In [156]:
import pandas as pd
import numpy as np
from Bio import SeqIO
from random import sample
from collections import defaultdict
In [166]:
ird_sequences = [s for s in SeqIO.parse('ird_seqs_name_as_accession.fasta', 'fasta')]
len(ird_sequences)
Out[166]:
21868
In [170]:
new_sequences = [s for s in SeqIO.parse('Alaska_waterfowl_79viruses_seqs_20151223.fasta', 'fasta')]
len(new_sequences)
Out[170]:
647
In [172]:
combined_sequences = []
combined_sequences.extend(ird_sequences)
combined_sequences.extend(new_sequences)
SeqIO.write(combined_sequences, '20160104_brandt Sequences.fasta', 'fasta')
Out[172]:
22515
In [ ]:
# Write the IRD-like table for the sequences. There should be 2648 rows at the end.
# The IRD tables have the following columns:
# - Segment (number)
# - Protein Name (string)
# - Sequence Accession (alphanumeric)
# - Complete Genome (Yes/No)
# - Segment Length (number)
# - Subtype (alphanumerica)
# - Collection Date (date)
# - Host Species (string)
# - Country (string)
# - State/Province (string)
# - Flu Season (alphanumeric)
# - Strain Name (alphanumeric)
In [159]:
# Read in the data
ird_df = pd.read_csv('20160104_brandt_ird.csv', parse_dates=['Collection Date'], na_filter=False)
# Clean strain name. Remove subtype from strain name, replace spaces with underscore.
ird_df['Strain Name'] = ird_df['Strain Name'].str.split('(').str[0].str.replace(' ', '_')
# Clean the Host Species names by removing "IRD" and removing "/Avian"
ird_df['Host Species'] = ird_df['Host Species'].str.split(':').str[1].str.replace('/Avian', '')
ird_df
Out[159]:
Segment
Protein Name
Sequence Accession
Complete Genome
Segment Length
Subtype
Collection Date
Host Species
Country
State/Province
Flu Season
Strain Name
0
7
M1,M2
KU289739
Yes
1027
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
1
5
NP
KU289741
Yes
1540
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
2
8
NS1,NS2
KU289742
Yes
865
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
3
3
PA,PA-N155,PA-N182,PA-X protein(+61)
KU289743
Yes
2208
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
4
1
PB2
KU289745
Yes
2307
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
5
4
HA
KU289738
Yes
1706
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
6
6
NA
KU289740
Yes
1428
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
7
2
PB1,PB1-F2,PB1-N40
KU289744
Yes
2316
H7N3
2010-02-18
American Black Duck
USA
Delaware
09-10
A/American_black_duck/Delaware/A00870108/2010
8
1
PB2
CY079459
Yes
2307
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
9
8
NS1,NS2
CY079456
Yes
852
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
10
6
NA
CY079454
Yes
1446
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
11
2
PB1,PB1-F2,PB1-N40
CY079458
Yes
2316
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
12
7
M1,M2
CY079453
Yes
1002
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
13
3
PA,PA-N155,PA-N182,PA-X protein(+61)
CY079457
Yes
2208
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
14
5
NP
CY079455
Yes
1540
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
15
4
HA
CY079452
Yes
1742
H5N2
2008-10-26
American Black Duck
USA
Illinois
08-09
A/American_black_duck/Illinois/08OS2688/2008
16
4
HA
CY097534
Yes
1719
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
17
2
PB1,PB1-F2,PB1-N40
CY097540
Yes
2316
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
18
7
M1,M2
CY097535
Yes
990
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
19
1
PB2
CY097541
Yes
2316
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
20
5
NP
CY097537
Yes
1541
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
21
6
NA
CY097536
Yes
1437
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
22
3
PA,PA-N155,PA-N182,PA-X protein(+61)
CY097539
Yes
2201
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
23
8
NS1,NS2
CY097538
Yes
865
H8N4
2009-11-29
American Black Duck
USA
Illinois
09-10
A/American_black_duck/Illinois/4119/2009
24
1
PB2
KP636475
Yes
2280
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
25
5
NP
KP636479
Yes
1497
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
26
2
PB1,PB1-F2,PB1-N40
KP636476
Yes
2274
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
27
4
HA
KP636478
Yes
1701
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
28
6
NA
KP636480
Yes
1413
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
29
7
M1,M2
KP636481
Yes
982
H3N8
2008-01-01
American Black Duck
USA
Maine
-N/A-
A/American_black_duck/Maine/44411/532/2008
...
...
...
...
...
...
...
...
...
...
...
...
...
21838
6
NA
CY132959
Yes
1421
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21839
4
HA
CY132957
Yes
1740
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21840
1
PB2
CY132964
Yes
2307
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21841
7
M1,M2
CY132958
Yes
1002
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21842
2
PB1,PB1-F2,PB1-N40
CY132963
Yes
2316
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21843
3
PA,PA-N155,PA-N182,PA-X protein(+61)
CY132962
Yes
2151
H3N8
2010-09-26
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/10OS2778/2010
21844
6
NA
CY167112
Yes
1440
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21845
8
NS1,NS2
CY167114
Yes
865
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21846
5
NP
CY167113
Yes
1540
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21847
4
HA
CY167110
Yes
1740
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21848
2
PB1,PB1-F2,PB1-N40
CY167116
Yes
2316
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21849
1
PB2
CY167117
Yes
2307
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21850
7
M1,M2
CY167111
Yes
1002
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21851
3
PA,PA-N155,PA-N182,PA-X protein(+61)
CY167115
Yes
2196
H3N6
2011-09-24
Duck
USA
Wisconsin
-N/A-
A/wood_duck/Wisconsin/11OS2912/2011
21852
6
NA
CY166655
Yes
1435
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21853
7
M1,M2
CY166654
Yes
1002
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21854
4
HA
CY166653
Yes
1709
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21855
8
NS1,NS2
CY166657
Yes
865
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21856
2
PB1,PB1-F2,PB1-N40
CY166659
Yes
2304
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21857
1
PB2
CY166660
Yes
2316
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21858
5
NP
CY166656
Yes
1540
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21859
3
PA,PA-N155,PA-N182,PA-X protein(+61)
CY166658
Yes
2208
H11N9
2011-10-16
Duck
USA
Wisconsin
11-12
A/wood_duck/Wisconsin/11OS3443/2011
21860
2
PB1
GU050165
Yes
2316
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21861
7
M1,M2
GU050160
Yes
1002
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21862
1
PB2
GU050166
Yes
2316
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21863
6
NA
GU050161
Yes
1383
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21864
5
NP
GU050162
Yes
1540
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21865
8
NS1,NS2
GU050163
Yes
865
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21866
4
HA
GU050159
Yes
1736
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21867
3
PA,PA-N155,PA-N182,PA-X protein(+61)
GU050164
Yes
2208
H5N2
2007-01-01
Parrot
USA
California
-N/A-
A/yellow-headed_Amazon/California/500658/2007
21868 rows × 12 columns
In [160]:
# The 79 new sequences that have been added to the dataset are not in the format of the IRD. I will make them as such.
newseqs_df = pd.read_csv('Alaska_waterfowl_79viruses_metadata_20151223.csv', parse_dates=['CollectionDate'])
newseqs_df['Strain_name'] = newseqs_df['Strain_name'].str.replace(' ', '_')
newseqs_df.set_index('Strain_name')
Out[160]:
Subtype
Blinded Number
Organism Name provided by collaborator
Updated Organism Name (names that changed are in blue)
Special Note_JCVIs
Complete/Draft
CEIRS Sample ID
UPDATED?
Age
Age_Brandt
...
Unnamed: 26
Unnamed: 27
Unnamed: 28
Unnamed: 29
Unnamed: 30
Unnamed: 31
Unnamed: 32
Unnamed: 33
Unnamed: 34
Unnamed: 35
Strain_name
A/northern_pintail/Interior_Alaska/10BM03314/2010
H4N4
NIGSP_CEIRS_CIP105_RUNC_00058
Influenza A virus (A/northern pintail/Interior...
Influenza A virus (A/northern pintail/Interior...
NaN
Complete
10BM03314
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/10BM12027/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00061
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
10BM12027
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/northern_pintail/Interior_Alaska/10BM12537/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00062
Influenza A virus (A/northern pintail/Interior...
Influenza A virus (A/northern pintail/Interior...
NaN
Complete
10BM12537
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/10BM13225/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00064
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
10BM13225
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/10BM13335/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00065
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
10BM13335
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/northern_pintail/Interior_Alaska/10BM13543/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00066
Influenza A virus (A/Northern pintail/Interior...
Influenza A virus (A/northern pintail/Interior...
NaN
Complete
10BM13543
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/northern_pintail/Interior_Alaska/10BM15017/2010
H12N5
NIGSP_CEIRS_CIP105_RUNC_00070
Influenza A virus (A/Northern pintail/Interior...
Influenza A virus (A/northern pintail/Interior...
NaN
Complete
10BM15017
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM00293/2011
H10N5
NIGSP_CEIRS_CIP105_RUNC_00074
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM00293
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM00304/2011
H10N5
NIGSP_CEIRS_CIP105_RUNC_00075
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM00304
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM01009/2011
H12N5
NIGSP_CEIRS_CIP105_RUNC_00076
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM01009
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM01179/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00077
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM01179
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM01180/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00078
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM01180
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM01254/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00079
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM01254
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM01255/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00080
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM01255
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02089/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00081
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02089
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02099/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00082
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02099
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM02195/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00083
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM02195
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02557/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00084
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02557
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02703/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00085
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02703
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02923/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00086
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02923
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02987/2011
H2N6
NIGSP_CEIRS_CIP105_RUNC_00087
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02987
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM02991/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00088
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM02991
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM03102/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00089
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM03102
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM03165/2011
H2N9
NIGSP_CEIRS_CIP105_RUNC_00090
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM03165
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM03166/2011
H2N9
NIGSP_CEIRS_CIP105_RUNC_00091
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM03166
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM03436/2011
H2N9
NIGSP_CEIRS_CIP105_RUNC_00092
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM03436
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM03443/2011
mixed
NIGSP_CEIRS_CIP105_RUNC_00093
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
Sequence data indicate that the sample was mix...
Complete
11BM03443
Y
After hatch year
AHY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/American_green-winged_teal/Interior_Alaska/11BM03479/2011
H4N6
NIGSP_CEIRS_CIP105_RUNC_00094
Influenza A virus (A/American green-winged tea...
Influenza A virus (A/American green-winged tea...
NaN
Complete
11BM03479
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM03577/2011
H7N3
NIGSP_CEIRS_CIP105_RUNC_00096
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM03577
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/11BM03591/2011
H2N9
NIGSP_CEIRS_CIP105_RUNC_00097
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
11BM03591
Y
Hatch year
HY
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
A/goose/Interior_Alaska/11PG00148/2011
H6N1
NIGSP_CEIRS_CIP105_RUNC_00163
Influenza A virus (A/goose/Interior Alaska/11P...
Influenza A virus (A/goose/Interior Alaska/11P...
NaN
Complete
11PG00148
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/goose/Interior_Alaska/11PG00149/2011
H6N1
NIGSP_CEIRS_CIP105_RUNC_00164
Influenza A virus (A/goose/Interior Alaska/11P...
Influenza A virus (A/goose/Interior Alaska/11P...
NaN
Complete
11PG00149
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/goose/Interior_Alaska/11PG00437/2011
H2N3
NIGSP_CEIRS_CIP105_RUNC_00165
Influenza A virus (A/goose/Interior Alaska/11P...
Influenza A virus (A/goose/Interior Alaska/11P...
NaN
Complete
11PG00437
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/duck/Interior_Alaska/11PG00451/2011
H2N3
NIGSP_CEIRS_CIP105_RUNC_00166
Influenza A virus (A/duck/Interior Alaska/11PG...
Influenza A virus (A/duck/Interior Alaska/11PG...
NaN
Complete
11PG00451
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/duck/Interior_Alaska/11PG00459/2011
H2N3
NIGSP_CEIRS_CIP105_RUNC_00167
Influenza A virus (A/duck/Interior Alaska/11PG...
Influenza A virus (A/duck/Interior Alaska/11PG...
NaN
Complete
11PG00459
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/duck/Interior_Alaska/11PG00703/2011
mixed
NIGSP_CEIRS_CIP105_RUNC_00169
Influenza A virus (A/duck/Interior Alaska/11PG...
Influenza A virus (A/duck/Interior Alaska/11PG...
Sequence data indicate that the sample was mix...
Draft
11PG00703
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/duck/Interior_Alaska/11PG00704/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00170
Influenza A virus (A/duck/Interior Alaska/11PG...
Influenza A virus (A/duck/Interior Alaska/11PG...
NaN
Complete
11PG00704
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/duck/Interior_Alaska/11PG00730/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00171
Influenza A virus (A/duck/Interior Alaska/11PG...
Influenza A virus (A/duck/Interior Alaska/11PG...
NaN
Complete
11PG00730
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/goose/Interior_Alaska/11PG00987/2011
H3N8
NIGSP_CEIRS_CIP105_RUNC_00173
Influenza A virus (A/goose/Interior Alaska/11P...
Influenza A virus (A/goose/Interior Alaska/11P...
NaN
Complete
11PG00987
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00034/2012
H3N8
NIGSP_CEIRS_CIP105_RUNC_00019
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00034
NaN
Hatch year
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00058/2012
H8N4
NIGSP_CEIRS_CIP105_RUNC_00020
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00058
NaN
Hatch year
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00059/2012
H2N9
NIGSP_CEIRS_CIP105_RUNC_00021
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00059
NaN
Hatch year
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00064/2012
H2N4
NIGSP_CEIRS_CIP105_RUNC_00022
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00064
NaN
After hatch year
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00076/2012
H8N4
NIGSP_CEIRS_CIP105_RUNC_00023
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00076
NaN
Hatch year
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00086/2012
mixed
NIGSP_CEIRS_CIP105_RUNC_00024
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
Sequence data indicate that the sample was mix...
Complete
12ML00086
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00098/2012
H3N8
NIGSP_CEIRS_CIP105_RUNC_00025
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00098
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
A/mallard/Interior_Alaska/12ML00120/2012
H8N4
NIGSP_CEIRS_CIP105_RUNC_00026
Influenza A virus (A/mallard/Interior Alaska/1...
Influenza A virus (A/mallard/Interior Alaska/1...
NaN
Complete
12ML00120
NaN
Unknown
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
92 rows × 35 columns
In [161]:
newseqs = [s for s in SeqIO.parse('Alaska_waterfowl_79viruses_seqs_20151223.fasta', 'fasta')]
len(newseqs) / 8
Out[161]:
80.875
In [162]:
segnum_name = dict()
segnum_name[1] = 'PB2'
segnum_name[2] = 'PB1'
segnum_name[3] = 'PA'
segnum_name[4] = 'HA'
segnum_name[5] = 'NP'
segnum_name[6] = 'NA'
segnum_name[7] = 'M'
segnum_name[8] = 'NS'
name_segnum = dict()
for k, v in segnum_name.items():
name_segnum[v] = k
name_segnum
Out[162]:
{'HA': 4, 'M': 7, 'NA': 6, 'NP': 5, 'NS': 8, 'PA': 3, 'PB1': 2, 'PB2': 1}
In [163]:
newstrains_data = []
for s in newseqs:
strain_name = s.id.split('|')[0]
segment_name = s.id.split('|')[1]
d = dict()
d['Segment'] = name_segnum[segment_name]
d['Protein Name'] = segment_name
d['Sequence Accession'] = 'Not assigned'
d['Complete Genome'] = 'Unconfirmed'
d['Segment Length'] = len(s.seq)
d['Subtype'] = newseqs_df.set_index('Strain_name').ix[strain_name]['Subtype']
d['Collection Date'] = newseqs_df.set_index('Strain_name').ix[strain_name]['CollectionDate']
d['Host Species'] = newseqs_df.set_index('Strain_name').ix[strain_name]['Species_final']
d['Country'] = 'USA'
d['State/Province'] = 'Alaska'
d['Flu Season'] = np.nan
d['Strain Name'] = strain_name
newstrains_data.append(d)
newstrains_df = pd.DataFrame(newstrains_data)
In [164]:
len(newstrains_data) / 8
Out[164]:
80.875
In [165]:
final_df = ird_df.append(newstrains_df).reset_index(drop=True)
final_df['Protein Name'] = final_df['Segment'].apply(lambda x: segnum_name[x])
final_df['Sequence Accession'] = final_df['Strain Name'].str.cat(final_df['Protein Name'], sep='|')
final_df.to_csv('20160104_brandt Sequences.csv')
final_df
Out[165]:
Collection Date
Complete Genome
Country
Flu Season
Host Species
Protein Name
Segment
Segment Length
Sequence Accession
State/Province
Strain Name
Subtype
0
2010-02-18
Yes
USA
09-10
American Black Duck
M
7
1027
A/American_black_duck/Delaware/A00870108/2010|M
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
1
2010-02-18
Yes
USA
09-10
American Black Duck
NP
5
1540
A/American_black_duck/Delaware/A00870108/2010|NP
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
2
2010-02-18
Yes
USA
09-10
American Black Duck
NS
8
865
A/American_black_duck/Delaware/A00870108/2010|NS
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
3
2010-02-18
Yes
USA
09-10
American Black Duck
PA
3
2208
A/American_black_duck/Delaware/A00870108/2010|PA
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
4
2010-02-18
Yes
USA
09-10
American Black Duck
PB2
1
2307
A/American_black_duck/Delaware/A00870108/2010|PB2
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
5
2010-02-18
Yes
USA
09-10
American Black Duck
HA
4
1706
A/American_black_duck/Delaware/A00870108/2010|HA
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
6
2010-02-18
Yes
USA
09-10
American Black Duck
NA
6
1428
A/American_black_duck/Delaware/A00870108/2010|NA
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
7
2010-02-18
Yes
USA
09-10
American Black Duck
PB1
2
2316
A/American_black_duck/Delaware/A00870108/2010|PB1
Delaware
A/American_black_duck/Delaware/A00870108/2010
H7N3
8
2008-10-26
Yes
USA
08-09
American Black Duck
PB2
1
2307
A/American_black_duck/Illinois/08OS2688/2008|PB2
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
9
2008-10-26
Yes
USA
08-09
American Black Duck
NS
8
852
A/American_black_duck/Illinois/08OS2688/2008|NS
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
10
2008-10-26
Yes
USA
08-09
American Black Duck
NA
6
1446
A/American_black_duck/Illinois/08OS2688/2008|NA
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
11
2008-10-26
Yes
USA
08-09
American Black Duck
PB1
2
2316
A/American_black_duck/Illinois/08OS2688/2008|PB1
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
12
2008-10-26
Yes
USA
08-09
American Black Duck
M
7
1002
A/American_black_duck/Illinois/08OS2688/2008|M
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
13
2008-10-26
Yes
USA
08-09
American Black Duck
PA
3
2208
A/American_black_duck/Illinois/08OS2688/2008|PA
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
14
2008-10-26
Yes
USA
08-09
American Black Duck
NP
5
1540
A/American_black_duck/Illinois/08OS2688/2008|NP
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
15
2008-10-26
Yes
USA
08-09
American Black Duck
HA
4
1742
A/American_black_duck/Illinois/08OS2688/2008|HA
Illinois
A/American_black_duck/Illinois/08OS2688/2008
H5N2
16
2009-11-29
Yes
USA
09-10
American Black Duck
HA
4
1719
A/American_black_duck/Illinois/4119/2009|HA
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
17
2009-11-29
Yes
USA
09-10
American Black Duck
PB1
2
2316
A/American_black_duck/Illinois/4119/2009|PB1
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
18
2009-11-29
Yes
USA
09-10
American Black Duck
M
7
990
A/American_black_duck/Illinois/4119/2009|M
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
19
2009-11-29
Yes
USA
09-10
American Black Duck
PB2
1
2316
A/American_black_duck/Illinois/4119/2009|PB2
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
20
2009-11-29
Yes
USA
09-10
American Black Duck
NP
5
1541
A/American_black_duck/Illinois/4119/2009|NP
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
21
2009-11-29
Yes
USA
09-10
American Black Duck
NA
6
1437
A/American_black_duck/Illinois/4119/2009|NA
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
22
2009-11-29
Yes
USA
09-10
American Black Duck
PA
3
2201
A/American_black_duck/Illinois/4119/2009|PA
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
23
2009-11-29
Yes
USA
09-10
American Black Duck
NS
8
865
A/American_black_duck/Illinois/4119/2009|NS
Illinois
A/American_black_duck/Illinois/4119/2009
H8N4
24
2008-01-01
Yes
USA
-N/A-
American Black Duck
PB2
1
2280
A/American_black_duck/Maine/44411/532/2008|PB2
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
25
2008-01-01
Yes
USA
-N/A-
American Black Duck
NP
5
1497
A/American_black_duck/Maine/44411/532/2008|NP
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
26
2008-01-01
Yes
USA
-N/A-
American Black Duck
PB1
2
2274
A/American_black_duck/Maine/44411/532/2008|PB1
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
27
2008-01-01
Yes
USA
-N/A-
American Black Duck
HA
4
1701
A/American_black_duck/Maine/44411/532/2008|HA
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
28
2008-01-01
Yes
USA
-N/A-
American Black Duck
NA
6
1413
A/American_black_duck/Maine/44411/532/2008|NA
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
29
2008-01-01
Yes
USA
-N/A-
American Black Duck
M
7
982
A/American_black_duck/Maine/44411/532/2008|M
Maine
A/American_black_duck/Maine/44411/532/2008
H3N8
...
...
...
...
...
...
...
...
...
...
...
...
...
22485
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NA
6
1425
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22486
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NP
5
1526
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22487
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NS
8
865
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22488
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PA
3
2208
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22489
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB1
2
2309
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22490
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB2
1
2295
A/northern_shoveler/Interior_Alaska/11BM03855/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03855/...
H3N8
22491
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
HA
4
1731
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22492
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
M
7
1002
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22493
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NA
6
1421
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22494
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NP
5
1540
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22495
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NS
8
865
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22496
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PA
3
2202
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22497
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB1
2
2316
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22498
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB2
1
2295
A/northern_shoveler/Interior_Alaska/11BM03861/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03861/...
H3N8
22499
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
HA
4
1731
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22500
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
M
7
1002
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22501
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NA
6
1425
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22502
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NP
5
1532
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22503
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
NS
8
865
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22504
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PA
3
2208
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22505
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB1
2
2309
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22506
2011-09-03
Unconfirmed
USA
NaN
Northern shoveler
PB2
1
2295
A/northern_shoveler/Interior_Alaska/11BM03889/...
Alaska
A/northern_shoveler/Interior_Alaska/11BM03889/...
H3N8
22507
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
HA
4
1700
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22508
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
M
7
1002
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22509
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
NA
6
1434
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22510
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
NP
5
1540
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22511
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
NS
8
865
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22512
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
PA
3
2196
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22513
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
PB1
2
2316
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22514
2011-09-09
Unconfirmed
USA
NaN
Northern shoveler
PB2
1
2301
A/northern_shoveler/Interior_Alaska/11ML00037/...
Alaska
A/northern_shoveler/Interior_Alaska/11ML00037/...
H4N6
22515 rows × 12 columns
In [ ]:
Content source: ericmjl/reassortment-minto-life-history
Similar notebooks: