cpgtools 1.12.0__py3-none-any.whl → 2.0.2__py3-none-any.whl

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_selectNBest.py

@@ -18,6 +18,7 @@ cg_003	0.845065	0.843957	0.840184	0.824286
 import sys
 import numpy as np
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule.utils import *
 import pandas as pd
 
@@ -28,7 +29,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"
@@ -40,8 +40,8 @@ def main():
 	parser = OptionParser(usage,version="%prog " + __version__)
 	parser.add_option("-i","--input_file",action="store",type="string",dest="input_file",help="Tab-separated data frame file containing beta values with the 1st row containing sample IDs and the 1st column containing CpG IDs.")
 	parser.add_option("-g","--group",action="store",type="string",dest="group_file",help="Comma-separated group file defining the biological groups of each sample.")
-	parser.add_option("-k","--topK",action="store",type='int', dest="cpg_count", default=100, help="Number of top features to select. default=%default" )
-	parser.add_option("-s","--score-function",action="store",type='string', dest="score_function", default='chi2', help="Scoring function used to measure the dependency between features scores and labels. Must be \"chisq\" (chi-squared statistic), \"anova\" (ANOVA F-value), or \"mutual_info\" (mutual information). default=%default" )
+	parser.add_option("-c","--topK",action="store",type='int', dest="cpg_count", default=100, help="Number of top features to select. default=%default" )
+	parser.add_option("-s","--score-function",action="store",type='string', dest="score_function", default='chisq', help="Scoring function used to measure the dependency between features scores and labels. Must be \"chisq\" (chi-squared statistic), \"anova\" (ANOVA F-value), or \"mi\" (mutual information). default=%default" )
 	parser.add_option("-o","--output",action="store",type='string', dest="out_file",help="The prefix of the output file.")
 	(options,args)=parser.parse_args()
 	
@@ -77,7 +77,7 @@ def main():
 	
 	printlog("Reading group file: \"%s\"" % (options.group_file))
 	group = pd.read_csv(options.group_file, index_col=0, header=0,names=['Sample_ID', 'Group_ID'])
-	a = list(group['Group_ID'])	#a is *string labels* for groups: ['Normal', 'Normal', 'Normal', 'Normal', 'Normal', 'Cancer', 'Cancer', 'Cancer', 'Cancer']
+	a = pd.Series(list(group['Group_ID']))	#a is *string labels* for groups: ['Normal', 'Normal', 'Normal', 'Normal', 'Normal', 'Cancer', 'Cancer', 'Cancer', 'Cancer']
 	#print (a)
 	y, tmp = pd.factorize(a)	#y is *numeric labels* for groups: [0 0 0 0 0 1 1 1 1]
 	#print (np.array(y))
@@ -87,12 +87,15 @@ def main():
 		if options.score_function == 'anova':
 			printlog ("Using ANOVA F value to select features ...")
 			selector = SelectKBest(f_classif, k = options.cpg_count)
-		elif options.score_function == 'mutual_info':
+		elif options.score_function == 'mi':
 			printlog ("Using Mutual Information to select features ...")
 			selector = SelectKBest(mutual_info_classif, k = options.cpg_count)
-		else:
+		elif options.score_function == 'chisq':
 			printlog ("Using Chi Square statistic to select features ...")
 			selector = SelectKBest(chi2, k = options.cpg_count)
+		else:
+			printlog("Unknown function: %s" % options.score_function)
+			sys.exit(0)
 	else:
 		printlog("Doing nothing! '-k' >= the total number of features in \"%s\"" % (options.input_file))
 		sys.exit(0)

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_stacked_barplot.py

@@ -28,6 +28,7 @@ import collections
 import subprocess
 import numpy as np
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
@@ -37,7 +38,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_stats.py

@@ -25,6 +25,7 @@ import collections
 import subprocess
 import numpy as np
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
@@ -33,7 +34,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_tSNE.py

@@ -33,6 +33,7 @@ import sys
 import subprocess
 from optparse import OptionParser
 from cpgmodule.utils import *
+from cpgmodule._version import __version__
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
 from sklearn.manifold import TSNE
@@ -41,15 +42,15 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"
 
 def pick_colors(n):
-	my_colors = ['#e6194B', '#3cb44b', '#4363d8', '#f58231', '#911eb4', '#42d4f4', '#f032e6', '#bfef45', '#fabebe', '#469990', '#e6beff', '#9A6324', '#fffac8', '#800000', '#aaffc3', '#808000', '#ffd8b1', '#000075', '#a9a9a9','#ffe119']
+	my_colors = [
+	"#F0A3FF", "#0075DC", "#993F00", "#4C005C", "#191919", "#005C31", "#2BCE48", "#FFCC99", "#808080", "#94FFB5", "#8F7C00", "#9DCC00", "#C20088", "#003380", "#FFA405", "#FFA8BB", "#426600", "#FF0010", "#5EF1F2", "#00998F", "#E0FF66", "#740AFF", "#990000", "#FFFF80", "#FFE100", "#FF5005"]
 	if n > len(my_colors):
-		print ("Only support 21 different colors", file = sys.stderr)
+		print ("Only support 26 different colors", file = sys.stderr)
 		sys.exit()
 	return my_colors[0:n]
 
@@ -99,27 +100,31 @@ def main():
 		printlog("Perplexigty value is set to %d" % options.perplexity_value)
 	
 	#remove NA and transpose
-	df2 = df1.dropna(axis=0, how='any')
-	printlog("%d rows with missing values were removed." % (len(df1) - len(df2)))
+	df2 = df1.dropna(axis=0, how='any').T
+	printlog("%d rows with missing values were removed." % (len(df1.index) - len(df2.columns)))
 	#print (df2.head())
-	
-	printlog("Transposing data frame ...")
-	df2 = df2.T
-	#print (df2.index) 
-		
-	printlog("Standarizing values ...")
-	x = df2.values
-	x = StandardScaler().fit_transform(x)
-	#print (x.shape)
-	
+
 	printlog("Reading group file: \"%s\" ..." % (options.group_file))
 	group = pd.read_csv(options.group_file, index_col=0, header=0,names=['Sample_ID', 'Group_ID'])
-	group.index = group.index.map(str)
-	
 	#check if sample IDs are unique
 	if len(group.index) != len(group.index.unique()):
 		print ("Sample IDs are not unique", file = sys.stderr)
-		sys.exit()
+		sys.exit()	
+	group.index = group.index.map(str)
+	printlog("Group file \"%s\" contains %d samples" % (options.group_file, len(group.index)))
+	
+	printlog("Find common sample IDs between group file and data file ...") 
+	common_samples = list(set(group.index) & set(df2.index))
+	used_df = df2.loc[common_samples]
+	(usable_sample, usable_cpg) = used_df.shape
+	printlog("Used CpGs: %d, Used samples: %d" % (usable_cpg, usable_sample))
+
+		
+	printlog("Standarizing values ...")
+	x = used_df.to_numpy()
+	x = StandardScaler().fit_transform(x)
+	
+
 	group_names = group['Group_ID'].unique().tolist()	# a list of unique group names
 	color_names = pick_colors(len(group_names))	# a list of unique colors
 	group_to_col = dict(zip(group_names, color_names))
@@ -127,13 +132,13 @@ def main():
 	group['Colors'] = color_list
 	
 	
-	tsne = TSNE(n_components = options.n_components, random_state = 0, perplexity = options.perplexity_value, learning_rate = options.learning_rate, n_iter = options.n_iterations)
+	tsne = TSNE(n_components = options.n_components, random_state = 0, perplexity = options.perplexity_value, learning_rate = options.learning_rate, max_iter = options.n_iterations)
 	tsne_components = tsne.fit_transform(x)
 	pc_names = [str(i)+str(j) for i,j in zip(['PC']*options.n_components,range(1,options.n_components+1))]
-	principalDf = pd.DataFrame(data = tsne_components, columns = pc_names, index = df2.index)
+	principalDf = pd.DataFrame(data = tsne_components, columns = pc_names, index = used_df.index)
 	principalDf.index.name = 'Sample_ID'
 	
-	finalDf = pd.concat([principalDf, group], axis=1,sort=False)
+	finalDf = pd.concat([principalDf, group], axis=1,sort=False, join='inner')
 	finalDf.index.name = 'Sample_ID'
 	
 	printlog("Writing t-SNE results to file: \"%s\" ..." % (options.out_file + '.t-SNE.tsv'))
@@ -149,10 +154,12 @@ def main():
 	
 	if options.plot_alpha:
 		print ('library(scales)', file=ROUT)
-		print ('plot(PC1, PC2, col = alpha(Colors, %f), pch=%d, cex=1.5, main="t-SNE 2D map")' % (options.plot_alpha, pch[options.plot_char]), file=ROUT)
+		print ('plot(PC1, PC2, col = alpha(Colors, %f), pch=%d, cex=1.5, main="tSNE 2D map", xlab="tSNE1", ylab="tSNE2")' 
+			% (options.plot_alpha, pch[options.plot_char]), file=ROUT)
 	else:
-		print ('plot(PC1, PC2, col = Colors, pch=%d, cex=1.2, main="t-SNE 2D map")' % pch[options.plot_char], file=ROUT)	
-		#print ('plot(PC1, PC2, col = Colors, pch=%d, cex=1, main="t-SNE 2D map")' % pch[options.plot_char], file=ROUT)
+		print ('plot(PC1, PC2, col = Colors, pch=%d, cex=1.2, main="tSNE 2D map", xlab="tSNE1", ylab="tSNE2")' 
+			% (pch[options.plot_char]), file=ROUT)
+
 	if options.text_label:
 		print ('text(PC1, PC2, labels=Sample_ID, col = Colors, cex=0.5, pos=1)', file=ROUT)
 	print ('legend("%s", legend=c(%s), col=c(%s), pch=%d,cex=1)' %  (legend_pos[options.legend_location], ','.join(['"' + str(i) + '"' for i in group_names]), ','.join(['"' + str(group_to_col[i]) + '"' for i in group_names]), pch[options.plot_char]), file=ROUT)

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_topN.py

@@ -18,6 +18,7 @@ import collections
 import subprocess
 import numpy as np
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
@@ -27,7 +28,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/beta_trichotmize.py

@@ -18,6 +18,7 @@ import numpy as np
 from optparse import OptionParser
 from sklearn import mixture
 from time import strftime
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 import pandas as pd
@@ -26,7 +27,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_Bayes.py

@@ -27,13 +27,13 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 from multiprocessing import Process, Manager, current_process
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_bb.py

@@ -36,12 +36,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_fisher.py

@@ -34,12 +34,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_glm.py

@@ -18,12 +18,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_logit.py

@@ -31,12 +31,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_nonparametric.py

@@ -19,12 +19,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/scripts/dmc_ttest.py

@@ -18,12 +18,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import padjust
+from cpgmodule._version import __version__
 
 __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="1.12.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"
@@ -146,8 +146,8 @@ def main():
 			# check if sample ID matches
 			for s in s2g:
 				if s not in sample_IDs:
-					printlog("Cannot find sample ID \"%s\" from file \"%s\"" % (s, options.input_file))
-					sys.exit(3)
+					printlog("Cannot find sample ID \"%s\" from file \"%s\". Exclude this sample from differential analysis." % (s, options.input_file))
+					#sys.exit(3)
 		else:
 			g2values = collections.defaultdict(list)
 			probe_ID = f[0]

cpgtools-2.0.2.data/scripts/predict_sex.py

@@ -0,0 +1,126 @@
+#!python
+
+"""
+#==============================================================================
+Predict sex based on the semi-methylation (also known as genomic imprinting) 
+ratio. This method leverages the fact that, due to X chromosome inactivation,
+females have a higher proportion of semi-methylated CpGs on their X chromosomes.
+A log2(ratio) greater than 0 indicates a female, while a log2(ratio) less than
+0 indicates a male.
+
+Example of input data file
+---------------------------
+CpG_ID    Sample_01    Sample_02    Sample_03    Sample_04
+cg_001    0.831035    0.878022    0.794427    0.880911
+cg_002    0.249544    0.209949    0.234294    0.236680
+cg_003    0.845065    0.843957    0.840184    0.824286
+
+Example of output file
+----------------------
+Sample_ID    log2_SM_ratio    Predicted_sex
+Sample_01    -2.249628052954919      Male
+Sample_02    -2.2671726671830674     Male
+Sample_03    1.4530581933290616      Female
+Sample_04    1.4808015115356654      Female
+
+...
+
+"""
+import sys
+import numpy as np
+from optparse import OptionParser
+from cpgmodule.utils import printlog
+from cpgmodule import ireader
+import pandas as pd
+from cpgmodule._version import __version__
+
+__author__ = "Liguo Wang"
+__copyright__ = "Copyleft"
+__credits__ = []
+__license__ = "GPL"
+__maintainer__ = "Liguo Wang"
+__email__ = "wang.liguo@mayo.edu"
+__status__ = "Development"
+
+    
+def main():
+    
+    usage="%prog [options]" + "\n"
+    parser = OptionParser(usage,version="%prog " + __version__)
+    parser.add_option("-i","--input_file",action="store", type="string",dest="input_file", help="Tab-separated data frame file containing beta values with the 1st row containing sample IDs and the 1st column containing CpG IDs.")
+    parser.add_option("-x","--xprobe",action="store", type="string",dest="xprobe_file", help="File with CpG IDs mapped to the X chromosome, with one probe listed per row.")
+    parser.add_option("-c","--cut",action="store", type='float', dest="cutoff", default=0.0, help="The cutoff of log2(SM ratio) to determine the sex prediction. Log2(SM ratio) greater than this cutoff indicates a female, while a log2(ratio) less than this cutoff indicates a male. default=%default")
+    parser.add_option("-o","--output",action="store", type='string', dest="out_file", help="The prefix of the output file.")
+    (options,args)=parser.parse_args()
+    
+    print ()
+    if not (options.input_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(101)
+    if not (options.xprobe_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(102)    
+    if not (options.out_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(103)    
+    
+    printlog("Reading X probes from: \"%s\"" % (options.xprobe_file))
+    x_cpgs = set()
+    for l in ireader.reader(options.xprobe_file):
+        l = l.strip()
+        if l.startswith('#'):
+            continue
+        x_cpgs.add(l)
+    printlog("Total %d X probes loaded." % len(x_cpgs))
+    
+    printlog("Reading input file: \"%s\"" % (options.input_file))
+    df1 = pd.read_csv(options.input_file, index_col = 0, sep="\t")
+    #print (df1)
+    
+    #remove any rows with NAs
+    df2 = df1.dropna(axis=0, how='any')
+    printlog("%d CpGs with missing values were removed." % (len(df1) - len(df2)))
+    #print (df2)
+    
+    sample_cpg_ids = df2.index
+    sample_names = df2.columns
+    found_x_cpgs = list(x_cpgs & set(sample_cpg_ids))
+    printlog("Found %d CpGs located on the chrX from file: %s" % (len(found_x_cpgs), options.input_file))
+    
+    # only X probes in df3
+    df3 = df2.loc[list(found_x_cpgs)]
+    #pd.DataFrame.to_csv(df3, options.out_file + '.tmp.tsv', sep="\t", index_label="sample")
+    
+    low_beta_range = [0, 0.2]
+    mid_beta_range = [0.3, 0.7]
+    high_beta_range = [0.8, 1.0]
+    
+    output = {}
+    for s in sample_names:
+        output[s] = {}
+        low_beta_count = pd.cut(df3[s], low_beta_range).count()
+        mid_beta_count = pd.cut(df3[s], mid_beta_range).count()
+        high_beta_count = pd.cut(df3[s], high_beta_range).count()
+        try:
+            ratio = np.log2(mid_beta_count/(low_beta_count + high_beta_count))
+        except:
+           ratio = np.nan
+        output[s]['log2_SM_ratio'] = ratio
+        
+        if ratio > options.cutoff:
+            output[s]['Predicted_sex'] = 'Female'
+        elif ratio < options.cutoff:
+            output[s]['Predicted_sex'] = 'Male'
+        else:
+            output[s]['Predicted_sex'] = 'Unknown'
+    df_out = pd.DataFrame(output).T
+    
+    outfile = options.out_file + '.predicted_sex.tsv'
+    printlog("Writing to file: \"%s\"" % outfile)
+    pd.DataFrame.to_csv(df_out, outfile, sep="\t", index_label="Sample_ID")
+
+if __name__=='__main__':
+    main()    

