In [1]:
%matplotlib inline

In [2]:
import glob
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib
pd.set_option('display.max_columns', 50) # print all rows


import os
os.chdir('/Users/evanbiederstedt/Downloads/RRBS_data_files')

import statsmodels.api as sm

In [3]:
"""
Normal_B_regions.csv
pcell_regions.csv
trito_regions.csv
mcell_regions.csv
CD19cell_regions.csv
cw154_regions.csv
"""


Out[3]:
'\nNormal_B_regions.csv\npcell_regions.csv\ntrito_regions.csv\nmcell_regions.csv\nCD19cell_regions.csv\ncw154_regions.csv\n'

In [6]:
normalB = pd.read_csv("Normal_B_regions.csv")
mcell = pd.read_csv("mcell_regions.csv")
pcell = pd.read_csv("pcell_regions.csv")
cd19cell = pd.read_csv("CD19cell_regions.csv")
trito = pd.read_csv("trito_regions.csv")
cw154 = pd.read_csv("cw154_regions.csv")

In [9]:
print(normalB.shape)
print(mcell.shape)
print(pcell.shape)
print(cd19cell.shape)
print(trito.shape)
print(cw154.shape)


(136, 39)
(88, 39)
(90, 39)
(89, 39)
(44, 39)
(66, 39)

In [10]:
136 + 88 + 90 + 89


Out[10]:
403

In [11]:
44 + 66


Out[11]:
110

In [37]:
# there are 104 CLL
# there are 342 normal 
#
# 113 normal B

In [38]:
"""
# remove 6 CLL cells

3	RRBS_trito_pool_1_TAAGGCGA.AGGATG.dan.anno
43	RRBS_trito_pool_2_CGTACTAG.TGCTGC.dan.anno
11	RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CTAT..
18	RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GTTG...
29	RRBS_cw154_Tris_protease_CTCTCTAC.CAAGAG.dan.anno
51	RRBS_cw154_Tris_protease_GR_CAGAGAGG.CAAGAG.da..
"""


Out[38]:
'\n3\tRRBS_trito_pool_1_TAAGGCGA.AGGATG.dan.anno\n43\tRRBS_trito_pool_2_CGTACTAG.TGCTGC.dan.anno\n11\tRRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CTAT..\n18\tRRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GTTG...\n29\tRRBS_cw154_Tris_protease_CTCTCTAC.CAAGAG.dan.anno\n51\tRRBS_cw154_Tris_protease_GR_CAGAGAGG.CAAGAG.da..\n'

In [42]:
print(normalB.shape)
print(mcell.shape)
print(pcell.shape)
print(cd19cell.shape)


(136, 39)
(88, 39)
(90, 39)
(89, 39)

In [43]:
# 84 total cd19cell; should be 5 cut


Out[43]:
83

In [44]:
# 70 total pcell; should be 20


Out[44]:
69

In [45]:
# 75 total mcell; should be 13 cut


Out[45]:
74

In [46]:
# 113 total normal B; should cut 23

In [82]:
84+70+75+113


Out[82]:
342

In [83]:
136-24


Out[83]:
112

In [84]:
"""
# remove 20 pcell
2	RRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.ACGTGG..
13	RRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.GACACG
20	RRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.TATCTC...
21	RRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.TCTCTG..
44	RRBS_NormalBCD19pCD27pcell23_44_CTCTCTAC.TGCTG
45	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ACAAC...
47	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ACGTG
49	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.AGGAT..
51	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ATCGA.
53	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CATGA
55	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CGGTA.
57	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CTCAG.
59	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GCATT...
60	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GCTGC
61	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GGCAT.
63	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GTTGA
65	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.TATCT..
66	RRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.TCTCT...
74	RRBS_NormalBCD19pCD27pcell67_88_GCTACGCT.CAAGA
89	RRBS_NormalBCD19pCD27pcell67_88_GCTACGCT.TGCTG.

# remove 23 normal B cell
3	RRBS_normal_B_cell_A1_24_TAAGGCGA.ACTCAC.dan.anno
9	RRBS_normal_B_cell_A1_24_TAAGGCGA.CCTTCG.dan.anno
14	RRBS_normal_B_cell_A1_24_TAAGGCGA.GCATTC.dan.anno
23	RRBS_normal_B_cell_A1_24_TAAGGCGA.TGCTGC.dan.anno
26	RRBS_normal_B_cell_B1_24_CGTACTAG.ACGTGG.dan.anno
28	RRBS_normal_B_cell_B1_24_CGTACTAG.AGGATG.dan.anno
30	RRBS_normal_B_cell_B1_24_CGTACTAG.ATCGAC.dan.anno
39	RRBS_normal_B_cell_B1_24_CGTACTAG.GCTGCC.dan.anno
57	RRBS_normal_B_cell_C1_24_AGGCAGAA.CCTTCG.dan.anno
60	RRBS_normal_B_cell_C1_24_AGGCAGAA.CTCAGC.dan.anno
69	RRBS_normal_B_cell_C1_24_AGGCAGAA.TCTCTG.dan.anno
75	RRBS_normal_B_cell_D1_24_TCCTGAGC.ATAGCG.dan.anno
79	RRBS_normal_B_cell_D1_24_TCCTGAGC.CCTTCG.dan.anno
82	RRBS_normal_B_cell_D1_24_TCCTGAGC.CTCAGC.dan.anno
87	RRBS_normal_B_cell_D1_24_TCCTGAGC.GTGAGG.dan.anno
91	RRBS_normal_B_cell_D1_24_TCCTGAGC.TCTCTG.dan.anno
97	RRBS_normal_B_cell_G1_22_GGACTCCT.ATAGCG.dan.anno
109	RRBS_normal_B_cell_G1_22_GGACTCCT.GTGAGG.dan.anno
113	RRBS_normal_B_cell_G1_22_GGACTCCT.TCTCTG.dan.anno
123	RRBS_normal_B_cell_H1_22_TAGGCATG.CCTTCG.dan.anno
128	RRBS_normal_B_cell_H1_22_TAGGCATG.GCATTC.dan.anno
132	RRBS_normal_B_cell_H1_22_TAGGCATG.GTTGAG.dan.anno
135	RRBS_normal_B_cell_H1_22_TAGGCATG.TCTCTG.dan.anno


# remove 13 mcell
0	RRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.ACAACC.
4	RRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.AGGATG
10	RRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.CGGTAG..
21	RRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.TCTCTG...
37	RRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.GCTGC.
38	RRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.GGCAT
41	RRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.TAGCG..
45	RRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.ACCGC.
58	RRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GCATT...
59	RRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GCTGC
60	RRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GGCAT.
62	RRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GTTGA.
81	RRBS_NormalBCD19pCD27mcell67_88_CGTACTAG.GCTGC


# remove 5 cd19 cell
17	RRBS_NormalBCD19pcell1_22_TAAGGCGA.GTGAGG.dan...
29	RRBS_NormalBCD19pcell23_44_CGTACTAG.CAAGAG.dan.
40	RRBS_NormalBCD19pcell23_44_CGTACTAG.GTTGAG.dan...
79	RRBS_NormalBCD19pcell67_88_TCCTGAGC.GACACG.dan..
88	RRBS_NormalBCD19pcell67_88_TCCTGAGC.TGCTGC.dan




"""


Out[84]:
'\n# remove 20 pcell\n2\tRRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.ACGTGG..\n13\tRRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.GACACG\n20\tRRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.TATCTC...\n21\tRRBS_NormalBCD19pCD27pcell1_22_TAGGCATG.TCTCTG..\n44\tRRBS_NormalBCD19pCD27pcell23_44_CTCTCTAC.TGCTG\n45\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ACAAC...\n47\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ACGTG\n49\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.AGGAT..\n51\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.ATCGA.\n53\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CATGA\n55\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CGGTA.\n57\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.CTCAG.\n59\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GCATT...\n60\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GCTGC\n61\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GGCAT.\n63\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.GTTGA\n65\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.TATCT..\n66\tRRBS_NormalBCD19pCD27pcell45_66_CAGAGAGG.TCTCT...\n74\tRRBS_NormalBCD19pCD27pcell67_88_GCTACGCT.CAAGA\n89\tRRBS_NormalBCD19pCD27pcell67_88_GCTACGCT.TGCTG.\n\n# remove 23 normal B cell\n3\tRRBS_normal_B_cell_A1_24_TAAGGCGA.ACTCAC.dan.anno\n9\tRRBS_normal_B_cell_A1_24_TAAGGCGA.CCTTCG.dan.anno\n14\tRRBS_normal_B_cell_A1_24_TAAGGCGA.GCATTC.dan.anno\n23\tRRBS_normal_B_cell_A1_24_TAAGGCGA.TGCTGC.dan.anno\n26\tRRBS_normal_B_cell_B1_24_CGTACTAG.ACGTGG.dan.anno\n28\tRRBS_normal_B_cell_B1_24_CGTACTAG.AGGATG.dan.anno\n30\tRRBS_normal_B_cell_B1_24_CGTACTAG.ATCGAC.dan.anno\n39\tRRBS_normal_B_cell_B1_24_CGTACTAG.GCTGCC.dan.anno\n57\tRRBS_normal_B_cell_C1_24_AGGCAGAA.CCTTCG.dan.anno\n60\tRRBS_normal_B_cell_C1_24_AGGCAGAA.CTCAGC.dan.anno\n69\tRRBS_normal_B_cell_C1_24_AGGCAGAA.TCTCTG.dan.anno\n75\tRRBS_normal_B_cell_D1_24_TCCTGAGC.ATAGCG.dan.anno\n79\tRRBS_normal_B_cell_D1_24_TCCTGAGC.CCTTCG.dan.anno\n82\tRRBS_normal_B_cell_D1_24_TCCTGAGC.CTCAGC.dan.anno\n87\tRRBS_normal_B_cell_D1_24_TCCTGAGC.GTGAGG.dan.anno\n91\tRRBS_normal_B_cell_D1_24_TCCTGAGC.TCTCTG.dan.anno\n97\tRRBS_normal_B_cell_G1_22_GGACTCCT.ATAGCG.dan.anno\n109\tRRBS_normal_B_cell_G1_22_GGACTCCT.GTGAGG.dan.anno\n113\tRRBS_normal_B_cell_G1_22_GGACTCCT.TCTCTG.dan.anno\n123\tRRBS_normal_B_cell_H1_22_TAGGCATG.CCTTCG.dan.anno\n128\tRRBS_normal_B_cell_H1_22_TAGGCATG.GCATTC.dan.anno\n132\tRRBS_normal_B_cell_H1_22_TAGGCATG.GTTGAG.dan.anno\n135\tRRBS_normal_B_cell_H1_22_TAGGCATG.TCTCTG.dan.anno\n\n\n# remove 13 mcell\n0\tRRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.ACAACC.\n4\tRRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.AGGATG\n10\tRRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.CGGTAG..\n21\tRRBS_NormalBCD19pCD27mcell1_22_CGAGGCTG.TCTCTG...\n37\tRRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.GCTGC.\n38\tRRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.GGCAT\n41\tRRBS_NormalBCD19pCD27mcell23_44_GTAGAGGA.TAGCG..\n45\tRRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.ACCGC.\n58\tRRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GCATT...\n59\tRRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GCTGC\n60\tRRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GGCAT.\n62\tRRBS_NormalBCD19pCD27mcell45_66_TAAGGCGA.GTTGA.\n81\tRRBS_NormalBCD19pCD27mcell67_88_CGTACTAG.GCTGC\n\n\n# remove 5 cd19 cell\n17\tRRBS_NormalBCD19pcell1_22_TAAGGCGA.GTGAGG.dan...\n29\tRRBS_NormalBCD19pcell23_44_CGTACTAG.CAAGAG.dan.\n40\tRRBS_NormalBCD19pcell23_44_CGTACTAG.GTTGAG.dan...\n79\tRRBS_NormalBCD19pcell67_88_TCCTGAGC.GACACG.dan..\n88\tRRBS_NormalBCD19pcell67_88_TCCTGAGC.TGCTGC.dan\n\n\n\n\n'

