cpgtools 2.0.0__py3-none-any.whl → 2.0.3__py3-none-any.whl

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __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-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"

{cpgtools-2.0.0.data → cpgtools-2.0.3.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__="2.0.0"
 __maintainer__ = "Liguo Wang"
 __email__ = "wang.liguo@mayo.edu"
 __status__ = "Development"
@@ -189,7 +189,7 @@ def main():
 			else:
 				continue
 		line_num += 1
-
+	
 	printlog("Perfrom Benjamini-Hochberg (aka FDR) correction ...")
 	adjusted_p = {}
 	q_list =  padjust.multiple_testing_correction(p_list)
@@ -204,6 +204,10 @@ def main():
 		else:
 			f = l.split()
 			probe_ID = f[0]
+			if probe_ID in delta_beta:
+				pass
+			else:
+				delta_beta[probe_ID] = 'n/a'
 			try:
 				print (l + '\t' + str(delta_beta[probe_ID]) + '\t' + adjusted_p[probe_ID], file=FOUT)
 			except: