gsMap 1.71.2__py3-none-any.whl → 1.72.3__py3-none-any.whl

gsMap/utils/generate_r2_matrix.py

@@ -1,23 +1,23 @@
 from pathlib import Path
+
 import bitarray as ba
 import numpy as np
 import pandas as pd
-from scipy.sparse import csr_matrix
-from scipy.sparse import save_npz, load_npz
-from tqdm import trange, tqdm
+from scipy.sparse import csr_matrix, load_npz, save_npz
+from tqdm import tqdm, trange
 
 
 # Define the log class
-class Logger(object):
+class Logger:
     # -
     def __init__(self, fh):
-        self.log_fh = open(fh, 'w')
+        self.log_fh = open(fh, "w")
 
     # -
     def log(self, msg):
-        '''
+        """
         Print to log file and stdout.
-        '''
+        """
         print(msg, file=self.log_fh)
         print(msg)
 
@@ -28,11 +28,11 @@ class Logger(object):
 
 # Compute ld-score using cellular annotations
 def get_compression(fh):
-    '''Which sort of compression should we use with read_csv?'''
-    if fh.endswith('gz'):
-        compression = 'gzip'
-    elif fh.endswith('bz2'):
-        compression = 'bz2'
+    """Which sort of compression should we use with read_csv?"""
+    if fh.endswith("gz"):
+        compression = "gzip"
+    elif fh.endswith("bz2"):
+        compression = "bz2"
     else:
         compression = None
     # -
@@ -42,7 +42,7 @@ def get_compression(fh):
 # Define the reading functions
 def ID_List_Factory(colnames, keepcol, fname_end, header=None, usecols=None):
     # -
-    class IDContainer(object):
+    class IDContainer:
         """
         A class to read data from a file, store it as a DataFrame, and provide a method for a left outer join operation.
         """
@@ -66,14 +66,15 @@ def ID_List_Factory(colnames, keepcol, fname_end, header=None, usecols=None):
             """
             end = self.fname_end
             if end and not fname.endswith(end):
-                raise ValueError('{f} filename must end in {f}'.format(f=end))
+                raise ValueError(f"{end} filename must end in {end}")
             comp = get_compression(fname)
-            self.df = pd.read_csv(fname, header=self.header, usecols=self.usecols,
-                                  sep='\s+', compression=comp)
+            self.df = pd.read_csv(
+                fname, header=self.header, usecols=self.usecols, sep=r"\s+", compression=comp
+            )
             if self.colnames:
                 self.df.columns = self.colnames
             if self.keepcol is not None:
-                self.IDList = self.df.iloc[:, [self.keepcol]].astype('object')
+                self.IDList = self.df.iloc[:, [self.keepcol]].astype("object")
 
         # -
         def loj(self, externalDf):
@@ -83,10 +84,9 @@ def ID_List_Factory(colnames, keepcol, fname_end, header=None, usecols=None):
             r = externalDf.columns[0]
             l = self.IDList.columns[0]
             merge_df = externalDf.iloc[:, [0]]
-            merge_df['keep'] = True
-            z = pd.merge(self.IDList, merge_df, how='left', left_on=l, right_on=r,
-                         sort=False)
-            ii = z['keep'] == True
+            merge_df["keep"] = True
+            z = pd.merge(self.IDList, merge_df, how="left", left_on=l, right_on=r, sort=False)
+            ii = z["keep"]
             return np.nonzero(ii)[0]
 
     # -
@@ -94,20 +94,22 @@ def ID_List_Factory(colnames, keepcol, fname_end, header=None, usecols=None):
 
 
 def getBlockLefts(coords, max_dist):
-    '''
+    """
     Converts coordinates + max block length to the a list of coordinates of the leftmost
     SNPs to be included in blocks.
+
     Parameters
     ----------
     coords : array
         Array of coordinates. Must be sorted.
     max_dist : float
         Maximum distance between SNPs included in the same window.
+
     Returns
     -------
     block_left : 1D np.ndarray with same length as block_left
         block_left[j] :=  min{k | dist(j, k) < max_dist}.
-    '''
+    """
     M = len(coords)
     j = 0
     block_left = np.zeros(M)
@@ -120,17 +122,19 @@ def getBlockLefts(coords, max_dist):
 
 
 def block_left_to_right(block_left):
-    '''
+    """
     Converts block lefts to block rights.
+
     Parameters
     ----------
     block_left : array
         Array of block lefts.
+
     Returns
     -------
     block_right : 1D np.ndarray with same length as block_left
         block_right[j] := max {k | block_left[k] <= j}
-    '''
+    """
     M = len(block_left)
     j = 0
     block_right = np.zeros(M)
@@ -142,54 +146,57 @@ def block_left_to_right(block_left):
     return block_right
 
 
-class GenotypeArrayInMemory(object):
-    '''
+class GenotypeArrayInMemory:
+    """
     Parent class for various classes containing interfaces for files with genotype
     matrices, e.g., plink .bed files, etc
-    '''
+    """
 
     def __init__(self, fname, n, snp_list, keep_snps=None, keep_indivs=None, mafMin=None):
         self.m = len(snp_list.IDList)
         self.n = n
         self.keep_snps = keep_snps
         self.keep_indivs = keep_indivs
-        self.df = np.array(snp_list.df[['CHR', 'SNP', 'BP', 'CM']])
-        self.colnames = ['CHR', 'SNP', 'BP', 'CM']
+        self.df = np.array(snp_list.df[["CHR", "SNP", "BP", "CM"]])
+        self.colnames = ["CHR", "SNP", "BP", "CM"]
         self.mafMin = mafMin if mafMin is not None else 0
         self._currentSNP = 0
         (self.nru, self.geno) = self.__read__(fname, self.m, n)
         # filter individuals
         if keep_indivs is not None:
-            keep_indivs = np.array(keep_indivs, dtype='int')
+            keep_indivs = np.array(keep_indivs, dtype="int")
             if np.any(keep_indivs > self.n):
-                raise ValueError('keep_indivs indices out of bounds')
+                raise ValueError("keep_indivs indices out of bounds")
             # -
-            (self.geno, self.m, self.n) = self.__filter_indivs__(self.geno, keep_indivs, self.m, self.n)
+            (self.geno, self.m, self.n) = self.__filter_indivs__(
+                self.geno, keep_indivs, self.m, self.n
+            )
             # -
             if self.n > 0:
-                print('After filtering, {n} individuals remain'.format(n=self.n))
+                print(f"After filtering, {self.n} individuals remain")
             else:
-                raise ValueError('After filtering, no individuals remain')
+                raise ValueError("After filtering, no individuals remain")
         # -
         # filter SNPs
         if keep_snps is not None:
-            keep_snps = np.array(keep_snps, dtype='int')
+            keep_snps = np.array(keep_snps, dtype="int")
             if np.any(keep_snps > self.m):  # if keep_snps is None, this returns False
-                raise ValueError('keep_snps indices out of bounds')
+                raise ValueError("keep_snps indices out of bounds")
         # -
         (self.geno, self.m, self.n, self.kept_snps, self.freq) = self.__filter_snps_maf__(
-            self.geno, self.m, self.n, self.mafMin, keep_snps)
+            self.geno, self.m, self.n, self.mafMin, keep_snps
+        )
         # -
         if self.m > 0:
-            print('After filtering, {m} SNPs remain'.format(m=self.m))
+            print(f"After filtering, {self.m} SNPs remain")
         else:
-            raise ValueError('After filtering, no SNPs remain')
+            raise ValueError("After filtering, no SNPs remain")
         # -
         self.df = self.df[self.kept_snps, :]
         self.maf = np.minimum(self.freq, np.ones(self.m) - self.freq)
         self.sqrtpq = np.sqrt(self.freq * (np.ones(self.m) - self.freq))
         self.df = np.c_[self.df, self.maf]
-        self.colnames.append('MAF')
+        self.colnames.append("MAF")
 
     # -
     def __read__(self, fname, m, n):
@@ -208,8 +215,11 @@ class GenotypeArrayInMemory(object):
 
     # -
     def ldScoreVarBlocks(self, block_left, c, annot=None):
-        '''Computes an unbiased estimate of L2(j) for j=1,..,M.'''
-        func = lambda x: self.__l2_unbiased__(x, self.n)
+        """Computes an unbiased estimate of L2(j) for j=1,..,M."""
+
+        def func(x):
+            return self.__l2_unbiased__(x, self.n)
+
         snp_getter = self.nextSNPs
         return self.__corSumVarBlocks__(block_left, c, func, snp_getter, annot)
 
@@ -225,7 +235,7 @@ class GenotypeArrayInMemory(object):
     # Methods for calculating sums of Pearson correlation coefficients (i.e.,ld-score)
     # c stands for the chunk size (default = 50)
     def __corSumVarBlocks__(self, block_left, c, func, snp_getter, annot=None):
-        '''
+        """
         Parameters
         ----------
         block_left : np.ndarray with shape (M, )
@@ -243,11 +253,12 @@ class GenotypeArrayInMemory(object):
             The method to be used to get the next SNPs
         annot: numpy array with shape (m,n_a)
             SNP annotations.
+
         Returns
         -------
         cor_sum : np.ndarray with shape (M, num_annots)
             Estimates.
-        '''
+        """
         m, n = self.m, self.n
         block_sizes = np.array(np.arange(m) - block_left)
         block_sizes = np.ceil(block_sizes / c) * c
@@ -256,7 +267,7 @@ class GenotypeArrayInMemory(object):
         else:
             annot_m = annot.shape[0]
             if annot_m != self.m:
-                raise ValueError('Incorrect number of SNPs in annot')
+                raise ValueError("Incorrect number of SNPs in annot")
         # -
         n_a = annot.shape[1]  # number of annotations
         cor_sum = np.zeros((m, n_a))
@@ -277,18 +288,18 @@ class GenotypeArrayInMemory(object):
         rfuncBB = np.zeros((c, c))
         # chunk inside of block
         for l_B in np.arange(0, b, c):  # l_B := index of leftmost SNP in matrix B
-            B = A[:, l_B:l_B + c]
+            B = A[:, l_B : l_B + c]
             # ld matrix
             np.dot(A.T, B / n, out=rfuncAB)
             # ld matrix square
             rfuncAB = func(rfuncAB)
-            cor_sum[l_A:l_A + b, :] += np.dot(rfuncAB, annot[l_B:l_B + c, :])
+            cor_sum[l_A : l_A + b, :] += np.dot(rfuncAB, annot[l_B : l_B + c, :])
 
         # chunk to right of block
         b0 = b
         md = int(c * np.floor(m / c))
         end = md + 1 if md != m else md
-        for l_B in tqdm(np.arange(b0, end, c), desc=f'Compute SNP Gene Weight'):
+        for l_B in tqdm(np.arange(b0, end, c), desc="Compute SNP Gene Weight"):
             # check if the annot matrix is all zeros for this block + chunk
             # this happens w/ sparse categories (i.e., pathways)
             # update the block
@@ -298,10 +309,10 @@ class GenotypeArrayInMemory(object):
                 # block_size can't increase more than c
                 # block_size can't be less than c unless it is zero
                 # both of these things make sense
-                A = np.hstack((A[:, old_b - b + c:old_b], B))
+                A = np.hstack((A[:, old_b - b + c : old_b], B))
                 l_A += old_b - b + c
             elif l_B == b0 and b > 0:
-                A = A[:, b0 - b:b0]
+                A = A[:, b0 - b : b0]
                 l_A = b0 - b
             elif b == 0:  # no SNPs to left in window, e.g., after a sequence gap
                 A = np.array(()).reshape((n, 0))
@@ -314,44 +325,45 @@ class GenotypeArrayInMemory(object):
                 rfuncAB = np.zeros((b, c))
             # -
             B = snp_getter(c)
-            p1 = np.all(annot[l_A:l_A + b, :] == 0)
-            p2 = np.all(annot[l_B:l_B + c, :] == 0)
+            p1 = np.all(annot[l_A : l_A + b, :] == 0)
+            p2 = np.all(annot[l_B : l_B + c, :] == 0)
             if p1 and p2:
                 continue
             # -
             np.dot(A.T, B / n, out=rfuncAB)
             rfuncAB = func(rfuncAB)
-            cor_sum[l_A:l_A + b, :] += np.dot(rfuncAB, annot[l_B:l_B + c, :])
-            cor_sum[l_B:l_B + c, :] += np.dot(annot[l_A:l_A + b, :].T, rfuncAB).T
+            cor_sum[l_A : l_A + b, :] += np.dot(rfuncAB, annot[l_B : l_B + c, :])
+            cor_sum[l_B : l_B + c, :] += np.dot(annot[l_A : l_A + b, :].T, rfuncAB).T
             np.dot(B.T, B / n, out=rfuncBB)
             rfuncBB = func(rfuncBB)
-            cor_sum[l_B:l_B + c, :] += np.dot(rfuncBB, annot[l_B:l_B + c, :])
+            cor_sum[l_B : l_B + c, :] += np.dot(rfuncBB, annot[l_B : l_B + c, :])
         # -
         return cor_sum
 
 
 class PlinkBEDFile(GenotypeArrayInMemory):
-    '''
+    """
     Interface for Plink .bed format
-    '''
+    """
 
     def __init__(self, fname, n, snp_list, keep_snps=None, keep_indivs=None, mafMin=None):
         self._bedcode = {
-            2: ba.bitarray('11'),
-            9: ba.bitarray('10'),
-            1: ba.bitarray('01'),
-            0: ba.bitarray('00')
+            2: ba.bitarray("11"),
+            9: ba.bitarray("10"),
+            1: ba.bitarray("01"),
+            0: ba.bitarray("00"),
         }
         # -
-        GenotypeArrayInMemory.__init__(self, fname, n, snp_list, keep_snps=keep_snps, keep_indivs=keep_indivs,
-                                       mafMin=mafMin)
+        GenotypeArrayInMemory.__init__(
+            self, fname, n, snp_list, keep_snps=keep_snps, keep_indivs=keep_indivs, mafMin=mafMin
+        )
 
     # -
     def __read__(self, fname, m, n):
-        if not fname.endswith('.bed'):
-            raise ValueError('.bed filename must end in .bed')
+        if not fname.endswith(".bed"):
+            raise ValueError(".bed filename must end in .bed")
         # -
-        fh = open(fname, 'rb')
+        fh = open(fname, "rb")
         magicNumber = ba.bitarray(endian="little")
         magicNumber.fromfile(fh, 2)
         bedMode = ba.bitarray(endian="little")
@@ -360,11 +372,11 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         nru = n + e
         self.nru = nru
         # check magic number
-        if magicNumber != ba.bitarray('0011011011011000'):
-            raise IOError("Magic number from Plink .bed file not recognized")
+        if magicNumber != ba.bitarray("0011011011011000"):
+            raise OSError("Magic number from Plink .bed file not recognized")
         # -
-        if bedMode != ba.bitarray('10000000'):
-            raise IOError("Plink .bed file must be in default SNP-major mode")
+        if bedMode != ba.bitarray("10000000"):
+            raise OSError("Plink .bed file must be in default SNP-major mode")
         # check file length
         self.geno = ba.bitarray(endian="little")
         self.geno.fromfile(fh)
@@ -377,7 +389,7 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         real_len = len(geno)
         if real_len != exp_len:
             s = "Plink .bed file has {n1} bits, expected {n2}"
-            raise IOError(s.format(n1=real_len, n2=exp_len))
+            raise OSError(s.format(n1=real_len, n2=exp_len))
 
     # -
     def __filter_indivs__(self, geno, keep_indivs, m, n):
@@ -388,14 +400,14 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         z = ba.bitarray(m * 2 * nru_new, endian="little")
         z.setall(0)
         for e, i in enumerate(keep_indivs):
-            z[2 * e::2 * nru_new] = geno[2 * i::2 * nru]
-            z[2 * e + 1::2 * nru_new] = geno[2 * i + 1::2 * nru]
+            z[2 * e :: 2 * nru_new] = geno[2 * i :: 2 * nru]
+            z[2 * e + 1 :: 2 * nru_new] = geno[2 * i + 1 :: 2 * nru]
         self.nru = nru_new
         return (z, m, n_new)
 
     # -
     def __filter_snps_maf__(self, geno, m, n, mafMin, keep_snps):
-        '''
+        """
         Credit to Chris Chang and the Plink2 developers for this algorithm
         Modified from plink_filter.c
         https://github.com/chrchang/plink-ng/blob/master/plink_filter.c
@@ -414,7 +426,7 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         major allele frequency = (b+c)/(2*(n-a+c))
         het ct + missing ct = a + b - 2*c
         Why does bitarray not have >> ????
-        '''
+        """
         nru = self.nru
         m_poly = 0
         y = ba.bitarray()
@@ -423,7 +435,7 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         kept_snps = []
         freq = []
         for e, j in enumerate(keep_snps):
-            z = geno[2 * nru * j:2 * nru * (j + 1)]
+            z = geno[2 * nru * j : 2 * nru * (j + 1)]
             A = z[0::2]
             a = A.count()
             B = z[1::2]
@@ -443,9 +455,10 @@ class PlinkBEDFile(GenotypeArrayInMemory):
 
     # -
     def nextSNPs(self, b, minorRef=None):
-        '''
+        """
         Unpacks the binary array of genotypes and returns an n x b matrix of floats of
         normalized genotypes for the next b SNPs, where n := number of samples.
+
         Parameters
         ----------
         b : int
@@ -453,29 +466,30 @@ class PlinkBEDFile(GenotypeArrayInMemory):
         minorRef: bool, default None
             Should we flip reference alleles so that the minor allele is the reference?
             (This is useful for computing l1 w.r.t. minor allele).
+
         Returns
         -------
         X : np.array with dtype float64 with shape (n, b), where n := number of samples
             Matrix of genotypes normalized to mean zero and variance one. If minorRef is
             not None, then the minor allele will be the positive allele (i.e., two copies
             of the minor allele --> a positive number).
-        '''
+        """
         # -
         try:
             b = int(b)
             if b <= 0:
                 raise ValueError("b must be > 0")
-        except TypeError:
-            raise TypeError("b must be an integer")
+        except TypeError as e:
+            raise TypeError("b must be an integer") from e
         # -
         if self._currentSNP + b > self.m:
-            s = '{b} SNPs requested, {k} SNPs remain'
+            s = "{b} SNPs requested, {k} SNPs remain"
             raise ValueError(s.format(b=b, k=(self.m - self._currentSNP)))
         # -
         c = self._currentSNP
         n = self.n
         nru = self.nru
-        slice = self.geno[2 * c * nru:2 * (c + b) * nru]
+        slice = self.geno[2 * c * nru : 2 * (c + b) * nru]
         X = np.array(slice.decode(self._bedcode), dtype="float64").reshape((b, nru)).T
         X = X[0:n, :]
         Y = np.zeros(X.shape)
@@ -499,14 +513,15 @@ class PlinkBEDFile(GenotypeArrayInMemory):
 
