In [1]:
%run GLOBALS.py
3.5.1 (v3.5.1:37a07cee5969, Dec 5 2015, 21:12:44)
[GCC 4.2.1 (Apple Inc. build 5666) (dot 3)]
The goal of this notebook is to investigate/justify why some samples "look" weird when summing across contigs.
In [2]:
import matplotlib as mpl
% matplotlib inline
import pandas as pd
import seaborn as sns
from IPython.display import IFrame
In [3]:
import elviz_utils
In [4]:
reduced = pd.read_csv('../results/reduced_data--all_phylogeny_remains.csv')
In [5]:
sample_info = elviz_utils.read_sample_info('../')
In [6]:
sample_info.head()
Out[6]:
ID
oxy
rep
week
project
0
1_LOW4
Low
1
4
1056013
1
13_LOW5
Low
1
5
1056037
2
25_LOW6
Low
1
6
1056061
3
37_LOW7
Low
1
7
1056085
4
49_LOW8
Low
1
8
1056109
In [7]:
IFrame('./plot_copies/160330_Order-Burkholderiales_Methylophilales_Methylococcales--Phylum-Bacteroidetes--rep.pdf',
width=800, height=300)
Out[7]:
In [8]:
ls "../plots/mixed_phylogeny/"
Family-Bacteriovoracaceae_Myxococcaceae--rep--annotated.pdf
Family-Bacteriovoracaceae_Myxococcaceae--rep.pdf
Genus-Methylobacter_Methylovulum_Methylomonas_Methylomicrobium_Methyloglobulus_Methylococcus_Methylocaldum_Methylosarcina--rep.pdf
Genus-Methylotenera_Methylovorus_Methylophilus_Methylobacillus--rep.pdf
Order-Burkholderiales_Methylophilales_Methylococcales--Phylum-Bacteroidetes--rep.pdf
Phylum-Bacteroidetes--Order-Burkholderiales_Methylophilales_Methylococcales--rep.pdf
In [9]:
sample_info[(sample_info['rep'] == 1) &
(sample_info['oxy'] == 'High') &
(sample_info['week'].isin([8, 10]))]
Out[9]:
ID
oxy
rep
week
project
48
55_HOW8
High
1
8
1056121
50
79_HOW10
High
1
10
1056169
In [10]:
reduced[(reduced['Order']== 'Burkholderiales') &(reduced['ID']=='55_HOW8')]
Out[10]:
Kingdom
Phylum
Class
Order
Family
Genus
Length
abundance
project
ID
oxy
rep
week
28425
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
NaN
other
7293012
0.328695
1056121
55_HOW8
High
1
8
28429
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Acidovorax
3276838
0.051180
1056121
55_HOW8
High
1
8
28430
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
other
3066762
0.047577
1056121
55_HOW8
High
1
8
28440
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
other
180848
0.007296
1056121
55_HOW8
High
1
8
28444
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Janthinobacterium
200994
0.005747
1056121
55_HOW8
High
1
8
28445
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Caldimonas
65886
0.005305
1056121
55_HOW8
High
1
8
28446
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Azohydromonas
95295
0.005024
1056121
55_HOW8
High
1
8
28447
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Variovorax
216718
0.004889
1056121
55_HOW8
High
1
8
28448
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Polaromonas
235192
0.004613
1056121
55_HOW8
High
1
8
28451
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Curvibacter
156196
0.003728
1056121
55_HOW8
High
1
8
28453
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Chitinimonas
91837
0.003180
1056121
55_HOW8
High
1
8
28454
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Comamonas
146042
0.003116
1056121
55_HOW8
High
1
8
28455
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Burkholderia
141186
0.002358
1056121
55_HOW8
High
1
8
28456
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Massilia
80712
0.002023
1056121
55_HOW8
High
1
8
28459
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Cupriavidus
50983
0.001542
1056121
55_HOW8
High
1
8
28461
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Herbaspirillum
57938
0.001331
1056121
55_HOW8
High
1
8
28464
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Alicycliphilus
52265
0.001249
1056121
55_HOW8
High
1
8
28465
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Ramlibacter
57246
0.001157
1056121
55_HOW8
High
1
8
28467
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Hydrogenophaga
34200
0.001012
1056121
55_HOW8
High
1
8
28473
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Pseudacidovorax
25347
0.000923
1056121
55_HOW8
High
1
8
28476
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Ralstonia
47142
0.000853
1056121
55_HOW8
High
1
8
28479
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Limnohabitans
50963
0.000786
1056121
55_HOW8
High
1
8
28485
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Hylemonella
30341
0.000661
1056121
55_HOW8
High
1
8
28494
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Derxia
20230
0.000476
1056121
55_HOW8
High
1
8
28495
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Delftia
34937
0.000471
1056121
55_HOW8
High
1
8
28496
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
other
22668
0.000455
1056121
55_HOW8
High
1
8
28500
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Herminiimonas
17493
0.000429
1056121
55_HOW8
High
1
8
28502
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Verminephrobacter
24390
0.000397
1056121
55_HOW8
High
1
8
28504
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Duganella
10154
0.000387
1056121
55_HOW8
High
1
8
28538
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Ottowia
24544
0.000269
1056121
55_HOW8
High
1
8
28548
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Bordetella
8768
0.000238
1056121
55_HOW8
High
1
8
28594
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Advenella
3801
0.000156
1056121
55_HOW8
High
1
8
28597
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Collimonas
13129
0.000155
1056121
55_HOW8
High
1
8
28619
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Achromobacter
8489
0.000124
1056121
55_HOW8
High
1
8
28662
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Pusillimonas
4803
0.000088
1056121
55_HOW8
High
1
8
28727
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
other
8612
0.000061
1056121
55_HOW8
High
1
8
28731
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Pandoraea
6765
0.000059
1056121
55_HOW8
High
1
8
28906
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Brachymonas
2404
0.000026
1056121
55_HOW8
High
1
8
28926
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Polynucleobacter
1121
0.000025
1056121
55_HOW8
High
1
8
28932
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Alcaligenes
2955
0.000024
1056121
55_HOW8
High
1
8
28939
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Candidatus Glomeribacter
4184
0.000023
1056121
55_HOW8
High
1
8
29110
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Sutterellaceae
Parasutterella
1289
0.000012
1056121
55_HOW8
High
1
8
29174
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Lautropia
784
0.000009
1056121
55_HOW8
High
1
8
29267
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Taylorella
639
0.000006
1056121
55_HOW8
High
1
8
29340
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Oligella
1263
0.000005
1056121
55_HOW8
High
1
8
29374
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Oxalobacter
517
0.000003
1056121
55_HOW8
High
1
8
In [11]:
reduced[(reduced['Order']== 'Burkholderiales') &(reduced['ID']=='79_HOW10')]
Out[11]:
Kingdom
Phylum
Class
Order
Family
Genus
Length
abundance
project
ID
oxy
rep
week
40950
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
NaN
other
20055769
0.188278
1056169
79_HOW10
High
1
10
40952
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
other
8980139
0.117398
1056169
79_HOW10
High
1
10
40954
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Acidovorax
8257013
0.091013
1056169
79_HOW10
High
1
10
40961
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Comamonas
950034
0.011405
1056169
79_HOW10
High
1
10
40962
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Polaromonas
472251
0.010333
1056169
79_HOW10
High
1
10
40963
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Curvibacter
688999
0.009526
1056169
79_HOW10
High
1
10
40964
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Variovorax
496236
0.008910
1056169
79_HOW10
High
1
10
40965
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Azohydromonas
281903
0.006750
1056169
79_HOW10
High
1
10
40967
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Burkholderia
289132
0.004447
1056169
79_HOW10
High
1
10
40968
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Janthinobacterium
226737
0.004122
1056169
79_HOW10
High
1
10
40969
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
other
223136
0.003903
1056169
79_HOW10
High
1
10
40974
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Caldimonas
90472
0.003038
1056169
79_HOW10
High
1
10
40978
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Cupriavidus
160249
0.002732
1056169
79_HOW10
High
1
10
40981
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Alicycliphilus
160291
0.002632
1056169
79_HOW10
High
1
10
40984
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Limnohabitans
75564
0.002478
1056169
79_HOW10
High
1
10
40985
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Chitinimonas
120778
0.002390
1056169
79_HOW10
High
1
10
40988
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Hydrogenophaga
78541
0.001956
1056169
79_HOW10
High
1
10
40989
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Ramlibacter
72566
0.001934
1056169
79_HOW10
High
1
10
40990
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Massilia
95180
0.001860
1056169
79_HOW10
High
1
10
40997
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Herbaspirillum
67801
0.001488
1056169
79_HOW10
High
1
10
40998
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Ottowia
54297
0.001459
1056169
79_HOW10
High
1
10
41003
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Delftia
105030
0.001175
1056169
79_HOW10
High
1
10
41004
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Ralstonia
74456
0.001155
1056169
79_HOW10
High
1
10
41006
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Pseudacidovorax
40852
0.000978
1056169
79_HOW10
High
1
10
41009
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Hylemonella
44374
0.000848
1056169
79_HOW10
High
1
10
41010
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Herminiimonas
36334
0.000833
1056169
79_HOW10
High
1
10
41017
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Achromobacter
44983
0.000596
1056169
79_HOW10
High
1
10
41020
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Bordetella
28491
0.000565
1056169
79_HOW10
High
1
10
41022
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Collimonas
18295
0.000541
1056169
79_HOW10
High
1
10
41024
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Derxia
36530
0.000531
1056169
79_HOW10
High
1
10
41025
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
other
80941
0.000520
1056169
79_HOW10
High
1
10
41038
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Oxalobacteraceae
Duganella
19955
0.000356
1056169
79_HOW10
High
1
10
41057
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Verminephrobacter
24364
0.000277
1056169
79_HOW10
High
1
10
41063
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Pusillimonas
13958
0.000232
1056169
79_HOW10
High
1
10
41071
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Pandoraea
20781
0.000215
1056169
79_HOW10
High
1
10
41095
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
other
11963
0.000166
1056169
79_HOW10
High
1
10
41107
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Comamonadaceae
Brachymonas
8489
0.000150
1056169
79_HOW10
High
1
10
41108
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Advenella
4246
0.000148
1056169
79_HOW10
High
1
10
41121
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Lautropia
4935
0.000128
1056169
79_HOW10
High
1
10
41156
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Alcaligenes
26796
0.000098
1056169
79_HOW10
High
1
10
41273
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Polynucleobacter
2814
0.000044
1056169
79_HOW10
High
1
10
41274
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Burkholderiaceae
Candidatus Glomeribacter
1634
0.000043
1056169
79_HOW10
High
1
10
41448
Bacteria
Proteobacteria
Betaproteobacteria
Burkholderiales
Alcaligenaceae
Oligella
1443
0.000008
1056169
79_HOW10
High
1
10
In [ ]:
Content source: JanetMatsen/elvizAnalysis
Similar notebooks: