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

cpgmodule/_version.py

@@ -0,0 +1 @@
+__version__ = "2.0.2"

cpgmodule/methylClock.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Nov 25 10:55:14 2022
+
+@author: Liguo Wang
+"""
+from cpgmodule import ireader
+#import sys,os
+
+class MethylSig():
+	"""
+	Pack DNA methylation signature file into object.
+
+	>>> from cpgmodule import methylClock
+	>>> a = methylClock.MethylAge(signature_file = 'coefBlup.tsv', signature_name = 'BLUP', signature_info="")
+	>>> a.name
+	'BLUP'
+	>>> a.Intercept
+	91.15396
+	>>> a.ncpg
+	319607
+	"""
+
+	def __init__(self, signature_file, signature_name, tissues = [], unit = '', signature_info = '', reference = '', pub_link = '', method = ''):
+		self.name = signature_name
+		self.info = signature_info
+		self.tissues = tissues
+		self.unit = unit
+		self.coef = {}
+		self.cpgs = []
+		self.ncpg = 0
+		self.Intercept = 0.0
+		self.ref = reference
+		self.pubmed = pub_link
+		self.method = method
+		for l in ireader.reader(signature_file):
+			if l.startswith('#'):
+				continue
+			f = l.split()
+			if l.startswith('Intercept'):
+				try:
+					self.Intercept = float(f[1])
+				except:
+					self.Intercept = 0.0
+			else:
+				self.cpgs.append(f[0])
+				self.ncpg  += 1
+				try:
+					self.coef[f[0]] = float(f[1])
+					#self.ncpg  += 1
+				except:
+					continue

cpgmodule/utils.py

@@ -5,6 +5,8 @@ from time import strftime
 from bx.intervals import *
 import numpy as np
 from cpgmodule import ireader
+import logging
+
 
 def revcomp(dna):
 	'''reverse complement DNA sequences'''
@@ -266,7 +268,7 @@ def count_over_range(lst, cpg_ranges):
 		total_count += len(tmp)
 	return(total_size,total_count)
 
-def read_grp_file1(gfile):
+def read_grp_file1(gfile,na_lab="NA"):
 	'''
 	read group file. Group file define the biological groups of data matrix file.
 	(1) It must has header
@@ -292,6 +294,8 @@ def read_grp_file1(gfile):
 		l = l.replace(' ','')
 		line_num += 1
 		f = l.split(',')
+		if f[1] == na_lab:
+			continue
 		if len(f) < 2:
 			print ("Group fle must have 2 columns!", file=sys.stderr)
 			sys.exit(1)
@@ -602,4 +606,37 @@ def read_CpG_bed(cpgfile,genefile, bin_count = 100):
 
 	return np.array(cpg_profile).means(axis=0)
 """
+def config_log(switch, logfile=None):
+    """
+    Configureing the logging module.
+
+    Parameters
+    ----------
+    switch : bool
+        Debugging switch.
+    Returns
+    -------
+    None.
+
+    """
+    if switch is True:
+        if logfile is None:
+            logging.basicConfig(
+                format="%(asctime)s [%(levelname)s]  %(message)s",
+                datefmt='%Y-%m-%d %I:%M:%S', level=logging.DEBUG)
+        else:
+            logging.basicConfig(
+                filename=logfile,
+                format="%(asctime)s [%(levelname)s]  %(message)s",
+                datefmt='%Y-%m-%d %I:%M:%S', level=logging.DEBUG)
+    else:
+        if logfile is None:
+            logging.basicConfig(
+                format="%(asctime)s [%(levelname)s]  %(message)s",
+                datefmt='%Y-%m-%d %I:%M:%S', level=logging.INFO)
+        else:
+            logging.basicConfig(
+                filename=logfile,
+                format="%(asctime)s [%(levelname)s]  %(message)s",
+                datefmt='%Y-%m-%d %I:%M:%S', level=logging.INFO)
 

{cpgtools-1.12.0.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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.data → cpgtools-2.0.2.data}/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)