In [1]:
%matplotlib inline
In [2]:
import os
import sys
from ggplot import *
pyrnafold_path = os.path.abspath(os.path.join('..'))
if pyrnafold_path not in sys.path:
sys.path.append(pyrnafold_path)
from pyrnafold.pyrnafold import trange_df, sig_positions
In [3]:
ls -lah ../data
total 1.6M
drwxrwxr-x 2 ilya ilya 4.0K Apr 18 13:26 ./
drwxrwxr-x 8 ilya ilya 4.0K Apr 18 12:55 ../
-rw-rw-r-- 1 ilya ilya 112K Apr 18 13:26 hHSR_35.txt
-rw-rw-r-- 1 ilya ilya 115K Apr 18 13:26 hHSR_36.txt
-rw-rw-r-- 1 ilya ilya 118K Apr 18 13:26 hHSR_37.txt
-rw-rw-r-- 1 ilya ilya 121K Apr 18 13:26 hHSR_38.txt
-rw-rw-r-- 1 ilya ilya 123K Apr 18 13:26 hHSR_39.txt
-rw-rw-r-- 1 ilya ilya 127K Apr 18 13:26 hHSR_40.txt
-rw-rw-r-- 1 ilya ilya 132K Apr 18 13:26 hHSR_41.txt
-rw-rw-r-- 1 ilya ilya 136K Apr 18 13:26 hHSR_42.txt
-rw-rw-r-- 1 ilya ilya 140K Apr 18 13:26 hHSR_43.txt
-rw-rw-r-- 1 ilya ilya 145K Apr 18 13:26 hHSR_44.txt
-rw-rw-r-- 1 ilya ilya 150K Apr 18 13:26 hHSR_45.txt
-rw-rw-r-- 1 ilya ilya 611 Apr 18 12:45 hHSR.fa
-rw-rw-r-- 1 ilya ilya 7.1K Apr 18 13:13 ROSE1_37.txt
-rw-rw-r-- 1 ilya ilya 7.8K Apr 18 13:13 ROSE1_38.txt
-rw-rw-r-- 1 ilya ilya 8.1K Apr 18 13:13 ROSE1_39.txt
-rw-rw-r-- 1 ilya ilya 8.2K Apr 18 13:13 ROSE1_40.txt
-rw-rw-r-- 1 ilya ilya 8.6K Apr 18 13:13 ROSE1_41.txt
-rw-rw-r-- 1 ilya ilya 8.8K Apr 18 13:13 ROSE1_42.txt
-rw-rw-r-- 1 ilya ilya 9.3K Apr 18 13:13 ROSE1_43.txt
-rw-rw-r-- 1 ilya ilya 19K Apr 18 12:58 ROSE1_dp.ps
-rw-rw-r-- 1 ilya ilya 126 Apr 18 12:46 rose.fa
In [4]:
df = trange_df('../data/hHSR', trange=range(35, 45))
df
Out[4]:
pos
Diff
Temp
0
0
0.000000
36
1
1
0.002137
36
2
2
0.002143
36
3
3
0.001084
36
4
4
0.001551
36
5
5
0.002297
36
6
6
0.002091
36
7
7
0.001138
36
8
8
0.002524
36
9
9
0.004284
36
10
10
0.005770
36
11
11
0.006140
36
12
12
0.006634
36
13
13
0.001101
36
14
14
0.001096
36
15
15
0.006333
36
16
16
0.006235
36
17
17
0.006208
36
18
18
0.009629
36
19
19
0.011970
36
20
20
0.002286
36
21
21
0.000415
36
22
22
0.000374
36
23
23
0.000376
36
24
24
0.000389
36
25
25
0.001158
36
26
26
0.004279
36
27
27
0.003266
36
28
28
0.006666
36
29
29
0.004278
36
...
...
...
...
575
575
0.136961
44
576
576
0.008605
44
577
577
0.017564
44
578
578
0.020003
44
579
579
0.020030
44
580
580
0.019213
44
581
581
0.018791
44
582
582
0.018228
44
583
583
0.071693
44
584
584
0.001168
44
585
585
0.011023
44
586
586
0.015023
44
587
587
0.007591
44
588
588
0.006163
44
589
589
0.006088
44
590
590
0.002258
44
591
591
0.001765
44
592
592
0.060197
44
593
593
0.019381
44
594
594
0.019577
44
595
595
0.020931
44
596
596
0.005520
44
597
597
0.023830
44
598
598
0.020185
44
599
599
0.016449
44
600
600
0.012782
44
601
601
0.000806
44
602
602
0.001157
44
603
603
0.007710
44
604
604
0.013289
44
5445 rows × 3 columns
In [5]:
df.describe()
Out[5]:
pos
Diff
Temp
count
5445.000000
5445.000000
5445.000000
mean
302.000000
0.030726
40.000000
std
174.664258
0.042001
2.582226
min
0.000000
0.000000
36.000000
25%
151.000000
0.003713
38.000000
50%
302.000000
0.013258
40.000000
75%
453.000000
0.038685
42.000000
max
604.000000
0.254724
44.000000
In [6]:
g = ggplot(df, aes(xmin='pos-1',xmax='pos', ymin=0, ymax='Diff')) \
+ geom_rect() \
+ facet_wrap('Temp')
print(g)
<ggplot: (-9223363292714695957)>
In [10]:
df[sig_positions(df, num_sigma=3)]
Out[10]:
pos
Diff
Temp
474
474
0.157715
40
475
475
0.157546
40
476
476
0.157095
40
474
474
0.170586
41
475
475
0.184866
41
476
476
0.184355
41
477
477
0.183233
41
297
297
0.157668
42
302
302
0.172771
42
337
337
0.172771
42
341
341
0.157668
42
474
474
0.162031
42
475
475
0.210209
42
476
476
0.209649
42
477
477
0.208365
42
483
483
0.171425
42
487
487
0.165673
42
488
488
0.163947
42
489
489
0.162715
42
490
490
0.162722
42
491
491
0.163510
42
505
505
0.163510
42
506
506
0.162722
42
507
507
0.162715
42
508
508
0.163947
42
509
509
0.165673
42
511
511
0.163513
42
512
512
0.172585
42
513
513
0.170463
42
514
514
0.169901
42
...
...
...
...
480
480
0.158090
44
483
483
0.207394
44
487
487
0.208092
44
488
488
0.205906
44
489
489
0.204361
44
490
490
0.204371
44
491
491
0.205139
44
505
505
0.205139
44
506
506
0.204371
44
507
507
0.204361
44
508
508
0.205906
44
509
509
0.208092
44
511
511
0.193020
44
512
512
0.203825
44
513
513
0.201002
44
514
514
0.200197
44
515
515
0.199886
44
516
516
0.200614
44
517
517
0.161292
44
518
518
0.201256
44
519
519
0.195252
44
523
523
0.174697
44
543
543
0.195252
44
544
544
0.201256
44
546
546
0.200614
44
547
547
0.199886
44
548
548
0.200197
44
549
549
0.201002
44
550
550
0.203825
44
551
551
0.167955
44
144 rows × 3 columns
In [ ]:
Content source: eco32i/pyRNAfold
Similar notebooks: