notebook.community

Edit and run



In [1]:

    
from __future__ import division
from pandas import *
import os, os.path
import csv
from itertools import product
import numpy as np
import matplotlib.pyplot as plt

os.chdir('/home/will/Tip60Data/')



In [2]:

    
microdata = read_csv('microdata.tsv', sep='\t', index_col = 0)
microdata.columns = MultiIndex.from_tuples([col.split('_') for col in microdata.columns], names = ['Experiment', 'Run'])
agg_microdata = microdata.groupby(level = 'Experiment', axis = 1).mean()



In [3]:

    
check_cols = ['dTIP60E431Q', 'dTIP60WT']
fold_changes = agg_microdata.copy()
for col in check_cols:
    fold_changes[col] = agg_microdata[col]/agg_microdata['Control']
    
fold_changes = fold_changes.drop(['Control'], axis = 1).applymap(np.log2)



In [4]:

    
microdata









    Out[4]:





<class 'pandas.core.frame.DataFrame'>
Index: 22636 entries, NM_001007095.2_at to NR_048526.1_at
Data columns:
('Control', '1')    22636  non-null values
('Control', '2')    22636  non-null values
('dTIP60E431Q', '1')22636  non-null values
('dTIP60E431Q', '2')22636  non-null values
('dTIP60WT', '1')   22636  non-null values
('dTIP60WT', '2')   22636  non-null values
dtypes: float64(6)



In [5]:

    
from scipy.stats import norm, ttest_1samp
fold_changes.plot(kind = 'kde')
plt.title('KS Density of fold-changes')









    Out[5]:





<matplotlib.text.Text at 0x4025990>



In [6]:

    
pvals = fold_changes.copy()
for col in check_cols:
    mval = fold_changes[col].mean()
    stdval = fold_changes[col].std()
    pvals[col] = 1 - norm.cdf(abs(fold_changes[col]), loc=mval, scale = stdval)



In [7]:

    
cut = 0.05/len(pvals.index)
good_mask = (pvals<cut).any(axis = 1)
print pvals[good_mask].to_string()









    



                    dTIP60E431Q      dTIP60WT
RefSeq Genes                                 
NM_001014489.2_at  2.356172e-02  4.055312e-12
NM_001031943.2_at  3.833501e-08  2.203379e-01
NM_001042847.2_at  2.273285e-01  1.351625e-10
NM_001043100.2_at  8.350605e-08  5.585120e-02
NM_001043144.1_at  5.481837e-12  5.072655e-10
NM_001103387.1_at  2.990798e-09  4.257876e-01
NM_001103616.1_at  2.193840e-06  1.457361e-03
NM_001103691.2_at  8.163893e-07  3.011441e-01
NM_001103928.1_at  4.012457e-12  1.334510e-01
NM_001104314.1_at  4.487533e-10  2.462526e-01
NM_001144423.2_at  1.335637e-07  4.256002e-01
NM_001144585.1_at  2.926381e-08  5.280150e-01
NM_001144751.1_at  1.367163e-01  1.718539e-06
NM_001169156.1_at  2.990798e-09  4.257876e-01
NM_001169518.1_at  2.008583e-07  3.381436e-01
NM_001170058.1_at  2.959241e-09  1.237294e-01
NM_001201799.1_at  8.063083e-07  1.587422e-02
NM_001201830.1_at  4.529393e-01  3.354802e-10
NM_001201871.1_at  2.037486e-07  5.515679e-09
NM_001201917.1_at  2.356172e-02  4.055312e-12
NM_001259447.1_at  6.809827e-05  3.996803e-14
NM_001259735.1_at  1.791859e-07  1.224591e-01
NM_001259896.1_at  1.304544e-07  3.929592e-01
NM_057232.4_at     2.055494e-06  1.487686e-01
NM_057444.3_at     6.440473e-07  1.793064e-02
NM_057596.3_at     1.963133e-08  1.701901e-01
NM_057930.3_at     5.637897e-04  6.898937e-10
NM_057983.4_at     4.028546e-10  4.652948e-03
NM_078583.2_at     0.000000e+00  3.943396e-01
NM_078794.3_at     1.689416e-01  0.000000e+00
NM_078798.4_at     0.000000e+00  3.033905e-01
NM_078979.3_at     2.629112e-01  4.560506e-10
NM_079005.4_at     1.982322e-02  0.000000e+00
NM_079020.4_at     3.889064e-02  0.000000e+00
NM_079021.4_at     2.910566e-08  6.220580e-13
NM_079025.4_at     3.793505e-01  2.446226e-08
NM_079028.2_at     2.093296e-01  0.000000e+00
NM_079063.3_at     4.185310e-01  1.734091e-10
NM_079143.2_at     3.871533e-07  2.834844e-01
NM_079144.4_at     5.480438e-09  5.264376e-01
NM_079157.2_at     7.764533e-02  6.533492e-08
NM_079177.3_at     3.844084e-04  0.000000e+00
NM_079397.2_at     3.735615e-07  1.813218e-01
NM_079667.3_at     3.644359e-02  0.000000e+00
NM_080077.2_at     0.000000e+00  3.780136e-01
NM_080175.2_at     3.390765e-11  2.908292e-02
NM_080275.2_at     2.530198e-05  2.631229e-14
NM_130535.2_at     1.298192e-08  3.230222e-01
NM_130687.2_at     4.254584e-02  0.000000e+00
NM_130688.3_at     8.135292e-06  3.223885e-08
NM_131923.3_at     1.188023e-10  0.000000e+00
NM_131984.1_at     2.215918e-02  3.038787e-07
NM_131995.1_at     4.773416e-03  2.664535e-15
NM_132034.1_at     4.197962e-07  2.085042e-02
NM_132038.2_at     3.802571e-07  6.174109e-02
NM_132341.3_at     3.807480e-01  2.066508e-07
NM_132525.2_at     1.773647e-06  2.438244e-01
NM_132571.1_at     1.510675e-09  7.868153e-10
NM_132713.2_at     1.931419e-03  7.986585e-08
NM_132723.2_at     3.596828e-01  9.301443e-07
NM_132749.1_at     6.337592e-03  9.734866e-10
NM_132756.2_at     5.020939e-01  0.000000e+00
NM_133117.2_at     7.289934e-05  0.000000e+00
NM_134577.1_at     1.367163e-01  1.718539e-06
NM_134601.2_at     2.262039e-01  6.639951e-07
NM_134874.3_at     2.861012e-07  3.519407e-13
NM_135030.2_at     2.193840e-06  1.457361e-03
NM_135313.2_at     4.343668e-09  7.771561e-16
NM_135329.2_at     4.330343e-01  3.219647e-15
NM_135391.2_at     1.006245e-04  0.000000e+00
NM_135456.3_at     4.529393e-01  3.354802e-10
NM_135590.1_at     4.792157e-08  1.689561e-03
NM_135844.3_at     2.037486e-07  5.515679e-09
NM_135869.1_at     5.058593e-06  2.035039e-13
NM_135952.1_at     2.008583e-07  3.381436e-01
NM_136145.3_at     3.267393e-01  9.420130e-10
NM_136240.2_at     1.923795e-06  4.479278e-01
NM_136679.4_at     2.408938e-01  0.000000e+00
NM_136685.2_at     6.683747e-03  1.196820e-13
NM_136807.1_at     4.692797e-07  4.608663e-07
NM_136841.2_at     3.936678e-10  4.308596e-03
NM_137057.2_at     4.461884e-05  6.360726e-08
NM_137115.2_at     1.940670e-13  4.153295e-01
NM_137158.3_at     1.171421e-06  1.699542e-05
NM_137176.2_at     6.171109e-03  1.029626e-09
NM_137316.3_at     6.809827e-05  3.996803e-14
NM_137361.3_at     2.512684e-06  1.145334e-08
NM_137475.2_at     1.105960e-01  0.000000e+00
NM_137559.1_at     3.716496e-01  2.220446e-16
NM_137574.2_at     2.279996e-03  0.000000e+00
NM_137608.2_at     2.993916e-11  0.000000e+00
NM_137617.3_at     1.141288e-06  4.308357e-01
NM_137639.1_at     7.676309e-08  6.428752e-02
NM_137720.3_at     8.350605e-08  5.585120e-02
NM_137738.2_at     2.158045e-06  5.078140e-01
NM_137981.2_at     4.455170e-03  1.882435e-10
NM_138241.3_at     9.508541e-07  5.075629e-01
NM_139618.3_at     4.373576e-03  3.418604e-07
NM_139633.2_at     1.341071e-07  2.084582e-01
NM_139649.2_at     5.587037e-07  3.507513e-02
NM_140154.2_at     1.588037e-04  2.383967e-08
NM_140163.2_at     3.358859e-07  0.000000e+00
NM_140165.1_at     2.942591e-04  0.000000e+00
NM_140181.1_at     2.553775e-10  1.693416e-01
NM_140273.2_at     9.212520e-11  5.053261e-01
NM_140352.2_at     1.432445e-02  7.027712e-13
NM_140603.1_at     3.033122e-04  3.302802e-12
NM_140615.2_at     2.296140e-07  6.606651e-06
NM_140621.1_at     5.481837e-12  5.072655e-10
NM_140646.3_at     1.860773e-06  1.111205e-01
NM_140660.3_at     4.977585e-01  2.729705e-11
NM_140765.3_at     8.167295e-02  6.903345e-11
NM_140776.2_at     4.973171e-07  3.004387e-01
NM_140777.2_at     9.895291e-08  4.825707e-01
NM_140805.1_at     1.304544e-07  3.929592e-01
NM_141052.2_at     7.261217e-08  1.566699e-01
NM_141088.1_at     4.525494e-03  4.299894e-13
NM_141097.3_at     3.254931e-08  1.890024e-01
NM_141098.2_at     6.304797e-09  4.188862e-02
NM_141099.2_at     6.933233e-10  2.708588e-01
NM_141103.3_at     2.035245e-09  1.142810e-01
NM_141186.3_at     1.519759e-06  4.634838e-01
NM_141189.1_at     1.275032e-07  3.052540e-09
NM_141364.1_at     9.660518e-09  4.653146e-06
NM_141368.2_at     5.632828e-12  0.000000e+00
NM_141371.2_at     6.289524e-12  2.447679e-04
NM_141379.1_at     1.120649e-03  0.000000e+00
NM_141383.1_at     1.941259e-08  1.249429e-01
NM_141384.3_at     2.183006e-06  3.457451e-02
NM_141420.3_at     1.965321e-06  4.424078e-04
NM_142057.2_at     1.642338e-07  7.828557e-03
NM_142115.1_at     2.007161e-11  3.472339e-03
NM_142187.2_at     2.926381e-08  5.280150e-01
NM_142347.2_at     2.122845e-06  2.986960e-01
NM_142349.2_at     1.185149e-05  0.000000e+00
NM_142370.1_at     1.984570e-04  1.086850e-08
NM_142380.3_at     4.011546e-09  3.108416e-01
NM_142382.2_at     4.923609e-10  2.270048e-01
NM_142881.3_at     1.586629e-06  2.725607e-04
NM_142918.2_at     2.751782e-08  4.946202e-01
NM_142963.3_at     7.897005e-11  2.880920e-01
NM_142985.4_at     1.225356e-06  7.879686e-06
NM_143112.2_at     1.653904e-06  3.776616e-02
NM_143229.1_at     1.625380e-07  1.807443e-02
NM_143233.2_at     4.872326e-08  6.015597e-03
NM_143237.3_at     2.179724e-07  4.080528e-01
NM_143456.2_at     3.632250e-11  4.374908e-01
NM_143527.2_at     2.743180e-08  1.543248e-01
NM_143635.1_at     6.229535e-07  8.881784e-16
NM_143761.3_at     8.276158e-12  0.000000e+00
NM_144109.1_at     2.974029e-03  2.285454e-10
NM_144111.2_at     1.562655e-05  0.000000e+00
NM_144191.4_at     1.791859e-07  1.224591e-01
NM_144196.2_at     3.037068e-07  2.728767e-01
NM_144368.2_at     1.128788e-06  4.901860e-01
NM_144379.3_at     4.841584e-02  7.272382e-07
NM_144380.2_at     1.488918e-01  0.000000e+00
NM_164601.1_at     2.193840e-06  1.457361e-03
NM_164602.1_at     2.193840e-06  1.457361e-03
NM_164740.2_at     1.800838e-02  1.020003e-10
NM_164888.3_at     1.770474e-01  3.377187e-12
NM_165165.1_at     2.008583e-07  3.381436e-01
NM_165362.1_at     1.747354e-03  0.000000e+00
NM_165363.1_at     1.747354e-03  0.000000e+00
NM_166277.2_at     4.561179e-03  1.675994e-08
NM_166512.2_at     1.226739e-07  3.399438e-01
NM_166957.1_at     4.789260e-02  7.236615e-10
NM_167061.2_at     5.042538e-03  2.576828e-13
NM_167540.3_at     5.534107e-06  2.512070e-07
NM_168019.3_at     4.862777e-14  3.389933e-02
NM_168078.1_at     1.341071e-07  2.084582e-01
NM_168079.1_at     1.341071e-07  2.084582e-01
NM_168244.2_at     8.111855e-02  0.000000e+00
NM_168288.2_at     1.469648e-02  4.488694e-10
NM_168396.1_at     3.404407e-02  6.398869e-07
NM_168441.1_at     1.128722e-06  2.464024e-01
NM_168657.1_at     3.033122e-04  3.302802e-12
NM_168795.3_at     6.167814e-07  1.092393e-07
NM_168796.3_at     6.167814e-07  1.092393e-07
NM_168797.2_at     6.167814e-07  1.092393e-07
NM_169130.1_at     9.660518e-09  4.653146e-06
NM_169766.2_at     4.866276e-08  3.329687e-08
NM_170211.2_at     5.935881e-07  4.464565e-01
NM_170415.4_at     3.807880e-02  9.898543e-10
NM_176222.1_at     3.478619e-08  4.015223e-01
NM_176359.1_at     1.032578e-06  2.064449e-01
NM_206133.3_at     1.515695e-04  2.080534e-10
NM_206350.2_at     1.302702e-11  1.501247e-02



In [8]:

    
from operator import methodcaller
from itertools import groupby
from Bio.Seq import Seq
from Bio import Motif
from StringIO import StringIO

def yield_motifs():
    motifdir = '/home/will/Tip60Data/TFdata/'
    with open(motifdir + 'matrix_only.txt') as handle:
        for key, lines in groupby(handle, methodcaller('startswith', '>')):
            if key:
                name = lines.next().strip().split()[-1].lower()
            else:
                tmp = ''.join(lines)
                mot = Motif.read(StringIO(tmp), 'jaspar-pfm')
                yield name, mot
                yield name+'-R', mot.reverse_complement()

            
pwm_dict = {}
for num, (name, mot) in enumerate(yield_motifs()):
    if num % 100 == 0:
        print num
    thresh = Motif.Thresholds.ScoreDistribution(mot, precision = 50).threshold_fpr(0.0001)
    pwm_dict[name] = (mot, thresh)



In [10]:

    
from itertools import imap
from operator import itemgetter
def unique_justseen(iterable, key=None):
    "List unique elements, preserving order. Remember only the element just seen."
    # unique_justseen('AAAABBBCCDAABBB') --> A B C D A B
    # unique_justseen('ABBCcAD', str.lower) --> A B C A D
    return imap(next, imap(itemgetter(1), groupby(iterable, key)))

def take(n, iterable):
    "Return first n items of the iterable as a list"
    return list(islice(iterable, n))



In [11]:

    
def scan_seqs(tup):
    pwm_tup, row = tup
    seq = Seq(row['Seq'])
    start = int(row['Start'])
    ch = row['Chromosome']
    strand = row['Strand']
    name, (mot, thresh) = pwm_tup
    results = []
    for loc, m in mot.search_pwm(seq, threshold=thresh):
        results.append((name, ch, start+loc, start+loc+len(mot), strand))
    
    return results



In [17]:

    
from concurrent.futures import ProcessPoolExecutor, as_completed
from functools import partial
from itertools import islice

interval_fields = ['Chromosome','Start','Stop','Refseq','Junk1','Strand','Junk2','Junk3','Junk4','Junk5','Junk6','Junk7','Seq']

with open('seqdata/PromoterSeqdata.interval') as handle:
    with open('seqdata/TFBindingPos.interval', 'w') as ohandle:
        reader = csv.DictReader(handle, delimiter = '\t', fieldnames=interval_fields)
        nreader = unique_justseen(reader, key = lambda x: x['Seq'])
        
        writer = csv.writer(ohandle, delimiter = '\t')
        writer.writerow(['TFname', 'Chr', 'Start', 'Stop', 'strand'])
        
        check_items = product(sorted(pwm_dict.items()), nreader)
        blocksize = 50000
        with ProcessPoolExecutor(max_workers = 30) as executor:
            block = take(blocksize, check_items)
            start = 0
            while block:
                res = executor.map(scan_seqs, block)
                for r in res:
                    if r:
                        writer.writerows(r)
                block = take(blocksize, check_items)    
                start += blocksize
                num = int(start/len(pwm_dict))
                print num



In [24]:

    
def make_filename(inp):
    return inp.replace(' ', '-').replace(':', '-')


with open('seqdata/TFBindingPos.interval') as handle:
    reader = csv.reader(handle, delimiter = '\t')
    junk = reader.next()
    grouper = lambda x: x[0]
    for key, rows in groupby(reader, key = grouper):
        fname = make_filename(key)
        with open('seqdata/TFhits/'+fname + '.bed', 'a') as ohandle:
            writer = csv.writer(ohandle, delimiter = '\t')
            for row in rows:
                if (int(row[2]) > 0) and (int(row[3]) > 0):
                    writer.writerow(row[1:])



In [23]:

    
wanted_genes = set([n.split('.')[0] for n in pvals[good_mask].index])

with open('seqdata/PromoterInervals') as handle:
    with open('seqdata/SigGenePromoters.bed', 'w') as ohandle:
        reader = csv.reader(handle, delimiter = '\t')
        writer = csv.writer(ohandle, delimiter = '\t')
        for row in reader:
            if row[3] in wanted_genes:
                print row[3]
                wanted = [row[0], row[1], row[2], row[5]]
                writer.writerow(wanted)









    



NM_001103387
NM_001169156
NM_057444
NM_130535
NM_130688
NM_166957
NM_130687
NM_057596
NM_131923
NM_131984
NM_131995
NM_132038
NM_132034
NM_167061
NM_132341
NM_132525
NM_132571
NM_078583
NM_132723
NM_132713
NM_132756
NM_132749
NM_167540
NM_133117
NM_134577
NM_001144751
NM_134601
NM_001042847
NM_135952
NM_165165
NM_001169518
NM_165363
NM_165362
NM_134874
NM_144380
NM_164602
NM_001103616
NM_135030
NM_164601
NM_164740
NM_135313
NM_144379
NM_135329
NM_001201799
NM_135391
NM_078794
NM_078798
NM_135456
NM_001201830
NM_164888
NM_135590
NM_135844
NM_001201871
NM_135869
NM_001103691
NM_001201917
NM_001014489
NM_136145
NM_136240
NM_136685
NM_136679
NM_136807
NM_136841
NM_078979
NM_079005
NM_137057
NM_137115
NM_079021
NM_079020
NM_143761
NM_079025
NM_137158
NM_137176
NM_079028
NM_206133
NM_137316
NM_001259447
NM_137361
NM_144111
NM_144109
NM_166277
NM_137475
NM_176222
NM_079063
NM_137559
NM_137574
NM_137608
NM_137617
NM_137639
NM_001043100
NM_137720
NM_137738
NM_001103928
NM_166512
NM_137981
NM_079143
NM_079144
NM_079157
NM_138241
NM_168019
NM_079177
NM_057232
NM_139633
NM_168079
NM_168078
NM_139618
NM_139649
NM_057930
NM_144196
NM_001144423
NM_168244
NM_144191
NM_001259735
NM_168288
NM_001031943
NM_168396
NM_140154
NM_140163
NM_140165
NM_168441
NM_140181
NM_080275
NM_140273
NM_080077
NM_140352
NM_206350
NM_140603
NM_001043144
NM_140621
NM_168657
NM_140615
NM_140646
NM_140660
NM_079397
NM_140765
NM_140776
NM_140777
NM_001259896
NM_140805
NM_176359
NM_168796
NM_168795
NM_168797
NM_141052
NM_141099
NM_141097
NM_141098
NM_141103
NM_141088
NM_141186
NM_141189
NM_141364
NM_169130
NM_141368
NM_141371
NM_141384
NM_141383
NM_001170058
NM_141379
NM_141420
NM_144368
NM_080175
NM_057983
NM_142057
NM_001104314
NM_142115
NM_001144585
NM_142187
NM_142347
NM_142349
NM_142370
NM_079667
NM_142380
NM_169766
NM_142382
NM_142881
NM_142918
NM_142963
NM_142985
NM_143112
NM_170211
NM_143237
NM_143229
NM_143233
NM_170415
NM_143456
NM_143527
NM_143635



In [22]:

    
wanted_genes









    Out[22]:





set(['NM_140273.2_at',
     'NM_136685.2_at',
     'NM_164888.3_at',
     'NM_143237.3_at',
     'NM_140615.2_at',
     'NM_169130.1_at',
     'NM_001201799.1_at',
     'NM_137720.3_at',
     'NM_142881.3_at',
     'NM_139649.2_at',
     'NM_001259896.1_at',
     'NM_057596.3_at',
     'NM_137738.2_at',
     'NM_078794.3_at',
     'NM_001031943.2_at',
     'NM_132723.2_at',
     'NM_001144751.1_at',
     'NM_176222.1_at',
     'NM_140660.3_at',
     'NM_142382.2_at',
     'NM_079157.2_at',
     'NM_137176.2_at',
     'NM_176359.1_at',
     'NM_141099.2_at',
     'NM_142347.2_at',
     'NM_001170058.1_at',
     'NM_143527.2_at',
     'NM_079397.2_at',
     'NM_001103691.2_at',
     'NM_079063.3_at',
     'NM_141383.1_at',
     'NM_142187.2_at',
     'NM_137115.2_at',
     'NM_079667.3_at',
     'NM_168441.1_at',
     'NM_141098.2_at',
     'NM_167540.3_at',
     'NM_057232.4_at',
     'NM_143112.2_at',
     'NM_001042847.2_at',
     'NM_168079.1_at',
     'NM_079028.2_at',
     'NM_137559.1_at',
     'NM_136240.2_at',
     'NM_144379.3_at',
     'NM_144111.2_at',
     'NM_140776.2_at',
     'NM_138241.3_at',
     'NM_141189.1_at',
     'NM_135030.2_at',
     'NM_141379.1_at',
     'NM_165362.1_at',
     'NM_080175.2_at',
     'NM_130688.3_at',
     'NM_206350.2_at',
     'NM_166277.2_at',
     'NM_137475.2_at',
     'NM_137316.3_at',
     'NM_135391.2_at',
     'NM_078798.4_at',
     'NM_139618.3_at',
     'NM_135590.1_at',
     'NM_079177.3_at',
     'NM_140765.3_at',
     'NM_142370.1_at',
     'NM_135952.1_at',
     'NM_137981.2_at',
     'NM_001103616.1_at',
     'NM_078583.2_at',
     'NM_001104314.1_at',
     'NM_131995.1_at',
     'NM_001043100.2_at',
     'NM_140777.2_at',
     'NM_137057.2_at',
     'NM_168797.2_at',
     'NM_144196.2_at',
     'NM_001043144.1_at',
     'NM_141384.3_at',
     'NM_001169518.1_at',
     'NM_142057.2_at',
     'NM_143233.2_at',
     'NM_137574.2_at',
     'NM_132034.1_at',
     'NM_080275.2_at',
     'NM_141371.2_at',
     'NM_168288.2_at',
     'NM_137617.3_at',
     'NM_132749.1_at',
     'NM_132341.3_at',
     'NM_132038.2_at',
     'NM_131923.3_at',
     'NM_131984.1_at',
     'NM_168657.1_at',
     'NM_166512.2_at',
     'NM_164601.1_at',
     'NM_206133.3_at',
     'NM_134577.1_at',
     'NM_142985.4_at',
     'NM_079025.4_at',
     'NM_078979.3_at',
     'NM_168795.3_at',
     'NM_140646.3_at',
     'NM_165363.1_at',
     'NM_001103387.1_at',
     'NM_001201871.1_at',
     'NM_001169156.1_at',
     'NM_079144.4_at',
     'NM_001144585.1_at',
     'NM_080077.2_at',
     'NM_057983.4_at',
     'NM_143456.2_at',
     'NM_136145.3_at',
     'NM_136807.1_at',
     'NM_144191.4_at',
     'NM_057444.3_at',
     'NM_137158.3_at',
     'NM_166957.1_at',
     'NM_141186.3_at',
     'NM_135869.1_at',
     'NM_168396.1_at',
     'NM_168796.3_at',
     'NM_001144423.2_at',
     'NM_133117.2_at',
     'NM_079021.4_at',
     'NM_170211.2_at',
     'NM_001201830.1_at',
     'NM_141103.3_at',
     'NM_079005.4_at',
     'NM_140163.2_at',
     'NM_168019.3_at',
     'NM_135313.2_at',
     'NM_135844.3_at',
     'NM_140181.1_at',
     'NM_139633.2_at',
     'NM_132713.2_at',
     'NM_144109.1_at',
     'NM_164602.1_at',
     'NM_132571.1_at',
     'NM_141420.3_at',
     'NM_001014489.2_at',
     'NM_142918.2_at',
     'NM_142115.1_at',
     'NM_130535.2_at',
     'NM_144368.2_at',
     'NM_170415.4_at',
     'NM_134601.2_at',
     'NM_142380.3_at',
     'NM_001201917.1_at',
     'NM_079020.4_at',
     'NM_142963.3_at',
     'NM_079143.2_at',
     'NM_140154.2_at',
     'NM_142349.2_at',
     'NM_141364.1_at',
     'NM_164740.2_at',
     'NM_132525.2_at',
     'NM_140805.1_at',
     'NM_144380.2_at',
     'NM_057930.3_at',
     'NM_137361.3_at',
     'NM_137639.1_at',
     'NM_168244.2_at',
     'NM_143229.1_at',
     'NM_168078.1_at',
     'NM_001259447.1_at',
     'NM_135329.2_at',
     'NM_132756.2_at',
     'NM_141088.1_at',
     'NM_136841.2_at',
     'NM_140621.1_at',
     'NM_140603.1_at',
     'NM_130687.2_at',
     'NM_134874.3_at',
     'NM_165165.1_at',
     'NM_140165.1_at',
     'NM_141368.2_at',
     'NM_135456.3_at',
     'NM_136679.4_at',
     'NM_137608.2_at',
     'NM_141052.2_at',
     'NM_001103928.1_at',
     'NM_140352.2_at',
     'NM_143635.1_at',
     'NM_169766.2_at',
     'NM_167061.2_at',
     'NM_001259735.1_at',
     'NM_143761.3_at',
     'NM_141097.3_at'])



In [ ]: