Read BAM file and get information about mapping

Author: Thomas Cokelaer, 2016-2018



In [1]:

    
%pylab inline









    



Populating the interactive namespace from numpy and matplotlib



In [2]:

    
from sequana import BAM, sequana_data



In [3]:

    
b = BAM(sequana_data('test.bam', 'testing'))



In [4]:

    
b.plot_bar_mapq()



In [5]:

    
b.get_flags_as_df().sum()









    Out[5]:





0          0
1       1000
2        484
4          2
8          2
16       499
32       500
64       477
128      523
256       64
512        0
1024       0
2048       0
dtype: int64



In [6]:

    
b.get_full_stats_as_df()









    Out[6]:







  
    
      
      description
      count
    
  
  
    
      30
      pairs on different chromosomes
      0
    
    
      19
      bases duplicated
      0
    
    
      18
      bases trimmed
      0
    
    
      13
      reads QC failed
      0
    
    
      12
      reads MQ0
      0
    
    
      11
      reads duplicated
      0
    
    
      1
      filtered sequences
      0
    
    
      3
      is sorted
      1
    
    
      27
      inward oriented pairs
      169
    
    
      8
      reads unmapped
      2
    
    
      28
      outward oriented pairs
      229
    
    
      29
      pairs with other orientation
      3
    
    
      24
      average quality
      36.9
    
    
      26
      insert size standard deviation
      3817.6
    
    
      4
      1st fragments
      451
    
    
      9
      reads properly paired
      462
    
    
      25
      insert size average
      4775.2
    
    
      5
      last fragments
      485
    
    
      20
      mismatches
      51
    
    
      14
      non-primary alignments
      64
    
    
      17
      bases mapped (cigar)
      65641
    
    
      21
      error rate
      7.769534e-04
    
    
      16
      bases mapped
      70050
    
    
      15
      total length
      70200
    
    
      22
      average length
      75
    
    
      23
      maximum length
      75
    
    
      7
      reads mapped and paired
      932
    
    
      6
      reads mapped
      934
    
    
      10
      reads paired
      936
    
    
      2
      sequences
      936
    
    
      0
      raw total sequences
      936



In [ ]:

	description	count
30	pairs on different chromosomes	0
19	bases duplicated	0
18	bases trimmed	0
13	reads QC failed	0
12	reads MQ0	0
11	reads duplicated	0
1	filtered sequences	0
3	is sorted	1
27	inward oriented pairs	169
8	reads unmapped	2
28	outward oriented pairs	229
29	pairs with other orientation	3
24	average quality	36.9
26	insert size standard deviation	3817.6
4	1st fragments	451
9	reads properly paired	462
25	insert size average	4775.2
5	last fragments	485
20	mismatches	51
14	non-primary alignments	64
17	bases mapped (cigar)	65641
21	error rate	7.769534e-04
16	bases mapped	70050
15	total length	70200
22	average length	75
23	maximum length	75
7	reads mapped and paired	932
6	reads mapped	934
10	reads paired	936
2	sequences	936
0	raw total sequences	936