In [ ]:
normalB = normalB.drop(normalB.index[])

In [ ]:
normalB.index[]

In [89]:
# remove 23 normal B cell
normalB = normalB.drop(normalB.index[[3,9,14,23,26,28,30,39,57,60,69,75,79,82,87,91,97,109,113,123,128,132,135]])

In [88]:
len([3,9,14,23,26,28,30,39,57,60,69,75,79,82,87,91,97,109,113,123,128,132,135])


Out[88]:
23

In [91]:
normalB = normalB.reset_index()

In [92]:
normalB.shape


Out[92]:
(113, 40)

In [93]:
normalB.to_csv("Correct_Normal_B_regions.csv", index=False)

In [95]:
len([2,13,20,21,44,45,47,49,51,53,55,57,59,60,61,63,65,66,74,89])


Out[95]:
20

In [96]:
pcell = pcell.drop(pcell.index[[2,13,20,21,44,45,47,49,51,53,55,57,59,60,61,63,65,66,74,89]])

In [97]:
pcell = pcell.reset_index()

In [98]:
pcell.shape


Out[98]:
(70, 40)

In [99]:
pcell.to_csv("Correct_pcell_regions.csv", index=False)

In [101]:
len([0,4,10,21,37,38,41,45,58,59,60,62,81])


Out[101]:
13

In [102]:
mcell = mcell.drop(mcell.index[[0,4,10,21,37,38,41,45,58,59,60,62,81]])

In [103]:
mcell = mcell.reset_index()

In [104]:
mcell.shape


Out[104]:
(75, 40)

In [105]:
mcell.to_csv("Correct_mcell_regions.csv", index=False)

In [106]:
len([17, 29, 40, 79, 88])


Out[106]:
5

In [107]:
cd19cell = cd19cell.drop(cd19cell.index[[17, 29, 40, 79, 88]])

In [108]:
cd19cell = cd19cell.reset_index()

In [109]:
cd19cell.shape


Out[109]:
(84, 40)

In [110]:
cd19cell.to_csv("Correct_CD19cell_regions.csv", index=False)

In [112]:
trito = trito.drop(trito.index[[3, 43]])

In [113]:
trito = trito.reset_index()

In [114]:
trito.shape


Out[114]:
(42, 40)

In [115]:
trito.to_csv("Correct_trito_regions.csv", index=False)