 
 class PlinkBEDFileWithR2Cache(PlinkBEDFile):
-    def compute_r2_cache(self,
-                         block_left,
-                         output_cache_file_dir: Path,
-                         chunk_size=500_000_000,
-                         c=500,
-                         r2_threshold=1e-4,
-                         annot=None):
-
+    def compute_r2_cache(
+        self,
+        block_left,
+        output_cache_file_dir: Path,
+        chunk_size=500_000_000,
+        c=500,
+        r2_threshold=1e-4,
+        annot=None,
+    ):
         func = np.square
         snp_getter = self.nextSNPs
         data, rows, cols = [], [], []
@@ -536,9 +551,11 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
             cols.extend(l_B + non_zero_indices[1])
             if len(data) > chunk_size:
                 # save the cache
-                print(f'Start saving the cache file: {output_cache_file_dir / f"{l_B}.npz"}')
-                r2_sparse_matrix = csr_matrix((data, (rows, cols)), shape=(self.m, self.m), dtype='float16')
-                save_npz(output_cache_file_dir / f'{l_B}.npz', r2_sparse_matrix)
+                print(f"Start saving the cache file: {output_cache_file_dir / f'{l_B}.npz'}")
+                r2_sparse_matrix = csr_matrix(
+                    (data, (rows, cols)), shape=(self.m, self.m), dtype="float16"
+                )
+                save_npz(output_cache_file_dir / f"{l_B}.npz", r2_sparse_matrix)
                 # reset the data
                 data.clear()
                 rows.clear()
@@ -552,9 +569,9 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         else:
             annot_m = annot.shape[0]
             if annot_m != self.m:
-                raise ValueError('Incorrect number of SNPs in annot')
+                raise ValueError("Incorrect number of SNPs in annot")
         # -
-        n_a = annot.shape[1]  # number of annotations
+        # n_a = annot.shape[1]  # number of annotations
         # cor_sum = np.zeros((m, n_a))
         # b = index of first SNP for which SNP 0 is not included in LD Score
         b = np.nonzero(block_left > 0)
@@ -573,7 +590,7 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         rfuncBB = np.zeros((c, c))
         # chunk inside of block
         for l_B in np.arange(0, b, c):  # l_B := index of leftmost SNP in matrix B
-            B = A[:, l_B:l_B + c]
+            B = A[:, l_B : l_B + c]
             # ld matrix
             np.dot(A.T, B / n, out=rfuncAB)
             # ld matrix square
@@ -585,7 +602,7 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         b0 = b
         md = int(c * np.floor(m / c))
         end = md + 1 if md != m else md
-        for l_B in trange(b0, end, c, desc=f'Compute r2 cache for {output_cache_file_dir.name}'):
+        for l_B in trange(b0, end, c, desc=f"Compute r2 cache for {output_cache_file_dir.name}"):
             # check if the annot matrix is all zeros for this block + chunk
             # this happens w/ sparse categories (i.e., pathways)
             # update the block
@@ -595,10 +612,10 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
                 # block_size can't increase more than c
                 # block_size can't be less than c unless it is zero
                 # both of these things make sense
-                A = np.hstack((A[:, old_b - b + c:old_b], B))
+                A = np.hstack((A[:, old_b - b + c : old_b], B))
                 l_A += old_b - b + c
             elif l_B == b0 and b > 0:
-                A = A[:, b0 - b:b0]
+                A = A[:, b0 - b : b0]
                 l_A = b0 - b
             elif b == 0:  # no SNPs to left in window, e.g., after a sequence gap
                 A = np.array(()).reshape((n, 0))
@@ -611,8 +628,8 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
                 rfuncAB = np.zeros((b, c))
             # -
             B = snp_getter(c)
-            p1 = np.all(annot[l_A:l_A + b, :] == 0)
-            p2 = np.all(annot[l_B:l_B + c, :] == 0)
+            p1 = np.all(annot[l_A : l_A + b, :] == 0)
+            p2 = np.all(annot[l_B : l_B + c, :] == 0)
             if p1 and p2:
                 continue
             # -
@@ -629,19 +646,19 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         if len(data) > 0:
             # save remaining data
             # save the cache
-            print(f'Start saving the cache file: {output_cache_file_dir / f"{l_B}.npz"}')
-            r2_sparse_matrix = csr_matrix((data, (rows, cols)), shape=(m, m), dtype='float16')
-            save_npz(output_cache_file_dir / f'{l_B}.npz', r2_sparse_matrix)
+            print(f"Start saving the cache file: {output_cache_file_dir / f'{l_B}.npz'}")
+            r2_sparse_matrix = csr_matrix((data, (rows, cols)), shape=(m, m), dtype="float16")
+            save_npz(output_cache_file_dir / f"{l_B}.npz", r2_sparse_matrix)
         # combine the cache files
-        print(f'Start combining the cache files in {output_cache_file_dir}')
-        cached_r2_matrix_files = list(output_cache_file_dir.glob('*.npz'))
+        print(f"Start combining the cache files in {output_cache_file_dir}")
+        cached_r2_matrix_files = list(output_cache_file_dir.glob("*.npz"))
         combined_r2_matrix_files = self.load_r2_matrix_from_cache_files(output_cache_file_dir)
         # remove the cache files
         for cached_r2_matrix_file in cached_r2_matrix_files:
             cached_r2_matrix_file.unlink()
         # save the combined r2 matrix
-        print(f'Start saving the combined r2 matrix in {output_cache_file_dir}')
-        combined_r2_matrix_file = output_cache_file_dir / 'combined_r2_matrix.npz'
+        print(f"Start saving the combined r2 matrix in {output_cache_file_dir}")
+        combined_r2_matrix_file = output_cache_file_dir / "combined_r2_matrix.npz"
         save_npz(combined_r2_matrix_file, combined_r2_matrix_files)
 
     def get_ldscore_using_r2_cache(self, annot_matrix, cached_r2_matrix_dir):
@@ -652,11 +669,15 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         cached_r2_matrix_dir = Path(cached_r2_matrix_dir)
         # iter the cached r2 matrix files
         result_matrix = np.zeros((self.m, annot_matrix.shape[1]))
-        cached_r2_matrix_files = list(cached_r2_matrix_dir.glob('*.npz'))
-        assert len(cached_r2_matrix_files) > 0, (f'No cached r2 matrix files in {cached_r2_matrix_dir}'
-                                                 f'Please run the function compute_r2_cache first!')
-        for r2_matrix_file in tqdm(cached_r2_matrix_files, desc=f'Compute ld score for {cached_r2_matrix_dir.name}'):
-            print(f'Compute r2 matrix multiplication for {r2_matrix_file}')
+        cached_r2_matrix_files = list(cached_r2_matrix_dir.glob("*.npz"))
+        assert len(cached_r2_matrix_files) > 0, (
+            f"No cached r2 matrix files in {cached_r2_matrix_dir}"
+            f"Please run the function compute_r2_cache first!"
+        )
+        for r2_matrix_file in tqdm(
+            cached_r2_matrix_files, desc=f"Compute ld score for {cached_r2_matrix_dir.name}"
+        ):
+            print(f"Compute r2 matrix multiplication for {r2_matrix_file}")
             r2_matrix = load_npz(r2_matrix_file)
             result_matrix += r2_matrix.dot(annot_matrix)
         return result_matrix
@@ -667,48 +688,60 @@ class PlinkBEDFileWithR2Cache(PlinkBEDFile):
         """
         cached_r2_matrix_dir = Path(cached_r2_matrix_dir)
         # iter the cached r2 matrix files
-        cached_r2_matrix_files = list(cached_r2_matrix_dir.glob('*.npz'))
-        assert len(cached_r2_matrix_files) > 0, (f'No cached r2 matrix files in {cached_r2_matrix_dir}'
-                                                 f'Please run the function compute_r2_cache first!')
+        cached_r2_matrix_files = list(cached_r2_matrix_dir.glob("*.npz"))
+        assert len(cached_r2_matrix_files) > 0, (
+            f"No cached r2 matrix files in {cached_r2_matrix_dir}"
+            f"Please run the function compute_r2_cache first!"
+        )
         # load the r2 matrix
         r2_matrix = load_npz(cached_r2_matrix_files[0])
-        for r2_matrix_file in tqdm(cached_r2_matrix_files[1:], desc=f'Load r2 matrix from {cached_r2_matrix_dir.name}'):
-            print(f'Load r2 matrix from {r2_matrix_file}')
+        for r2_matrix_file in tqdm(
+            cached_r2_matrix_files[1:], desc=f"Load r2 matrix from {cached_r2_matrix_dir.name}"
+        ):
+            print(f"Load r2 matrix from {r2_matrix_file}")
             r2_matrix += load_npz(r2_matrix_file)
         # to float16
-        r2_matrix = r2_matrix.astype('float16')
+        r2_matrix = r2_matrix.astype("float16")
         return r2_matrix
+
     def load_combined_r2_matrix(self, cached_r2_matrix_dir):
         """
         Load the combined r2 matrix
         """
-        combined_r2_matrix_file = Path(cached_r2_matrix_dir) / 'combined_r2_matrix.npz'
-        assert combined_r2_matrix_file.exists(), (f'No combined r2 matrix file in {cached_r2_matrix_dir}'
-                                                  f'Should delete the cache files and run the function compute_r2_cache first!')
+        combined_r2_matrix_file = Path(cached_r2_matrix_dir) / "combined_r2_matrix.npz"
+        assert combined_r2_matrix_file.exists(), (
+            f"No combined r2 matrix file in {cached_r2_matrix_dir}"
+            f"Should delete the cache files and run the function compute_r2_cache first!"
+        )
         # load the r2 matrix
         r2_matrix = load_npz(combined_r2_matrix_file)
         # to float16
-        r2_matrix = r2_matrix.astype('float16')
+        r2_matrix = r2_matrix.astype("float16")
         return r2_matrix
 
+
 def load_bfile(bfile_chr_prefix):
-    PlinkBIMFile = ID_List_Factory(['CHR', 'SNP', 'CM', 'BP', 'A1', 'A2'], 1, '.bim', usecols=[0, 1, 2, 3, 4, 5])
-    PlinkFAMFile = ID_List_Factory(['IID'], 0, '.fam', usecols=[1])
+    PlinkBIMFile = ID_List_Factory(
+        ["CHR", "SNP", "CM", "BP", "A1", "A2"], 1, ".bim", usecols=[0, 1, 2, 3, 4, 5]
+    )
+    PlinkFAMFile = ID_List_Factory(["IID"], 0, ".fam", usecols=[1])
 
-    snp_file, snp_obj = bfile_chr_prefix + '.bim', PlinkBIMFile
+    snp_file, snp_obj = bfile_chr_prefix + ".bim", PlinkBIMFile
     array_snps = snp_obj(snp_file)
     m = len(array_snps.IDList)
-    print(f'Read list of {m} SNPs from {snp_file}')
+    print(f"Read list of {m} SNPs from {snp_file}")
     #
     # Load fam
-    ind_file, ind_obj = bfile_chr_prefix + '.fam', PlinkFAMFile
+    ind_file, ind_obj = bfile_chr_prefix + ".fam", PlinkFAMFile
     array_indivs = ind_obj(ind_file)
     n = len(array_indivs.IDList)
-    print(f'Read list of {n} individuals from {ind_file}')
+    print(f"Read list of {n} individuals from {ind_file}")
 
     # Load genotype array
-    array_file, array_obj = bfile_chr_prefix + '.bed', PlinkBEDFileWithR2Cache
-    geno_array = array_obj(array_file, n, array_snps, keep_snps=None, keep_indivs=None, mafMin=None)
+    array_file, array_obj = bfile_chr_prefix + ".bed", PlinkBEDFileWithR2Cache
+    geno_array = array_obj(
+        array_file, n, array_snps, keep_snps=None, keep_indivs=None, mafMin=None
+    )
 
     return array_snps, array_indivs, geno_array
 
@@ -717,19 +750,19 @@ def generate_r2_matrix_chr_cache(bfile_chr_prefix, ld_wind_cm, output_cache_file
     # Load genotype array
     array_snps, array_indivs, geno_array = load_bfile(bfile_chr_prefix)
     # Compute block lefts
-    block_left = getBlockLefts(geno_array.df[:, 3], ld_wind_cm)
+    # block_left = getBlockLefts(geno_array.df[:, 3], ld_wind_cm)
     # Compute LD score
-    r2_matrix = geno_array.load_r2_matrix_from_cache(output_cache_file_dir)
+    # r2_matrix = geno_array.load_r2_matrix_from_cache(output_cache_file_dir)
 
 
 def generate_r2_matrix_cache(bfile_prefix, chromosome_list, r2_cache_dir, ld_wind_cm=1):
     r2_cache_dir = Path(r2_cache_dir)
 
     for chr in chromosome_list:
-        output_cache_file_prefix = r2_cache_dir / f'chr{chr}'
+        output_cache_file_prefix = r2_cache_dir / f"chr{chr}"
         output_cache_file_prefix.mkdir(parents=True, exist_ok=True)
-        bfile_chr_prefix = bfile_prefix + '.' + str(chr)
-        generate_r2_matrix_chr_cache(bfile_chr_prefix,
-                                     ld_wind_cm=ld_wind_cm,
-                                     output_cache_file_dir=output_cache_file_prefix)
-        print(f'Compute r2 matrix for chr{chr} done!')
+        bfile_chr_prefix = bfile_prefix + "." + str(chr)
+        generate_r2_matrix_chr_cache(
+            bfile_chr_prefix, ld_wind_cm=ld_wind_cm, output_cache_file_dir=output_cache_file_prefix
+        )
+        print(f"Compute r2 matrix for chr{chr} done!")