': [2.0],
         'YPD_log2P': [0.05]
     })
@@ -61,22 +64,41 @@ def test_chipexo_data(tmpdir):
 
     assert os.path.isdir(test_data_directory) is True
 
+    # chipexo_data_path = os.path.join(test_data_directory,
+    #                                  'chipexo_10352.csv.gz')
+    # chrmap_data_path = os.path.join(test_data_directory,
+    #                                 'chrmap.csv.gz')
+    # promoter_data_path = os.path.join(test_data_directory,
+    #                                   'yiming_promoters.bed.gz')
+
+    # output_path = os.path.join(tmpdir, 'chipexo_promoter_sig.csv')
+
     chipexo_data_path = os.path.join(test_data_directory,
-                                     'chipexo_10352.csv.gz')
+                                     'test_user_count0/binding/pugh_none/49.csv.gz')
     chrmap_data_path = os.path.join(test_data_directory,
-                                    'chrmap.csv.gz')
+                                    'test_user_count0/chrmap.csv')
     promoter_data_path = os.path.join(test_data_directory,
-                                      'yiming_promoters.bed.gz')
+                                      'test_user_count0/promotersets/yiming/33.bed.gz')
 
     output_path = os.path.join(tmpdir, 'chipexo_promoter_sig.csv')
 
+    # args = argparse.Namespace(
+    #     chipexo_data_path=chipexo_data_path,
+    #     chipexo_orig_chr_convention='chr',
+    #     unified_chr_convention='ucsc',
+    #     chrmap_data_path=chrmap_data_path,
+    #     promoter_data_path=promoter_data_path,
+    #     promoter_orig_chr_convention='id',
+    #     output_file=output_path,
+    #     compress=False)
+
     args = argparse.Namespace(
         chipexo_data_path=chipexo_data_path,
-        chipexo_orig_chr_convention='chr',
+        chipexo_orig_chr_convention='ucsc',
         unified_chr_convention='ucsc',
         chrmap_data_path=chrmap_data_path,
         promoter_data_path=promoter_data_path,
-        promoter_orig_chr_convention='id',
+        promoter_orig_chr_convention='ucsc',
         output_file=output_path,
         compress=False)