cpgtools 2.0.3__py3-none-any.whl → 2.0.4__py3-none-any.whl

{cpgtools-2.0.3.data → cpgtools-2.0.4.data}/scripts/beta_PCA.py

@@ -73,7 +73,10 @@ def main():
 		print (__doc__)
 		parser.print_help()
 		sys.exit(101)
-	
+	if not (options.group_file):
+		print (__doc__)
+		parser.print_help()
+		sys.exit(101)	
 	if not (options.out_file):
 		print (__doc__)
 		parser.print_help()

cpgtools-2.0.4.data/scripts/beta_remove_batch_effects.py

@@ -0,0 +1,138 @@
+#!python
+
+"""
+Description
+-----------
+This program corrects batch effect.
+
+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 batch file
+-------------------------------
+Sample,Group
+Sample_01,plate_1
+Sample_02,plate_1
+Sample_03,plate_2
+Sample_04,plate_2
+...
+
+Notes
+-----
+* Rows with missing values will be removed
+
+"""
+
+
+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
+from collections import Counter
+from combat.pycombat import pycombat
+import matplotlib.pyplot as plt
+import matplotlib.colors as mcolors
+
+__author__ = "Liguo Wang"
+__copyright__ = "Copyleft"
+__credits__ = []
+__license__ = "GPL"
+__maintainer__ = "Liguo Wang"
+__email__ = "wang.liguo@mayo.edu"
+__status__ = "Development"
+
+def pick_colors(n):
+	my_colors = list(mcolors.CSS4_COLORS.keys())
+	if n > len(my_colors):
+		print ("Too many colors requested", file = sys.stderr)
+		sys.exit()
+	return my_colors[0:n]
+
+def box_plot(df, s_colors,  out_png, ylab="Beta values", title=""):
+	s_names = df.columns
+	fig, ax = plt.subplots()
+	bplot = ax.boxplot(df, patch_artist=True, tick_labels = s_names)
+	for patch, color in zip(bplot['boxes'], s_colors):
+		patch.set_facecolor(color)
+	ax.set_xticklabels(s_names, rotation='vertical')
+	plt.ylabel(ylab)
+	plt.title(title)
+	plt.savefig(out_png)
+
+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("-g","--group",action="store",type="string",dest="group_file",help="Comma-separated group file defining the batch groups of each sample.")
+	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.group_file):
+		print (__doc__)
+		parser.print_help()
+		sys.exit(101)	
+	if not (options.out_file):
+		print (__doc__)
+		parser.print_help()
+		sys.exit(103)	
+
+	beta_out = options.out_file + '.combat.tsv'
+	beta_boxplot_before = options.out_file + '.boxplot.png'
+	beta_boxplot_after = options.out_file + '.boxplot_combat.png'
+	
+	printlog("Reading input file: \"%s\" ..." % (options.input_file))
+	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.index) - len(df2.index)))
+
+	printlog("Reading group file: \"%s\" ..." % (options.group_file))
+	group = pd.read_csv(options.group_file, index_col=0, names=['Sample_ID', 'Group_ID'])
+	#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/batch \"%s\" contains %d samples" % (options.group_file, len(group.index)))
+	
+	# a list of unique group names, and their frequencies
+	group_info = Counter(group['Group_ID'])
+	print(list(group['Group_ID']))
+	# a list of unique colors
+	color_names = pick_colors(len(group_info))	
+	color_list = []
+	for name,count in zip(color_names, list(group_info.values())):
+		color_list.extend([name]*count)
+
+	printlog("Generate boxplot before correction. Save to '%s'" % beta_boxplot_before)
+	box_plot(df2, s_colors=color_list, out_png=beta_boxplot_before, title="Before batch effects correction")
+
+	# remove batch effect
+	printlog("Removing batch effect ...")
+	df_corrected = pycombat(df2, list(group['Group_ID']))
+	
+
+	df_corrected.to_csv(beta_out,sep="\t")
+
+	printlog("Generate boxplot after correction. Save to '%s'" % beta_boxplot_after)
+	box_plot(df_corrected, s_colors=color_list, out_png=beta_boxplot_after, title="After batch effects correction")
+
+
+if __name__=='__main__':
+	main()	

{cpgtools-2.0.3.dist-info → cpgtools-2.0.4.dist-info}/METADATA

@@ -1,35 +1,15 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: cpgtools
-Version: 2.0.3
+Version: 2.0.4
 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.
-        
+License-Expression: MIT
 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
@@ -37,7 +17,7 @@ Classifier: Operating System :: POSIX
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.5
 Description-Content-Type: text/markdown
-License-File: LICENSE
+License-File: LICENSE.txt
 Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: scikit-learn
@@ -46,6 +26,8 @@ Requires-Dist: bx-python
 Requires-Dist: pandas
 Requires-Dist: umap-learn
 Requires-Dist: fancyimpute
+Requires-Dist: pycombat
+Dynamic: license-file
 
 ## Install CpGtools using [pip](https://pip.pypa.io/en/stable/)
 

{cpgtools-2.0.3.dist-info → cpgtools-2.0.4.dist-info}/RECORD

@@ -30,36 +30,38 @@ cpgmodule/data/Ped_Wu.pkl,sha256=gjXtpdpQ8QVJs1I6UM-VPAvQjNd-JDoy5DzDL-gP-Cg,292
 cpgmodule/data/Zhang_BLUP.pkl,sha256=dpH0L3qTxMAJ50XtTeNMmqx1khZkZyrH204E37fE37E,7038226
 cpgmodule/data/Zhang_EN.pkl,sha256=RFEOmBQGXZvIwQ7tOYT8itOPU87V2Y02vJA2PfY6TnI,11844
 cpgmodule/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cpgtools-2.0.3.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
-cpgtools-2.0.3.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
-cpgtools-2.0.3.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
-cpgtools-2.0.3.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
-cpgtools-2.0.3.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
-cpgtools-2.0.3.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
-cpgtools-2.0.3.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
-cpgtools-2.0.3.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
-cpgtools-2.0.3.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
-cpgtools-2.0.3.data/scripts/beta_PCA.py,sha256=cRlqGC5CQlpsmzhAwy2AoI4_lLwjFh_rvn7ObNbHgYg,7155
-cpgtools-2.0.3.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
-cpgtools-2.0.3.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
-cpgtools-2.0.3.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
-cpgtools-2.0.3.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
-cpgtools-2.0.3.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
-cpgtools-2.0.3.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
-cpgtools-2.0.3.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
-cpgtools-2.0.3.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
-cpgtools-2.0.3.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
-cpgtools-2.0.3.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
-cpgtools-2.0.3.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
-cpgtools-2.0.3.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
-cpgtools-2.0.3.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
-cpgtools-2.0.3.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
-cpgtools-2.0.3.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
-cpgtools-2.0.3.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
-cpgtools-2.0.3.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
-cpgtools-2.0.3.data/scripts/dmc_ttest.py,sha256=DDmWi1udo1gqOAQvFTeRxhIJuAgEmakSNU7P4LKTT7U,6786
-cpgtools-2.0.3.data/scripts/predict_missing.py,sha256=pNSfOD9i7LNLG9BGa80W2-bsCi6qcUlIwoiLnBLbPlo,32465
-cpgtools-2.0.3.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
+cpgtools-2.0.4.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
+cpgtools-2.0.4.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
+cpgtools-2.0.4.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
+cpgtools-2.0.4.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
+cpgtools-2.0.4.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
+cpgtools-2.0.4.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
+cpgtools-2.0.4.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
+cpgtools-2.0.4.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
+cpgtools-2.0.4.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
+cpgtools-2.0.4.data/scripts/beta_PCA.py,sha256=TooY1jzEUE24a8lkwR33mcT7NR18RHXMd3IBPk0j1PE,7240
+cpgtools-2.0.4.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
+cpgtools-2.0.4.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
+cpgtools-2.0.4.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
+cpgtools-2.0.4.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
+cpgtools-2.0.4.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
+cpgtools-2.0.4.data/scripts/beta_remove_batch_effects.py,sha256=KFvttTojLaXHjf-3Q5xnv94P_elWId6HUnbKz3N8Qds,4349
+cpgtools-2.0.4.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
+cpgtools-2.0.4.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
+cpgtools-2.0.4.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
+cpgtools-2.0.4.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
+cpgtools-2.0.4.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
+cpgtools-2.0.4.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
+cpgtools-2.0.4.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
+cpgtools-2.0.4.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
+cpgtools-2.0.4.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
+cpgtools-2.0.4.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
+cpgtools-2.0.4.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
+cpgtools-2.0.4.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
+cpgtools-2.0.4.data/scripts/dmc_ttest.py,sha256=DDmWi1udo1gqOAQvFTeRxhIJuAgEmakSNU7P4LKTT7U,6786
+cpgtools-2.0.4.data/scripts/predict_missing.py,sha256=pNSfOD9i7LNLG9BGa80W2-bsCi6qcUlIwoiLnBLbPlo,32465
+cpgtools-2.0.4.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
+cpgtools-2.0.4.dist-info/licenses/LICENSE.txt,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
 impyute/__init__.py,sha256=Q07nw2fDjLm_c3EQWMpSo8nZCfC-fvs2lpRG5uha-gg,87
 impyute/contrib/__init__.py,sha256=DgGgN0iBoMfHjzr9edz-ZgtJ2KeyIDlyV1t8hxhcM2c,209
 impyute/contrib/compare.py,sha256=psWygE7PD4Cky4MoTJLAgjaEkTXwqemv3NTKkKVaapo,2852
@@ -94,8 +96,7 @@ 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-2.0.3.dist-info/LICENSE,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
-cpgtools-2.0.3.dist-info/METADATA,sha256=N1FqwvSLFmK2DvVyYY4oHcqbo6Vj1B4ii48vESlNPkU,2943
-cpgtools-2.0.3.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-cpgtools-2.0.3.dist-info/top_level.txt,sha256=L6IX1ORvZ1JssvdU8qOtU99-vbMK9ZSIgYg4zH-rL5Y,28
-cpgtools-2.0.3.dist-info/RECORD,,
+cpgtools-2.0.4.dist-info/METADATA,sha256=bE5Ko9iBnYkBf5embxo-7K39bEXk2-7i67miII00eu4,1730
+cpgtools-2.0.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cpgtools-2.0.4.dist-info/top_level.txt,sha256=L6IX1ORvZ1JssvdU8qOtU99-vbMK9ZSIgYg4zH-rL5Y,28
+cpgtools-2.0.4.dist-info/RECORD,,

{cpgtools-2.0.3.dist-info → cpgtools-2.0.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any