In [116]:
cw154


Out[116]:
filename methylation_tssDistance methylation_genesDistance methylation_exonsDistance methylation_intronsDistance methylation_promoterDistance methylation_cgiDistance methylation_ctcfDistance methylation_ctcfUpDistance methylation_ctcfDownDistance methylation_geneDistalRegulatoryModulesDistance methylation_vistaEnhancersDistance methylation_3PrimeUTRDistance methylation_5PrimeUTRDistance methylation_firstExonDistance methylation_geneDistalRegulatoryModulesK562Distance methylation_hypoInHues64Distance methylation_intergenic methylation_shore methylation_shelf PDR_tssDistance PDR_genesDistance PDR_exonsDistance PDR_intronsDistance PDR_promoterDistance PDR_cgiDistance PDR_ctcfDistance PDR_ctcfUpDistance PDR_ctcfDownDistance PDR_geneDistalRegulatoryModulesDistance PDR_vistaEnhancersDistance PDR_3PrimeUTRDistance PDR_5PrimeUTRDistance PDR_firstExonDistance PDR_geneDistalRegulatoryModulesK562Distance PDR_hypoInHues64Distance PDR_intergenic PDR_shore PDR_shelf
0 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ACAA... 0.0 0.557445 0.387638 0.583685 0.148984 0.173551 0.197546 0.0 0.197546 0.330378 0.534917 0.659609 0.300969 0.142909 0.246735 0.805699 0.820512 0.590658 0.806973 0.0 0.370149 0.420504 0.359511 0.408136 0.450911 0.436709 0.0 0.436709 0.446102 0.393463 0.409348 0.376109 0.438725 0.388377 0.397393 0.379858 0.378600 0.345222
1 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ACCG... 0.0 0.495537 0.324467 0.521993 0.140566 0.157658 0.175575 0.0 0.175575 0.296219 0.366917 0.587535 0.261936 0.137202 0.237040 0.690698 0.796567 0.530634 0.780923 0.0 0.388093 0.435418 0.383256 0.418755 0.458484 0.442186 0.0 0.442186 0.440632 0.840602 0.376294 0.386659 0.445932 0.394716 0.346512 0.418598 0.404386 0.362456
2 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ACGT... 0.0 0.520409 0.357209 0.544602 0.138190 0.161856 0.202110 0.0 0.202110 0.314849 0.463004 0.656101 0.275719 0.138640 0.225783 0.761359 0.792970 0.551861 0.785731 0.0 0.383971 0.430167 0.374988 0.410647 0.455464 0.453277 0.0 0.453277 0.450694 0.324865 0.443011 0.387172 0.439933 0.414011 0.280260 0.411414 0.389000 0.363575
3 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ACTC... 0.0 0.569906 0.398614 0.595372 0.158028 0.178889 0.196911 0.0 0.196911 0.340942 0.608100 0.665446 0.310607 0.154927 0.247978 0.867355 0.831256 0.609382 0.812445 0.0 0.363173 0.416487 0.354378 0.421272 0.454977 0.438265 0.0 0.438265 0.452257 0.477332 0.376957 0.382624 0.449764 0.400321 0.171406 0.369736 0.385435 0.345905
4 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.AGGA... 0.0 0.554293 0.390193 0.576205 0.148946 0.173784 0.194668 0.0 0.194668 0.339245 0.494894 0.652036 0.291318 0.145185 0.250083 0.894932 0.825017 0.592558 0.807747 0.0 0.365658 0.414198 0.357211 0.407138 0.447926 0.433596 0.0 0.433596 0.428716 0.406863 0.397655 0.376272 0.425466 0.383864 0.274772 0.382212 0.378352 0.346732
5 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ATAG... 0.0 0.526884 0.365643 0.552338 0.136827 0.156219 0.186982 0.0 0.186982 0.301051 0.415511 0.644089 0.271955 0.138062 0.216288 0.857859 0.811758 0.577252 0.782210 0.0 0.367963 0.412391 0.359439 0.403460 0.439426 0.423300 0.0 0.423300 0.429729 0.292245 0.380568 0.375672 0.428114 0.370678 0.322551 0.389826 0.380924 0.350955
6 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.ATCG... 0.0 0.565536 0.398508 0.589354 0.153438 0.180336 0.206914 0.0 0.206914 0.347903 0.522757 0.669365 0.309018 0.148969 0.258009 0.820103 0.819525 0.596228 0.804310 0.0 0.369158 0.418102 0.361217 0.417424 0.458302 0.448756 0.0 0.448756 0.443698 0.440532 0.368417 0.382661 0.443897 0.395646 0.354083 0.387312 0.389256 0.340801
7 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CAAG... 0.0 0.547472 0.384373 0.572749 0.152863 0.174421 0.196066 0.0 0.196066 0.323417 0.597436 0.672153 0.293574 0.158459 0.240607 0.824585 0.818860 0.588054 0.798634 0.0 0.376000 0.434308 0.366559 0.423294 0.459171 0.451662 0.0 0.451662 0.447380 0.488112 0.390544 0.391449 0.454109 0.397710 0.296812 0.377959 0.384896 0.350755
8 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CATG... 0.0 0.560115 0.399275 0.582994 0.152070 0.177982 0.210642 0.0 0.210642 0.340830 0.435017 0.658850 0.302575 0.158123 0.251308 0.843652 0.824098 0.590612 0.803914 0.0 0.373358 0.424900 0.366055 0.417887 0.459681 0.468793 0.0 0.468793 0.450033 0.352024 0.396828 0.387961 0.445253 0.403604 0.319329 0.384551 0.390295 0.359863
9 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CCTT... 0.0 0.532219 0.373563 0.554328 0.142907 0.169012 0.183736 0.0 0.183736 0.302616 0.550507 0.615149 0.286602 0.137620 0.221478 0.836297 0.797139 0.569496 0.783430 0.0 0.385187 0.431739 0.377812 0.418669 0.460034 0.465381 0.0 0.465381 0.453603 0.594966 0.418134 0.380153 0.439284 0.396606 0.339958 0.408284 0.396687 0.369618
10 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CGGT... 0.0 0.531700 0.370532 0.555725 0.143834 0.165315 0.196658 0.0 0.196658 0.309425 0.623132 0.622519 0.289789 0.155198 0.227672 0.843004 0.805881 0.560993 0.780727 0.0 0.382102 0.430692 0.375433 0.424467 0.459925 0.446492 0.0 0.446492 0.438186 0.285556 0.395191 0.396617 0.457859 0.385372 0.288365 0.385553 0.395152 0.348968
11 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CTAT... 0.0 0.000000 0.438795 0.584559 0.167596 0.132262 0.247382 0.0 0.247382 0.367269 0.666667 0.802508 0.266462 0.184211 0.438384 NaN 0.864040 0.753557 0.898721 0.0 0.320416 0.364490 0.306668 0.356688 0.364810 0.492147 0.0 0.492147 0.336617 1.000000 0.278997 0.367534 0.408669 0.282828 0.000000 0.255152 0.306773 0.166311
12 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.CTCA... 0.0 0.541012 0.377389 0.563507 0.145227 0.168764 0.192585 0.0 0.192585 0.316389 0.499417 0.620360 0.294856 0.143099 0.234895 0.807127 0.815787 0.578767 0.792081 0.0 0.376073 0.421432 0.367262 0.419961 0.462968 0.441023 0.0 0.441023 0.437581 0.588098 0.388470 0.389301 0.439037 0.393979 0.358086 0.389474 0.390579 0.352459
13 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GACA... 0.0 0.539446 0.379285 0.562106 0.151057 0.169830 0.197479 0.0 0.197479 0.319023 0.526829 0.624394 0.298679 0.152752 0.245067 0.817265 0.808146 0.560909 0.785910 0.0 0.383113 0.442335 0.372629 0.432990 0.474104 0.484110 0.0 0.484110 0.456716 0.394038 0.435484 0.392065 0.465344 0.397636 0.453005 0.394112 0.399016 0.354612
14 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GCAT... 0.0 0.573906 0.406627 0.598475 0.155752 0.181375 0.219125 0.0 0.219125 0.349142 0.461636 0.692945 0.314043 0.149229 0.265561 0.805184 0.818499 0.600889 0.805211 0.0 0.364838 0.413731 0.355293 0.418106 0.451039 0.460955 0.0 0.460955 0.439120 0.427394 0.374650 0.384259 0.436755 0.386565 0.237381 0.388799 0.388247 0.351250
15 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GCTG... 0.0 0.539193 0.372853 0.564383 0.150046 0.168813 0.200850 0.0 0.200850 0.317655 0.268741 0.630294 0.293949 0.147488 0.230698 0.821040 0.793269 0.565109 0.775614 0.0 0.393342 0.452026 0.385192 0.444778 0.484272 0.488233 0.0 0.488233 0.459993 0.214993 0.453466 0.409531 0.469308 0.402897 0.556227 0.403487 0.399105 0.359500
16 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GGCA... 0.0 0.548961 0.381545 0.572243 0.146518 0.163592 0.183910 0.0 0.183910 0.332055 0.649764 0.659449 0.302050 0.137127 0.242075 0.858011 0.802843 0.573498 0.788575 0.0 0.369289 0.415335 0.362727 0.408150 0.450432 0.434240 0.0 0.434240 0.448769 0.330582 0.427089 0.369247 0.423437 0.403369 0.205525 0.403571 0.402985 0.363866
17 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GTGA... 0.0 0.517231 0.360581 0.541139 0.144744 0.169206 0.192751 0.0 0.192751 0.305701 0.480723 0.644707 0.272439 0.143972 0.224896 0.918484 0.809293 0.549385 0.774150 0.0 0.384798 0.440085 0.375126 0.427821 0.470287 0.458102 0.0 0.458102 0.450411 0.491777 0.418309 0.398621 0.454455 0.393129 0.153117 0.377603 0.389681 0.372192
18 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.GTTG... 0.0 0.445185 0.314814 0.459320 0.101895 0.106513 0.175696 0.0 0.175696 0.255117 0.000000 0.678481 0.205315 0.121112 0.152685 1.000000 0.864037 0.541609 0.803819 0.0 0.289698 0.302033 0.274471 0.305291 0.323511 0.320269 0.0 0.320269 0.332025 0.000000 0.272405 0.287926 0.304364 0.244743 0.000000 0.259456 0.350199 0.261936
19 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.TAGC... 0.0 0.515064 0.355504 0.538392 0.136692 0.160634 0.179352 0.0 0.179352 0.304709 0.444590 0.584831 0.275469 0.136273 0.232486 0.726700 0.784468 0.534703 0.769952 0.0 0.396907 0.440482 0.389549 0.423470 0.462821 0.449771 0.0 0.449771 0.465285 0.426702 0.407070 0.397690 0.445997 0.414601 0.361041 0.422636 0.409871 0.372959
20 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.TATC... 0.0 0.576698 0.407457 0.601190 0.156286 0.179898 0.203588 0.0 0.203588 0.341264 0.581638 0.672314 0.322060 0.151705 0.253217 0.870145 0.827566 0.609707 0.808661 0.0 0.363719 0.416227 0.355604 0.418422 0.454966 0.438377 0.0 0.438377 0.442940 0.321610 0.394777 0.380926 0.444623 0.400264 0.253117 0.374934 0.378514 0.347429
21 RRBS_cw154_CutSmart_proteinase_K_TAGGCATG.TCTC... 0.0 0.565269 0.398589 0.589572 0.157359 0.178807 0.211161 0.0 0.211161 0.342742 0.563872 0.681485 0.312209 0.155151 0.256075 0.863981 0.828704 0.602805 0.808628 0.0 0.368633 0.420777 0.360477 0.423342 0.463158 0.464180 0.0 0.464180 0.449781 0.310764 0.373593 0.395798 0.454929 0.396916 0.177725 0.372295 0.384154 0.345767
22 RRBS_cw154_Tris_protease_CTCTCTAC.ACAACC.dan.anno 0.0 0.534341 0.373414 0.559693 0.140429 0.159554 0.178100 0.0 0.178100 0.309936 0.497813 0.645147 0.292520 0.143238 0.226691 0.731040 0.808980 0.580810 0.795186 0.0 0.388448 0.444272 0.377688 0.433265 0.469909 0.469338 0.0 0.469338 0.451973 0.651118 0.429110 0.404743 0.471306 0.398084 0.377739 0.394894 0.395843 0.368690
23 RRBS_cw154_Tris_protease_CTCTCTAC.ACCGCG.dan.anno 0.0 0.460252 0.301662 0.485655 0.123422 0.144838 0.161997 0.0 0.161997 0.258069 0.137171 0.607551 0.216179 0.125607 0.192525 0.893236 0.784792 0.496794 0.751479 0.0 0.393472 0.439482 0.385331 0.422044 0.459844 0.438432 0.0 0.438432 0.456989 0.173419 0.457588 0.402154 0.453262 0.412374 0.324368 0.422718 0.423725 0.343020
24 RRBS_cw154_Tris_protease_CTCTCTAC.ACGTGG.dan.anno 0.0 0.458037 0.323757 0.482683 0.127488 0.161868 0.176395 0.0 0.176395 0.285677 0.407810 0.584367 0.216456 0.126353 0.201637 0.975253 0.791770 0.517245 0.752050 0.0 0.410130 0.440868 0.407166 0.426673 0.464655 0.448130 0.0 0.448130 0.451854 0.296589 0.413079 0.408591 0.454207 0.418433 0.066367 0.399408 0.404818 0.339397
25 RRBS_cw154_Tris_protease_CTCTCTAC.ACTCAC.dan.anno 0.0 0.590028 0.422366 0.612746 0.168838 0.192126 0.204903 0.0 0.204903 0.371221 0.733536 0.676370 0.340330 0.165456 0.282602 0.831377 0.816232 0.594412 0.805338 0.0 0.381890 0.444354 0.372424 0.453939 0.496793 0.476430 0.0 0.476430 0.467415 0.134052 0.405989 0.397287 0.473730 0.425922 0.237761 0.393858 0.396729 0.348192
26 RRBS_cw154_Tris_protease_CTCTCTAC.AGGATG.dan.anno 0.0 0.526552 0.369634 0.553452 0.143346 0.165112 0.189923 0.0 0.189923 0.319121 0.419560 0.650610 0.281031 0.137878 0.234273 0.826387 0.793863 0.560189 0.785121 0.0 0.389957 0.447900 0.378239 0.447429 0.480496 0.498393 0.0 0.498393 0.459329 0.192210 0.399631 0.408654 0.479657 0.409307 0.294912 0.419935 0.403721 0.382693
27 RRBS_cw154_Tris_protease_CTCTCTAC.ATAGCG.dan.anno 0.0 0.514725 0.364374 0.536571 0.138552 0.163622 0.209144 0.0 0.209144 0.301816 0.432663 0.641328 0.275702 0.138910 0.225859 0.926267 0.798583 0.542398 0.777647 0.0 0.387464 0.435454 0.380125 0.440076 0.477478 0.453723 0.0 0.453723 0.448844 0.455532 0.378974 0.401406 0.462439 0.404434 0.175444 0.404892 0.414161 0.349822
28 RRBS_cw154_Tris_protease_CTCTCTAC.ATCGAC.dan.anno 0.0 0.558080 0.398185 0.580534 0.151438 0.175596 0.197664 0.0 0.197664 0.334314 0.433680 0.703718 0.302549 0.152055 0.248275 0.877315 0.819819 0.581308 0.796077 0.0 0.380517 0.431675 0.373339 0.438100 0.476924 0.467834 0.0 0.467834 0.464795 0.732005 0.401747 0.402183 0.468532 0.413423 0.445849 0.379814 0.380670 0.343064
29 RRBS_cw154_Tris_protease_CTCTCTAC.CAAGAG.dan.anno 0.0 0.486270 0.370296 0.502550 0.152896 0.168602 0.205128 0.0 0.205128 0.170190 0.235294 0.743697 0.231379 0.191316 0.100649 0.500000 0.848130 0.564462 0.827768 0.0 0.427703 0.430160 0.436737 0.494695 0.470844 0.458974 0.0 0.458974 0.465425 1.000000 0.340336 0.543755 0.458727 0.457792 0.000000 0.335998 0.348029 0.298770
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
36 RRBS_cw154_Tris_protease_CTCTCTAC.GCATTC.dan.anno 0.0 0.550686 0.397458 0.573475 0.155206 0.175344 0.197986 0.0 0.197986 0.317136 0.483328 0.689705 0.302586 0.153650 0.237950 0.865758 0.812120 0.583075 0.787242 0.0 0.383840 0.440115 0.373946 0.430963 0.471428 0.460249 0.0 0.460249 0.444606 0.497993 0.406583 0.406167 0.463870 0.403142 0.234360 0.388152 0.397824 0.364322
37 RRBS_cw154_Tris_protease_CTCTCTAC.GCTGCC.dan.anno 0.0 0.549865 0.375639 0.572812 0.150089 0.162113 0.164505 0.0 0.164505 0.324149 0.608583 0.611432 0.317604 0.143925 0.240400 0.757844 0.797200 0.527989 0.792693 0.0 0.383353 0.438283 0.376650 0.435875 0.472296 0.471156 0.0 0.471156 0.443709 0.592978 0.387363 0.416812 0.445048 0.423542 0.478172 0.389699 0.403168 0.358137
38 RRBS_cw154_Tris_protease_CTCTCTAC.GGCATC.dan.anno 0.0 0.534038 0.370099 0.556779 0.145719 0.162697 0.180510 0.0 0.180510 0.319885 0.502717 0.643891 0.294115 0.142610 0.227868 0.782086 0.793476 0.560685 0.779066 0.0 0.393307 0.441777 0.386214 0.433309 0.468830 0.459156 0.0 0.459156 0.464283 0.369318 0.423972 0.391096 0.448848 0.413452 0.402209 0.419728 0.410595 0.385529
39 RRBS_cw154_Tris_protease_CTCTCTAC.GTGAGG.dan.anno 0.0 0.489653 0.326848 0.515329 0.130821 0.151956 0.181042 0.0 0.181042 0.287429 0.652036 0.607564 0.253067 0.128629 0.208924 0.832283 0.789822 0.519845 0.771301 0.0 0.393518 0.435982 0.385103 0.421115 0.461429 0.432756 0.0 0.432756 0.444819 0.511312 0.470527 0.406976 0.454380 0.377418 0.532563 0.409291 0.411337 0.363646
40 RRBS_cw154_Tris_protease_CTCTCTAC.GTTGAG.dan.anno 0.0 0.531990 0.370032 0.557751 0.135521 0.158191 0.182368 0.0 0.182368 0.308875 0.524319 0.620437 0.279451 0.135809 0.245574 0.858791 0.796981 0.548003 0.795593 0.0 0.378032 0.429048 0.366821 0.420896 0.457147 0.420198 0.0 0.420198 0.441564 0.596819 0.350647 0.385625 0.446510 0.377840 0.322593 0.416306 0.394795 0.360156
41 RRBS_cw154_Tris_protease_CTCTCTAC.TAGCGG.dan.anno 0.0 0.471778 0.313727 0.499631 0.125400 0.152194 0.185181 0.0 0.185181 0.275724 0.331111 0.528724 0.243965 0.131895 0.194354 0.889034 0.792664 0.523283 0.743746 0.0 0.400202 0.440841 0.390273 0.438782 0.479660 0.487100 0.0 0.487100 0.453398 0.542222 0.474395 0.402119 0.453015 0.411555 0.259791 0.413971 0.416831 0.362602
42 RRBS_cw154_Tris_protease_CTCTCTAC.TATCTC.dan.anno 0.0 0.516220 0.350940 0.542691 0.144981 0.164118 0.185249 0.0 0.185249 0.308461 0.439266 0.625922 0.269605 0.140071 0.225836 0.873896 0.797049 0.564834 0.796188 0.0 0.392915 0.435968 0.384976 0.433091 0.471331 0.468878 0.0 0.468878 0.454272 0.560982 0.409778 0.400449 0.448436 0.404954 0.250000 0.417221 0.404421 0.371054
43 RRBS_cw154_Tris_protease_CTCTCTAC.TCTCTG.dan.anno 0.0 0.553577 0.386507 0.579787 0.155410 0.178985 0.208762 0.0 0.208762 0.336380 0.501952 0.654150 0.298292 0.152577 0.246424 0.827148 0.817611 0.585299 0.788970 0.0 0.377694 0.434611 0.366589 0.438043 0.475137 0.472028 0.0 0.472028 0.459645 0.571333 0.377541 0.397031 0.456302 0.423987 0.213718 0.388219 0.394885 0.358565
44 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ACAACC.da... 0.0 0.576284 0.406097 0.601754 0.161465 0.185395 0.207583 0.0 0.207583 0.357942 0.547005 0.670954 0.324295 0.157820 0.268130 0.846800 0.817763 0.599877 0.789617 0.0 0.385672 0.442893 0.376316 0.443877 0.485673 0.476193 0.0 0.476193 0.477462 0.557266 0.414924 0.405707 0.472460 0.436088 0.193601 0.390099 0.402147 0.356893
45 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ACCGCG.da... 0.0 0.511334 0.343362 0.525529 0.146702 0.155815 0.161441 0.0 0.161441 0.300844 0.255682 0.604491 0.270828 0.137620 0.232425 0.460251 0.763500 0.494908 0.734817 0.0 0.421948 0.474217 0.419047 0.445339 0.484756 0.396339 0.0 0.396339 0.472072 0.625000 0.475384 0.430449 0.478865 0.442140 0.246862 0.427111 0.408966 0.424868
46 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ACGTGG.da... 0.0 0.512682 0.345234 0.536809 0.137729 0.160869 0.176882 0.0 0.176882 0.311430 0.473591 0.616956 0.277755 0.130273 0.230467 0.931588 0.793475 0.532694 0.771031 0.0 0.398524 0.452411 0.391642 0.448729 0.485078 0.475244 0.0 0.475244 0.463947 0.347774 0.436047 0.417028 0.471349 0.425034 0.192148 0.416041 0.417826 0.365604
47 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ACTCAC.da... 0.0 0.573171 0.401849 0.597199 0.151773 0.171875 0.194561 0.0 0.194561 0.345406 0.517198 0.670404 0.319500 0.153398 0.263630 0.815552 0.823303 0.608822 0.800335 0.0 0.378345 0.434331 0.370594 0.440354 0.477316 0.461536 0.0 0.461536 0.463942 0.533343 0.377821 0.398082 0.465740 0.432103 0.403309 0.383423 0.391929 0.353436
48 RRBS_cw154_Tris_protease_GR_CAGAGAGG.AGGATG.da... 0.0 0.564190 0.400639 0.587070 0.156148 0.178286 0.200963 0.0 0.200963 0.341886 0.720597 0.682988 0.310596 0.151629 0.253827 0.866745 0.815414 0.594260 0.803257 0.0 0.379929 0.434078 0.371444 0.444880 0.483348 0.468416 0.0 0.468416 0.458227 0.361589 0.389223 0.405786 0.467325 0.408632 0.225639 0.388187 0.390956 0.356615
49 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ATAGCG.da... 0.0 0.511650 0.347418 0.536770 0.130230 0.152742 0.171285 0.0 0.171285 0.301554 0.600641 0.620994 0.268694 0.129413 0.230489 0.721732 0.801653 0.536829 0.779564 0.0 0.389526 0.437767 0.377810 0.426748 0.469372 0.442436 0.0 0.442436 0.460019 0.354316 0.390483 0.394218 0.452053 0.397870 0.406152 0.393092 0.402037 0.364014
50 RRBS_cw154_Tris_protease_GR_CAGAGAGG.ATCGAC.da... 0.0 0.581265 0.413731 0.604593 0.159955 0.182839 0.200410 0.0 0.200410 0.348518 0.473692 0.685157 0.329431 0.157349 0.261800 0.883827 0.827906 0.608313 0.808906 0.0 0.378523 0.439229 0.367856 0.442772 0.484959 0.491116 0.0 0.491116 0.471417 0.430501 0.409146 0.406994 0.473154 0.427580 0.355927 0.376216 0.398450 0.348651
51 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CAAGAG.da... 0.0 0.000000 0.372152 0.546730 0.184593 0.188679 0.283105 0.0 0.283105 0.368590 0.000000 0.694737 0.249365 0.219697 0.267257 NaN 0.805740 0.603448 0.860000 0.0 0.369933 0.427426 0.365895 0.447646 0.463819 0.458143 0.0 0.458143 0.495726 0.000000 0.436842 0.409264 0.415909 0.522124 0.000000 0.374869 0.358012 0.230000
52 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CATGAC.da... 0.0 0.587509 0.432016 0.608034 0.165995 0.187324 0.214616 0.0 0.214616 0.367932 0.518964 0.674795 0.330463 0.168557 0.271944 0.902915 0.821682 0.598753 0.808898 0.0 0.381658 0.436510 0.374043 0.451143 0.490825 0.466760 0.0 0.466760 0.462817 0.547771 0.413982 0.411164 0.476445 0.416048 0.233673 0.385518 0.398958 0.344039
53 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CCTTCG.da... 0.0 0.516150 0.346647 0.540346 0.143693 0.154591 0.175251 0.0 0.175251 0.310324 0.413022 0.614101 0.274294 0.137531 0.228403 0.769873 0.783656 0.524627 0.766010 0.0 0.392435 0.446851 0.385694 0.434338 0.475932 0.485631 0.0 0.485631 0.436179 0.792247 0.403187 0.403722 0.464367 0.398929 0.258439 0.416008 0.411363 0.378304
54 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CGGTAG.da... 0.0 0.534594 0.369322 0.558910 0.146821 0.161236 0.192204 0.0 0.192204 0.310096 0.545982 0.604021 0.284603 0.144641 0.235544 0.837650 0.794706 0.546525 0.773418 0.0 0.386344 0.440891 0.378346 0.439248 0.487651 0.475052 0.0 0.475052 0.463789 0.426339 0.398519 0.407179 0.461797 0.431631 0.290587 0.397254 0.397529 0.366067
55 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CTATTG.da... 0.0 0.506774 0.372387 0.528822 0.145138 0.174562 0.185376 0.0 0.185376 0.313840 0.351714 0.634783 0.260631 0.147495 0.225961 0.888504 0.800684 0.565772 0.791344 0.0 0.397668 0.443187 0.389245 0.434167 0.479863 0.461500 0.0 0.461500 0.466725 0.299837 0.448787 0.405493 0.460125 0.402327 0.284124 0.403780 0.397252 0.388561
56 RRBS_cw154_Tris_protease_GR_CAGAGAGG.CTCAGC.da... 0.0 0.585109 0.420451 0.608710 0.164237 0.177026 0.200596 0.0 0.200596 0.354298 0.402174 0.652141 0.332674 0.155343 0.274508 0.897694 0.802184 0.584740 0.811600 0.0 0.380717 0.430851 0.372447 0.446459 0.484725 0.452090 0.0 0.452090 0.470944 0.403339 0.398307 0.408462 0.454746 0.447672 0.241869 0.407099 0.410584 0.357457
57 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GACACG.da... 0.0 0.515384 0.348097 0.540523 0.136907 0.150941 0.169903 0.0 0.169903 0.302160 0.415330 0.628959 0.278453 0.132860 0.220073 0.945615 0.790033 0.517115 0.755147 0.0 0.397503 0.455544 0.389747 0.437309 0.480080 0.467647 0.0 0.467647 0.456722 0.269456 0.408003 0.418366 0.481040 0.413696 0.220401 0.395705 0.414493 0.385641
58 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GCATTC.da... 0.0 0.608538 0.428746 0.629168 0.173777 0.186020 0.225286 0.0 0.225286 0.365004 0.607946 0.682409 0.362460 0.161610 0.266919 0.943119 0.820956 0.601619 0.811971 0.0 0.373311 0.429765 0.366590 0.449237 0.490146 0.514217 0.0 0.514217 0.463287 0.525091 0.398041 0.400434 0.468651 0.427292 0.251376 0.386496 0.409402 0.348546
59 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GCTGCC.da... 0.0 0.576122 0.404285 0.598434 0.162122 0.181122 0.220391 0.0 0.220391 0.353660 0.488789 0.695825 0.342339 0.158025 0.267716 0.868908 0.802257 0.574030 0.802627 0.0 0.392724 0.459133 0.382072 0.448174 0.497532 0.473646 0.0 0.473646 0.442382 0.715994 0.419597 0.426912 0.490002 0.393181 0.174790 0.404133 0.416121 0.340402
60 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GGCATC.da... 0.0 0.567852 0.405896 0.589092 0.159208 0.173028 0.194514 0.0 0.194514 0.339230 0.400992 0.625731 0.327633 0.153576 0.241934 0.824254 0.797284 0.567597 0.778227 0.0 0.393760 0.455299 0.386012 0.451880 0.500343 0.508443 0.0 0.508443 0.480389 0.404090 0.447343 0.421022 0.480479 0.440682 0.414732 0.411504 0.411222 0.373854
61 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GTGAGG.da... 0.0 0.540579 0.378239 0.563490 0.148783 0.168545 0.180514 0.0 0.180514 0.310731 0.521963 0.667501 0.303415 0.143335 0.227983 0.820113 0.793085 0.542785 0.767958 0.0 0.401265 0.458648 0.394131 0.454753 0.489479 0.463048 0.0 0.463048 0.465206 0.518934 0.391409 0.415603 0.493483 0.414381 0.373337 0.403627 0.402933 0.389869
62 RRBS_cw154_Tris_protease_GR_CAGAGAGG.GTTGAG.da... 0.0 0.590227 0.420827 0.615305 0.167125 0.186078 0.203812 0.0 0.203812 0.365675 0.464368 0.654491 0.343965 0.176519 0.283145 0.911492 0.808049 0.596742 0.792297 0.0 0.384102 0.433679 0.374276 0.441195 0.482594 0.457740 0.0 0.457740 0.471821 0.675575 0.414101 0.400324 0.461227 0.430853 0.246331 0.398943 0.401963 0.361181
63 RRBS_cw154_Tris_protease_GR_CAGAGAGG.TAGCGG.da... 0.0 0.551284 0.385638 0.574912 0.152819 0.166841 0.182777 0.0 0.182777 0.317631 0.606152 0.628592 0.322355 0.152436 0.238888 0.879544 0.784437 0.541362 0.761603 0.0 0.389318 0.439817 0.380264 0.431510 0.483114 0.470635 0.0 0.470635 0.455824 0.668417 0.378515 0.399306 0.451436 0.432468 0.149803 0.405760 0.397798 0.373977
64 RRBS_cw154_Tris_protease_GR_CAGAGAGG.TATCTC.da... 0.0 0.587895 0.412116 0.613305 0.165356 0.185364 0.209044 0.0 0.209044 0.353929 0.580729 0.665446 0.343067 0.159167 0.268219 0.780298 0.816863 0.589350 0.788591 0.0 0.376174 0.435518 0.367302 0.448862 0.487347 0.475819 0.0 0.475819 0.458763 0.523438 0.370440 0.413176 0.476628 0.412619 0.439182 0.387418 0.387567 0.355424
65 RRBS_cw154_Tris_protease_GR_CAGAGAGG.TCTCTG.da... 0.0 0.563683 0.396403 0.586718 0.154660 0.175256 0.209778 0.0 0.209778 0.336147 0.540323 0.668507 0.315953 0.154404 0.243405 0.791259 0.803866 0.580085 0.803588 0.0 0.383811 0.442727 0.373669 0.431037 0.478234 0.464356 0.0 0.464356 0.461964 0.353719 0.412310 0.396713 0.462184 0.405112 0.475546 0.405538 0.402137 0.342846

66 rows × 39 columns


In [118]:
cw154 = cw154.drop(cw154.index[[11, 18, 29, 51]])

In [121]:
cw154 = cw154.reset_index()

In [122]:
cw154.shape


Out[122]:
(62, 40)

In [123]:
cw154.to_csv("Correct_cw154_regions.csv", index=False)

In [124]:
print(normalB.shape)
print(mcell.shape)
print(pcell.shape)
print(cd19cell.shape)
print(trito.shape)
print(cw154.shape)


(113, 40)
(75, 40)
(70, 40)
(84, 40)
(42, 40)
(62, 40)

In [125]:
113+70+75+84


Out[125]:
342

In [ ]:


In [ ]:


In [ ]:


In [ ]:


In [ ]:


In [ ]: