cpgtools 1.12.0__tar.gz → 2.0.2__tar.gz

cpgtools-2.0.2/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-1.12.0 → cpgtools-2.0.2}/MANIFEST.in

@@ -1,10 +1,11 @@
 include MANIFEST.in
 include README.md
 include PKG-INFO
-include LICENSE.txt
+include LICENSE
 
 include distribute_setup.py
 recursive-include lib *.pyx
 recursive-include lib *.py
+recursive-include lib *.pkl
 recursive-include bin *
 recursive-include doc *

cpgtools-2.0.2/PKG-INFO

@@ -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/README.md

@@ -0,0 +1,27 @@
+## 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/pyproject.toml

@@ -0,0 +1,48 @@
+#Declaring the build backend
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+#Project's meta data
+[project]
+version = "2.0.2"
+name = "cpgtools"
+authors = [
+  {name="Liguo Wang", email="wangliguo78@gmail.com"},
+]
+maintainers = [
+  {name = "Liguo Wang", email = "wangliguo78@gmail.com"}
+]
+description = "Tools to analyze and visualize DNA methylation data"
+readme = "README.md"
+license = {file = "LICENSE"}
+requires-python = ">=3.5"
+
+dependencies = [
+	"numpy",
+	"scipy",
+	"scikit-learn",
+	"weblogo",
+	"bx-python",
+	"pandas",
+	"umap-learn",
+	"fancyimpute",
+]
+
+classifiers=[
+	"Programming Language :: Python :: 3",
+	'Development Status :: 4 - Beta',
+	"License :: OSI Approved :: MIT License",
+	'Environment :: Console',
+	'Intended Audience :: Science/Research',
+	'Operating System :: MacOS :: MacOS X',
+	'Operating System :: POSIX',
+	'Topic :: Scientific/Engineering :: Bio-Informatics',
+]
+
+keywords = ["DNA methylation", "EPIC", "450K", "850K", "935K", "RRBS", "WGBS"]
+
+[project.urls]
+Documentation = "https://cpgtools.readthedocs.io/en/latest/index.html"
+Repository = "https://github.com/liguowang/cpgtools.git"
+

{cpgtools-1.12.0/bin → cpgtools-2.0.2/scripts}/CpG_aggregation.py

@@ -34,6 +34,7 @@ import numpy as np
 from scipy.stats import binom
 
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
@@ -44,7 +45,6 @@ __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/bin → cpgtools-2.0.2/scripts}/CpG_anno_position.py

@@ -18,6 +18,7 @@ import subprocess
 import numpy as np
 from os.path import basename
 from optparse import OptionParser
+from cpgmodule._version import __version__
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
@@ -28,7 +29,6 @@ __author__ = "Liguo Wang"
 __copyright__ = "Copyleft"
 __credits__ = []
 __license__ = "GPL"
-__version__="0.1.9"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-1.12.0/bin → cpgtools-2.0.2/scripts}/CpG_anno_probe.py

@@ -10,13 +10,12 @@ import sys,os
 from optparse import OptionParser
 from cpgmodule import ireader
 from cpgmodule.utils import *
-
+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"
@@ -76,8 +75,11 @@ def main():
 	for l in ireader.reader(options.input_file):
 		line_num += 1
 		f = l.split()
-		if (line_num == 1 and options.header):
-			print (l + '\t' +  '\t'.join(header), file=OUT)
+		if line_num == 1:
+			if options.header:
+				print (l + '\t' +  '\t'.join(header), file=OUT)
+			else:
+				print ('\t'.join(['NA']*len(f)) + '\t' +  '\t'.join(header), file=OUT)
 		else:
 			if options.probe_col >= len(f):
 				print ("Error: column ID must be smaller than %d!" % len(f), file=sys.stderr)

{cpgtools-1.12.0/bin → cpgtools-2.0.2/scripts}/CpG_density_gene_centered.py

@@ -19,12 +19,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule import extend_bed
+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/bin → cpgtools-2.0.2/scripts}/CpG_distrb_chrom.py

@@ -14,12 +14,12 @@ import numpy as np
 from optparse import OptionParser
 from cpgmodule import ireader
 from cpgmodule.utils import *
+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/bin → cpgtools-2.0.2/scripts}/CpG_distrb_gene_centered.py

@@ -34,12 +34,12 @@ from optparse import OptionParser
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
+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/bin → cpgtools-2.0.2/scripts}/CpG_distrb_region.py

@@ -23,18 +23,16 @@ import sys,os
 import collections
 import subprocess
 import numpy as np
-#import re
 from optparse import OptionParser
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
-
+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/bin → cpgtools-2.0.2/scripts}/CpG_logo.py

@@ -17,12 +17,12 @@ from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule import BED
 from cpgmodule.imotif import PSSM
+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/bin → cpgtools-2.0.2/scripts}/CpG_to_gene.py

@@ -34,12 +34,12 @@ from optparse import OptionParser
 from cpgmodule import ireader
 from cpgmodule.utils import *
 from cpgmodule.region2gene import *
+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/bin → cpgtools-2.0.2/scripts}/beta_PCA.py

@@ -32,6 +32,7 @@ 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.decomposition import PCA
@@ -40,15 +41,15 @@ __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]
 
@@ -86,27 +87,30 @@ def main():
 	df1 = pd.read_csv(options.input_file, index_col = 0, sep="\t")
 	
 	#remove NA and transpose
-	df2 = df1.dropna(axis=0, how='any')
-	printlog("%d rows with missing values were removed." % (len(df1) - len(df2)))
-	#print (df2.head())
-	
-	printlog("Transposing data frame ...")
-	df2 = df2.T
-	#print (df2.head()) 
-	
-	printlog("Standarizing values ...")
-	x = df2.values
-	x = StandardScaler().fit_transform(x)
-	
+	df2 = df1.dropna(axis=0, how='any').T
+	printlog("%d rows with missing values were removed." % (len(df1.index) - len(df2.columns)))
+
 	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()	
+	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))
@@ -116,9 +120,9 @@ def main():
 	pca = PCA(n_components = options.n_components, random_state = 0)
 	principalComponents = pca.fit_transform(x)	
 	pca_names = [str(i)+str(j) for i,j in zip(['PC']*options.n_components,range(1,options.n_components+1))]
-	principalDf = pd.DataFrame(data = principalComponents, columns = pca_names, index = df2.index)	
+	principalDf = pd.DataFrame(data = principalComponents, columns = pca_names, index = used_df.index)	
 	
-	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 PCA results to file: \"%s\" ..." % (options.out_file + '.PCA.tsv'))
@@ -133,18 +137,22 @@ def main():
 	
 	print ('pdf(file=\"%s\", width=8, height=8)' % (options.out_file + '.PCA.pdf'),file=ROUT)
 	print ('')
-	print ('d = read.table(file=\"%s\", sep="\\t", header=TRUE,  comment.char = "", stringsAsFactors=FALSE)' % (options.out_file + '.PCA.tsv'), file=ROUT)
+	print ('d = read.table(file=\"%s\", sep="\\t", header=TRUE,  comment.char = "", stringsAsFactors=FALSE)' 
+		% (options.out_file + '.PCA.tsv'), file=ROUT)
 	print ('attach(d)', file=ROUT)
 	if options.plot_alpha:
 		print ('library(scales)', file=ROUT)
-		print ('plot(PC1, PC2, col = alpha(Colors, %f), pch=%d, cex=1.5, main="PCA 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="PCA 2D map", xlab="PC1 (var. explained: %.2f%%)", ylab="PC2 (var. explained: %.2f%%)")' 
+			% (options.plot_alpha, pch[options.plot_char], pca_vars[0]*100, pca_vars[1]*100), file=ROUT)
 	else:
-		print ('plot(PC1, PC2, col = Colors, pch=%d, cex=1.2, main="PCA 2D map")' % pch[options.plot_char], file=ROUT)	
+		print ('plot(PC1, PC2, col = Colors, pch=%d, cex=1.2, main="PCA 2D map", xlab="PC1 (var. explained: %.2f%%)", ylab="PC2 (var. explained: %.2f%%)")' 
+			% (pca_vars[0]*100, pca_vars[1]*100, pch[options.plot_char], pca_vars[0]*100, pca_vars[1]*100), 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)
+	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)
 	
 	
 	print ('dev.off()', file=ROUT)

{cpgtools-1.12.0/bin → cpgtools-2.0.2/scripts}/beta_UMAP.py

@@ -32,6 +32,7 @@ import pandas as pd
 import subprocess
 from optparse import OptionParser
 from cpgmodule.utils import *
+from cpgmodule._version import __version__
 from sklearn.preprocessing import StandardScaler
 #import datatable as dt
 #import seaborn as sns
@@ -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]
 
@@ -99,26 +100,28 @@ def main():
 	df1 = pd.read_csv(options.input_file, index_col = 0, sep="\t")
 	
 	#remove NA and transpose
-	df2 = df1.dropna(axis=0, how='any')
-	printlog("%d rows with missing values were removed." % (len(df1) - len(df2)))
-	#print (df2.head())
-	
-	printlog("Transposing data frame ...")
-	df2 = df2.T
-	#print (df2.head()) 
-	
-	printlog("Standarizing values ...")
-	x = df2.values
-	x = StandardScaler().fit_transform(x)
+	df2 = df1.dropna(axis=0, how='any').T
+	printlog("%d rows with missing values were removed." % (len(df1.index) - len(df2.columns)))
 	
 	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()	
+	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
@@ -133,9 +136,9 @@ def main():
 	#pca = PCA(n_components = options.n_components, random_state = 0)
 	#principalComponents = pca.fit_transform(x)	
 	pca_names = [str(i)+str(j) for i,j in zip(['UMAP']*options.n_components,range(1,options.n_components+1))]
-	principalDf = pd.DataFrame(data = principalComponents, columns = pca_names, index = df2.index)	
+	principalDf = pd.DataFrame(data = principalComponents, columns = pca_names, index = used_df.index)	
 	
-	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 UMAP results to file: \"%s\" ..." % (options.out_file + '.UMAP.tsv'))
@@ -146,18 +149,22 @@ def main():
 	
 	print ('pdf(file=\"%s\", width=8, height=8)' % (options.out_file + '.UMAP.pdf'),file=ROUT)
 	print ('')
-	print ('d = read.table(file=\"%s\", sep="\\t", header=TRUE,  comment.char = "", stringsAsFactors=FALSE)' % (options.out_file + '.UMAP.tsv'), file=ROUT)
+	print ('d = read.table(file=\"%s\", sep="\\t", header=TRUE,  comment.char = "", stringsAsFactors=FALSE)' 
+		% (options.out_file + '.UMAP.tsv'), file=ROUT)
 	print ('attach(d)', file=ROUT)
 	if options.plot_alpha:
 		print ('library(scales)', file=ROUT)
-		print ('plot(UMAP1, UMAP2, col = alpha(Colors, %f), pch=%d, cex=1.5, main="UMAP 2D map", xlab="UMAP_1", ylab="UMAP_2")' % (options.plot_alpha, pch[options.plot_char]), file=ROUT)
+		print ('plot(UMAP1, UMAP2, col = alpha(Colors, %f), pch=%d, cex=1.5, main="UMAP 2D map", xlab="UMAP_1", ylab="UMAP_2")' 
+			% (options.plot_alpha, pch[options.plot_char]), file=ROUT)
 	else:
-		print ('plot(UMAP1, UMAP2, col = Colors, pch=%d, cex=1.2, main="UMAP 2D map", xlab="UMAP_1", ylab="UMAP_2")' % pch[options.plot_char], file=ROUT)	
+		print ('plot(UMAP1, UMAP2, col = Colors, pch=%d, cex=1.2, main="UMAP 2D map", xlab="UMAP_1", ylab="UMAP_2")' 
+			% pch[options.plot_char], file=ROUT)	
 	
 	if options.text_label:
 		print ('text(UMAP1, UMAP2, 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)
+	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)
 	
 	
 	print ('dev.off()', file=ROUT)