cpgtools-2.0.2.dist-info/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2024 The Python Packaging Authority
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cpgtools-2.0.2.dist-info/METADATA

@@ -0,0 +1,76 @@
+Metadata-Version: 2.1
+Name: cpgtools
+Version: 2.0.2
+Summary: Tools to analyze and visualize DNA methylation data
+Author-email: Liguo Wang <wangliguo78@gmail.com>
+Maintainer-email: Liguo Wang <wangliguo78@gmail.com>
+License: Copyright (c) 2024 The Python Packaging Authority
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Documentation, https://cpgtools.readthedocs.io/en/latest/index.html
+Project-URL: Repository, https://github.com/liguowang/cpgtools.git
+Keywords: DNA methylation,EPIC,450K,850K,935K,RRBS,WGBS
+Classifier: Programming Language :: Python :: 3
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.5
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
+Requires-Dist: weblogo
+Requires-Dist: bx-python
+Requires-Dist: pandas
+Requires-Dist: umap-learn
+Requires-Dist: fancyimpute
+
+## Install CpGtools using [pip](https://pip.pypa.io/en/stable/)
+
+1. (Optional) Create Virtual Environments (Note: `venv` is available in Python 3.3 and later. You can also use [virtualenv](https://packaging.python.org/en/latest/key_projects/#virtualenv))
+
+ `$ python3 -m venv my_env` (will create a directory called my_env)
+ 
+ `$ source my_env/bin/activate`
+
+2. Install CpGtools
+
+ `$ pip install cpgtools`
+ 
+ or
+ 
+ `$ pip install git+https://github.com/liguowang/cpgtools.git`
+
+3. Upgrade
+
+ `$ pip install cpgtools --upgrade`
+
+4. Uninstall
+
+ `pip -y uninstall cpgtools`
+
+## Documentation
+
+https://cpgtools.readthedocs.io/en/latest/

cpgtools-2.0.2.dist-info/RECORD

@@ -0,0 +1,82 @@
+cpgmodule/BED.py,sha256=ZNAhGZPFMFD4UpVwGTDOM0hMLnfXF52zerdMb21sH6s,12675
+cpgmodule/MI.py,sha256=pkUWzKXYeyRuGsGKZdFVxHzFWikkuJavdQ_4fsnN3U4,8649
+cpgmodule/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cpgmodule/_version.py,sha256=tATvJM5shAzfspHYjdVwpV2w3-gDA119NlEYi5X2lFY,22
+cpgmodule/cgID.py,sha256=DLG5Djm6JP0d6MiFvP_keUXv_rYxESWrISuVClTs8kw,16017914
+cpgmodule/extend_bed.py,sha256=sjRxbRJFRumjYHwd6_AMTAYBG29yXQPYp1lDjTv2Q_Q,4648
+cpgmodule/imotif.py,sha256=j7_MQFnowGsVTGCRQHHLUnEzSD0HehZPEHKKZ68Jv24,9227
+cpgmodule/ireader.py,sha256=NRTdFnQvd1AEkYchfgvTVTixBVwUjn8xNyswc0OWU1Q,720
+cpgmodule/methylClock.py,sha256=HyMk3vpVwR3yrkLCPv9fVJs6JCeSchbJEBe7i69jdSs,1202
+cpgmodule/padjust.py,sha256=mvbQ9_crn_S39yvWrv_JPoU5OxZGHaw7cV3deBxTPdk,2389
+cpgmodule/region2gene.py,sha256=iuSYa2-ki-qbL1TqqAlTXGT7g-j1uNIA1y7hzMwVM2U,5347
+cpgmodule/utils.py,sha256=NgKT3aJlRT5pQKKO3_e0WB2_u93pY13F-k-r0pvgKno,16095
+cpgmodule/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cpgtools-2.0.2.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
+cpgtools-2.0.2.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
+cpgtools-2.0.2.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
+cpgtools-2.0.2.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
+cpgtools-2.0.2.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
+cpgtools-2.0.2.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
+cpgtools-2.0.2.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
+cpgtools-2.0.2.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
+cpgtools-2.0.2.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
+cpgtools-2.0.2.data/scripts/beta_PCA.py,sha256=cRlqGC5CQlpsmzhAwy2AoI4_lLwjFh_rvn7ObNbHgYg,7155
+cpgtools-2.0.2.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
+cpgtools-2.0.2.data/scripts/beta_imputation.py,sha256=o7wM_iHFwhxjRAMQ5_fCxgAfO9VYe48O9dY4BeZF2wA,28928
+cpgtools-2.0.2.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
+cpgtools-2.0.2.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
+cpgtools-2.0.2.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
+cpgtools-2.0.2.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
+cpgtools-2.0.2.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
+cpgtools-2.0.2.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
+cpgtools-2.0.2.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
+cpgtools-2.0.2.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
+cpgtools-2.0.2.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
+cpgtools-2.0.2.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
+cpgtools-2.0.2.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
+cpgtools-2.0.2.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
+cpgtools-2.0.2.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
+cpgtools-2.0.2.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
+cpgtools-2.0.2.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
+cpgtools-2.0.2.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
+cpgtools-2.0.2.data/scripts/dmc_ttest.py,sha256=jOW0el_NeJlBuF91wKN2UHnu7phoP0OPrKCNCaOAQBs,6704
+cpgtools-2.0.2.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
+impyute/__init__.py,sha256=Q07nw2fDjLm_c3EQWMpSo8nZCfC-fvs2lpRG5uha-gg,87
+impyute/contrib/__init__.py,sha256=DgGgN0iBoMfHjzr9edz-ZgtJ2KeyIDlyV1t8hxhcM2c,209
+impyute/contrib/compare.py,sha256=psWygE7PD4Cky4MoTJLAgjaEkTXwqemv3NTKkKVaapo,2852
+impyute/contrib/count_missing.py,sha256=KkCpYeuDP5jRxCcURJbne_k-7Zq1k31oq2aFHpqygx8,742
+impyute/contrib/describe.py,sha256=LI6Xage19-DEEDZVNqaaOjemRAVqVkSlH4mxjjubw-A,2033
+impyute/cs/__init__.py,sha256=ArkuAVHm0z4jl3_UK_FUBF8i2vZUvAZpfVFyryUTm18,373
+impyute/cs/buck_iterative.py,sha256=ceoQ2ij64pXHy7NszErTTRb9h2wctF0CMBexhc6YZSA,3009
+impyute/cs/central_tendency.py,sha256=xHwTVeDL-N-O5refvP536FiVEDODR7s-cgX2Ao9LsfI,2127
+impyute/cs/em.py,sha256=SwvVNMYK3llATR2r1baVCA0hy_fwJIkGD110du9Woos,1631
+impyute/cs/fast_knn.py,sha256=CI4RKMcrbXPi7izUtWo-lnq1BuLYwl8bvbx62dj8Qn0,6246
+impyute/cs/random.py,sha256=-Ti4BwMwUGdsciKTp8OVAgYK6TzGP-R4Nw62UY_xqAs,594
+impyute/dataset/__init__.py,sha256=GK-ktaf86PLZOUlO_oOhvc-55SX1YFLcpjcpgf7a87c,192
+impyute/dataset/base.py,sha256=bNYszhYP62fSeDe8w_Ij4yhEf-dv6NiNGcCdC22OkuY,4445
+impyute/dataset/corrupt.py,sha256=uGCnpofJWfWZYBucQMrwT9yOSpEQAaZSG010Jv6ks1I,1491
+impyute/deletion/__init__.py,sha256=ztemVB8Q6LRaxSv8DDdFzZlGUVUQbsVRA7gvcs_vMhM,124
+impyute/deletion/complete_case.py,sha256=2xBhqNOSmEeW-sBQvl3TVJCcf2Ybmkr8HXNk9xrQ2J0,395
+impyute/ops/__init__.py,sha256=ZP_rQQ0qATGEibUA9I8D1JfD1kRT2Xqw8SsOMPIddog,275
+impyute/ops/error.py,sha256=lyXJcIDyfdrj_JJbsEI18z-t4UKi1mpLTyt3iS2YvTs,226
+impyute/ops/inverse_distance_weighting.py,sha256=88hmyc-dWltP66MbjrW-VHBcVgPOI0V0BkrV30B-Lyc,1017
+impyute/ops/matrix.py,sha256=-eniwqvbvwXNrYw8PmIMD95uMcPMq6HE6OBOyjzR-Vk,837
+impyute/ops/testing.py,sha256=3ZRVL1sc5IIQLPW2GrD6-lF4_nVnSLo7SBW4rfaOMLA,415
+impyute/ops/util.py,sha256=Tcm8reCrWQf8btKRP5StawBL1UV_GOBWmzy1NYDcPbY,2204
+impyute/ops/wrapper.py,sha256=bQj3r9WsZxqNw51y3OobyyXPPxCeISUv2jb-Ga2C_-M,6022
+impyute/ts/__init__.py,sha256=veePCYSBfo1t5Ahh3wrVCNveizcniXZYhjyS7ahkIhI,145
+impyute/ts/locf.py,sha256=qusLWfBrepKzFIkeGxIS0S5KnqRgZde2CV6mcF5nf4c,1876
+impyute/ts/moving_window.py,sha256=G3Z4ohhqZXAVPflptuOhktwucbW3tg8FySb7gTtBraE,4991
+missingpy/__init__.py,sha256=H_yX0CtfoG2UaJPRcoZKv0AFhi4n-1hHmfIwfqQXoPk,96
+missingpy/knnimpute.py,sha256=WxniKg6-3pvwJa9mipiCZBqkRL_GGHUcxDu-7b57x3k,13456
+missingpy/missforest.py,sha256=UYRf2YANPwxvRPruN3P6xlhJ5JPZB1x8o4xVhYfIp74,24696
+missingpy/pairwise_external.py,sha256=XU_vW-rMCPD3aH9k0UrP_p90QUHDZqe3QZPoOQmu2vo,13221
+missingpy/utils.py,sha256=sMU4OGHPvRgReT8e_HqGCYvjAJZkE_qlAPDzLo-_M6U,4360
+missingpy/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+missingpy/tests/test_knnimpute.py,sha256=rR1OPZ4-IzcIKgWmSEN7UEPvVSRwJe0KU_wTxPr46k0,17527
+missingpy/tests/test_missforest.py,sha256=5YfKZf_xdy9RcXmnlFz7cJDqdnspJDzzrxLnVVWJi3A,13725
+cpgtools-2.0.2.dist-info/LICENSE,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
+cpgtools-2.0.2.dist-info/METADATA,sha256=EfdjaKSMi75Wo041GCIx9gd9JjFf7rULeCkAhw2uuqY,2943
+cpgtools-2.0.2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+cpgtools-2.0.2.dist-info/top_level.txt,sha256=L6IX1ORvZ1JssvdU8qOtU99-vbMK9ZSIgYg4zH-rL5Y,28
+cpgtools-2.0.2.dist-info/RECORD,,