update data

docs/requirements.txt

@@ -3,4 +3,5 @@ sphinx-rtd-theme==1.3.0rc1
 numpy
 pysam==0.22.0
 tqdm
-pyBigWig==0.3.22
+pyBigWig==0.3.22
+pandas

genomkit/regions/gregions.py

@@ -775,7 +775,7 @@ def subtract(self, regions, whole_region: bool = False,
                                 if counts == len(regions.elements):
                                     finished = 1
                             else:
-                                # region.sequence < 
+                                # region.sequence <
                                 # target.sequences[counts].sequence:
                                 small_self.add(r)
                     else:
@@ -805,8 +805,9 @@ def subtract(self, regions, whole_region: bool = False,
                 return self
             if not self.sorted:
                 self.sort()
-            # if there is overlap within self or y, and the `merge` option is set,
-            # we merge any overlapping sequence and create two different GRegions
+            # if there is overlap within self or y, and the `merge` option
+            # is set, we merge any overlapping sequence and create two
+            # different GRegions
             if merge:
                 a = self.merge(inplace=False)
                 b = regions.merge(inplace=False)
@@ -846,10 +847,18 @@ def subtract(self, regions, whole_region: bool = False,
                         # ------        -----      -------
                         #   ------        --        ---
                         if s.end > b[j].end:
-                            s1 = GRegion(sequence=s.sequence, start=s.start, end=b[j].start,
-                                         name=s.name, orientation=s.orientation, data=s.data)
-                            s2 = GRegion(sequence=s.sequence, start=b[j].end, end=s.end,
-                                         name=s.name, orientation=s.orientation, data=s.data)
+                            s1 = GRegion(sequence=s.sequence,
+                                         start=s.start,
+                                         end=b[j].start,
+                                         name=s.name,
+                                         orientation=s.orientation,
+                                         data=s.data)
+                            s2 = GRegion(sequence=s.sequence,
+                                         start=b[j].end,
+                                         end=s.end,
+                                         name=s.name,
+                                         orientation=s.orientation,
+                                         data=s.data)
                             res.add(s1)
                             s = s2
                             if j < last_j:
@@ -983,3 +992,13 @@ def cluster(self, max_distance):
                     previous = deepcopy(s)
             z.add(previous)
             return z
+
+    def total_coverage(self):
+        """Return the total coverage (bp) of all the regions.
+
+        :return: Total coverage (bp)
+        :rtype: int
+        """
+        merged_regions = self.merge(inplace=False)
+        cov = sum([len(r) for r in merged_regions])
+        return cov

genomkit/regions/gregions_set.py

@@ -1,5 +1,7 @@
 from genomkit import GRegions
 from collections import OrderedDict
+import numpy as np
+import pandas as pd
 
 
 class GRegionsSet:
@@ -10,6 +12,15 @@ class GRegionsSet:
     multiple GRegions.
     """
     def __init__(self, name: str = "", load_dict=None):
+        """Initiate a GRegionsSet object which can contain multiple GRegions.
+
+        :param name: Define the name, defaults to ""
+        :type name: str, optional
+        :param load_dict: Given the file paths of multiple GRegions as a
+                          dictionary with names as keys and values as file
+                          paths, defaults to None
+        :type load_dict: dict, optional
+        """
         self.collection = OrderedDict()
         if load_dict:
             for name, filename in load_dict.items():
@@ -18,9 +29,21 @@ def __init__(self, name: str = "", load_dict=None):
                                           load=filename))
 
     def add(self, name: str, regions):
+        """Add a GRegions object into this set.
+
+        :param name: Define the name
+        :type name: str
+        :param regions: Given the GRegions
+        :type regions: GRegions
+        """
         self.collection[name] = regions
 
     def __len__(self):
+        """Return the number of GRegions in this set.
+
+        :return: Number of GRegions
+        :rtype: int
+        """
         return len(self.collection)
 
     def __getattr__(self, key):
@@ -36,10 +59,43 @@ def __setattr__(self, key, value):
         self.collection[key] = value
 
     def get_names(self):
+        """Return the names of all GRegions.
+
+        :return: Names
+        :rtype: list
+        """
         return list(self.collection.keys())
 
     def get_lengths(self):
+        """Return a list of the number of regions in all GRegions
+
+        :return: A list of region numbers
+        :rtype: list
+        """
         res = OrderedDict()
         for name, regions in self.collection.items():
             res[name] = len(regions)
         return res
+
+    def count_overlaps(self, query_set):
+        """Return a pandas dataframe of the numbers of overlapping regions
+        between the reference GRegionsSet (self) and the query GRegionsSet.
+
+        :param query_set: Query GRegionsSet
+        :type query_set: GRegionsSet
+        :return: Matrix of numbers of overlaps
+        :rtype: dataframe
+        """
+        res = np.zeros((len(self), len(query_set)))
+        row_names = []
+        col_names = []
+        for i, (ref_name, ref) in enumerate(self.collection.items()):
+            row_names.append(ref_name)
+            for j, (query_name, query) in enumerate(query_set.items()):
+                col_names.append(query_name)
+                c = ref.overlap_count(target=query)
+                res[i, j] = c
+        df = pd.DataFrame(res,
+                          index=row_names,
+                          columns=col_names)
+        return df

requirements.txt

@@ -1,4 +1,5 @@
 numpy
 pysam==0.22.0
 tqdm
-pyBigWig==0.3.22
+pyBigWig==0.3.22
+pandas

tests/test_files/wig/example.wig

@@ -0,0 +1,13 @@
+track type=wiggle_0 name="Example Track" description="Example Wiggle Track"
+variableStep chrom=chr1
+1000 0.5
+2000 0.7
+3000 0.9
+4000 1.0
+5000 0.8
+variableStep chrom=chr2
+1000 0.3
+2000 0.4
+3000 0.6
+4000 0.7
+5000 0.5