Three metadata files for this analysis:

  • tara_metadata_SRF.csv -- generated by singlecell_tara_stats.ipynb
  • genome_metadata.csv -- generated here
  • og_metadata.csv -- generated here

In [2]:
import pandas as pd


/Users/luke/anaconda/envs/qiime190/lib/python2.7/site-packages/pandas/computation/__init__.py:19: UserWarning: The installed version of numexpr 2.4.4 is not supported in pandas and will be not be used

  UserWarning)

Tara metadata


In [114]:
# read tara_metadata_SRF.tsv
df_tara_metadata = pd.read_csv('/Users/luke/singlecell/notebooks/tara_metadata_SRF.tsv', sep='\t', index_col=0)

In [115]:
df_tara_metadata


Out[115]:
PANGAEA Sample ID Sample label [TARA_station#_environmental-feature_size-fraction].1 Mean_Date [YY/MM/DD hh:mm]* Mean_Lat* Mean_Long* Mean_Depth [m]* Mean_Temperature [deg C]* Mean_Salinity [PSU]* Mean_Oxygen [umol/kg]* Mean_Nitrates[umol/L]* ... OG.Richness OG.Evenness FC - heterotrophs [cells/mL] FC - autotrophs [cells/mL] FC - bacteria [cells/mL] FC - picoeukaryotes [cells/mL] minimum generation time [h] category_latitude category_temperature category_redsea
Sample label [TARA_station#_environmental-feature_size-fraction]
TARA_100_SRF_0.22-3 TARA_B100000963 TARA_100_SRF_0.22-3 4/15/11 13:10 -12.99 -95.99 5.5 25.3 35.8 200.2 4.6 ... 14283.0 0.749 464267.0 155789.0 620056.0 7780.0 14.0 tropical tropical False
TARA_102_SRF_0.22-3 TARA_B100000900 TARA_102_SRF_0.22-3 4/21/11 20:16 -5.25 -85.16 5.5 24.9 34.7 206.0 11.7 ... 13566.0 0.750 1032721.0 192335.0 1225056.0 19091.0 12.0 tropical tropical False
TARA_109_SRF_0.22-3 TARA_B100000925 TARA_109_SRF_0.22-3 5/12/11 13:38 1.99 -84.58 5.4 27.6 33.4 198.6 1.2 ... 15162.0 0.745 1053096.0 0.0 1053096.0 0.0 11.0 tropical tropical False
TARA_110_SRF_0.22-3 TARA_B100001109 TARA_110_SRF_0.22-3 5/21/11 12:37 -2.01 -84.59 5.5 23.9 35.0 190.8 6.7 ... 15814.0 0.743 646867.0 189912.0 836779.0 12656.0 13.0 tropical tropical False
TARA_111_SRF_0.22-3 TARA_B100000575 TARA_111_SRF_0.22-3 5/31/11 14:12 -16.96 -100.63 5.9 22.8 36.0 208.9 2.6 ... 14494.0 0.744 498513.0 112358.0 610871.0 5839.0 13.0 tropical tropical False
TARA_112_SRF_0.22-3 TARA_B100000941 TARA_112_SRF_0.22-3 6/14/11 16:54 -23.28 -129.40 5.4 24.2 36.5 202.2 -0.9 ... 16502.0 0.733 493328.0 118066.0 611394.0 321.0 15.0 tropical tropical False
TARA_122_SRF_0.22-3 TARA_B100001115 TARA_122_SRF_0.22-3 7/26/11 17:34 -8.99 -139.21 5.9 26.5 35.4 186.2 4.0 ... 16069.0 0.736 NaN 150974.0 150974.0 5770.0 13.0 tropical tropical False
TARA_123_SRF_0.22-3 TARA_B100000683 TARA_123_SRF_0.22-3 7/31/11 17:24 -8.91 -140.28 5.5 26.6 35.4 189.8 3.9 ... 19169.0 0.731 721664.0 31112.0 752776.0 10279.0 10.0 tropical tropical False
TARA_124_SRF_0.22-3 TARA_B100000674 TARA_124_SRF_0.22-3 8/5/11 0:27 -9.11 -140.58 9.9 26.5 35.4 190.7 5.1 ... 17533.0 0.738 705265.0 250340.0 955605.0 10669.0 13.0 tropical tropical False
TARA_125_SRF_0.22-3 TARA_B100001121 TARA_125_SRF_0.22-3 8/8/11 17:38 -8.91 -142.56 5.5 26.8 35.4 187.3 5.0 ... 17303.0 0.734 800561.0 146848.0 947408.0 5808.0 14.0 tropical tropical False
TARA_128_SRF_0.22-3 TARA_B100000609 TARA_128_SRF_0.22-3 9/4/11 18:04 0.00 -153.68 5.4 26.1 35.1 179.9 2.5 ... 18140.0 0.732 435093.0 179847.0 614940.0 7872.0 12.0 tropical tropical False
TARA_132_SRF_0.22-3 TARA_B100001248 TARA_132_SRF_0.22-3 10/4/11 17:49 31.52 -159.00 5.5 25.2 35.2 197.7 -1.0 ... 14422.0 0.741 416576.0 121337.0 537913.0 932.0 13.0 subtropical tropical False
TARA_133_SRF_0.22-3 TARA_B100001093 TARA_133_SRF_0.22-3 10/18/11 18:58 35.41 -127.74 5.5 19.2 33.1 224.4 -0.7 ... 15279.0 0.742 1000349.0 169828.0 1170177.0 6068.0 13.0 subtropical temperate False
TARA_137_SRF_0.22-3 TARA_B100001287 TARA_137_SRF_0.22-3 12/2/11 14:10 14.20 -116.63 5.4 26.4 33.9 195.1 3.2 ... 13939.0 0.747 755425.0 273894.0 1029319.0 10134.0 12.0 tropical tropical False
TARA_138_SRF_0.22-3 TARA_B100001989 TARA_138_SRF_0.22-3 12/10/11 13:58 6.33 -102.94 5.4 26.6 33.4 196.9 -1.2 ... 17717.0 0.728 394198.0 222835.0 617033.0 1567.0 15.0 tropical tropical False
TARA_140_SRF_0.22-3 TARA_B100002019 TARA_140_SRF_0.22-3 12/21/11 16:25 7.41 -79.30 5.4 26.6 28.9 205.3 -3.8 ... 17614.0 0.735 867923.0 264990.0 1132914.0 5808.0 13.0 tropical tropical False
TARA_141_SRF_0.22-3 TARA_B100001939 TARA_141_SRF_0.22-3 12/30/11 12:56 9.85 -80.04 5.4 27.1 34.3 195.5 -1.7 ... 16828.0 0.743 439099.0 139450.0 578549.0 2277.0 10.0 tropical tropical False
TARA_142_SRF_0.22-3 TARA_B100002051 TARA_142_SRF_0.22-3 1/9/12 12:41 25.51 -88.38 5.4 25.0 36.2 194.3 -2.2 ... 17734.0 0.735 436017.0 89629.0 525647.0 1597.0 11.0 subtropical tropical False
TARA_145_SRF_0.22-3 TARA_B100001142 TARA_145_SRF_0.22-3 2/2/12 12:02 39.23 -70.03 5.5 14.1 35.2 233.9 3.5 ... 14527.0 0.747 374730.0 22789.0 397520.0 7749.0 10.0 subtropical temperate False
TARA_146_SRF_0.22-3 TARA_B100001540 TARA_146_SRF_0.22-3 2/15/12 12:59 34.68 -71.30 11.7 19.1 36.5 214.4 0.9 ... 15917.0 0.739 338145.0 27459.0 365604.0 4165.0 11.0 subtropical temperate False
TARA_148_SRF_0.22-3 TARA_B100001741 TARA_148_SRF_0.22-3 2/24/12 11:41 31.70 -64.25 6.1 20.4 36.6 212.6 NaN ... 15943.0 0.741 318391.0 45701.0 364093.0 1911.0 10.0 subtropical tropical False
TARA_149_SRF_0.22-3 TARA_B100001758 TARA_149_SRF_0.22-3 3/1/12 11:55 34.10 -49.89 5.5 18.7 36.4 220.2 -1.2 ... 15146.0 0.742 379018.0 54719.0 433737.0 7375.0 10.0 subtropical temperate False
TARA_150_SRF_0.22-3 TARA_B100001769 TARA_150_SRF_0.22-3 3/5/12 11:02 35.91 -37.26 5.5 17.6 36.3 228.4 -0.3 ... 14688.0 0.743 514205.0 146022.0 660227.0 7940.0 11.0 subtropical temperate False
TARA_151_SRF_0.22-3 TARA_B100001564 TARA_151_SRF_0.22-3 3/9/12 10:13 36.16 -29.01 5.4 17.3 36.2 232.1 0.3 ... 14772.0 0.742 377257.0 66886.0 444143.0 3569.0 9.0 subtropical temperate False
TARA_152_SRF_0.22-3 TARA_B100001173 TARA_152_SRF_0.22-3 3/19/12 10:42 43.69 -16.85 5.4 14.3 36.0 243.1 3.0 ... 14843.0 0.748 555269.0 104028.0 659297.0 7551.0 11.0 temperate temperate False
TARA_018_SRF_0.22-1.6 TARA_A100000164 TARA_018_SRF_0.22-1.6 11/2/09 8:18 35.76 14.26 5.4 21.4 37.9 207.8 NaN ... 14161.0 0.747 633618.0 39180.0 672798.0 947.0 14.0 subtropical tropical False
TARA_023_SRF_0.22-1.6 TARA_E500000075 TARA_023_SRF_0.22-1.6 11/18/09 8:23 42.21 17.71 5.5 17.6 38.2 220.0 NaN ... 14477.0 0.745 746759.0 57854.0 804613.0 1499.0 18.0 temperate temperate False
TARA_025_SRF_0.22-1.6 TARA_E500000178 TARA_025_SRF_0.22-1.6 11/23/09 9:14 39.39 19.39 5.5 18.3 38.2 218.0 NaN ... 14408.0 0.749 264404.0 34000.0 298404.0 1123.0 21.0 subtropical temperate False
TARA_030_SRF_0.22-1.6 TARA_A100001015 TARA_030_SRF_0.22-1.6 12/15/09 10:40 33.92 32.89 5.4 20.5 39.4 207.6 -0.7 ... 12612.0 0.754 232380.0 36418.0 268797.0 1225.0 15.0 subtropical tropical False
TARA_031_SRF_0.22-1.6 TARA_A100001388 TARA_031_SRF_0.22-1.6 1/9/10 7:25 27.16 34.83 5.4 25.1 40.0 188.8 -0.1 ... 14134.0 0.740 473351.0 204723.0 678074.0 1192.0 13.0 subtropical tropical True
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
TARA_036_SRF_0.22-1.6 TARA_Y100000022 TARA_036_SRF_0.22-1.6 3/12/10 6:19 20.82 63.50 5.5 25.6 36.5 210.9 NaN ... 12504.0 0.754 2216959.0 231702.0 2448661.0 4807.0 12.0 tropical tropical False
TARA_038_SRF_0.22-1.6 TARA_Y100000287 TARA_038_SRF_0.22-1.6 3/15/10 3:44 19.04 64.49 5.5 26.2 36.6 199.9 0.9 ... 13741.0 0.749 1626279.0 285872.0 1912151.0 8040.0 11.0 tropical tropical False
TARA_004_SRF_0.22-1.6 TARA_Y200000002 TARA_004_SRF_0.22-1.6 9/15/09 10:15 36.55 -6.57 10.0 20.5 36.6 NaN NaN ... 14591.0 0.745 839531.0 54593.0 894124.0 1222.0 15.0 subtropical tropical False
TARA_041_SRF_0.22-1.6 TARA_B100000282 TARA_041_SRF_0.22-1.6 3/30/10 2:56 14.60 69.98 5.5 29.1 36.0 187.4 -1.3 ... 16594.0 0.731 491899.0 249308.0 741207.0 818.0 14.0 tropical tropical False
TARA_042_SRF_0.22-1.6 TARA_B100000123 TARA_042_SRF_0.22-1.6 4/4/10 3:13 6.03 73.89 5.4 30.0 34.6 189.3 -1.5 ... 15541.0 0.735 808564.0 188746.0 997310.0 909.0 14.0 tropical tropical False
TARA_045_SRF_0.22-1.6 TARA_B100000161 TARA_045_SRF_0.22-1.6 4/13/10 3:21 0.00 71.64 5.5 30.5 35.1 185.2 2.6 ... 14553.0 0.736 393599.0 305984.0 699583.0 818.0 13.0 tropical tropical False
TARA_048_SRF_0.22-1.6 TARA_B100000242 TARA_048_SRF_0.22-1.6 4/19/10 7:54 -9.39 66.42 5.4 29.8 34.2 187.3 -2.2 ... 13177.0 0.744 313030.0 148147.0 461176.0 566.0 13.0 tropical tropical False
TARA_052_SRF_0.22-1.6 TARA_B100000212 TARA_052_SRF_0.22-1.6 5/17/10 3:56 -16.96 53.99 5.5 27.9 34.6 191.7 NaN ... 14573.0 0.739 425006.0 206037.0 631044.0 3913.0 15.0 tropical tropical False
TARA_056_SRF_0.22-3 TARA_B000000609 TARA_056_SRF_0.22-3 6/26/10 7:12 -15.34 43.29 5.5 27.3 35.0 193.1 NaN ... 13543.0 0.744 409420.0 207207.0 616626.0 634.0 13.0 tropical tropical False
TARA_057_SRF_0.22-3 TARA_B000000565 TARA_057_SRF_0.22-3 6/27/10 12:07 -17.02 42.74 5.6 27.0 35.1 190.1 NaN ... 14117.0 0.749 NaN NaN NaN NaN 10.0 tropical tropical False
TARA_062_SRF_0.22-3 TARA_B000000532 TARA_062_SRF_0.22-3 7/2/10 10:17 -21.38 39.56 5.4 25.1 35.3 199.9 -0.2 ... 13750.0 0.746 371432.0 149622.0 521054.0 1949.0 12.0 tropical tropical False
TARA_064_SRF_0.22-3 TARA_B100000401 TARA_064_SRF_0.22-3 7/7/10 4:56 -29.50 37.99 5.5 22.2 35.3 210.0 NaN ... 13216.0 0.748 570751.0 403151.0 973902.0 7078.0 11.0 subtropical tropical False
TARA_065_SRF_0.22-3 TARA_B000000437 TARA_065_SRF_0.22-3 7/12/10 6:46 -35.19 26.29 5.9 21.8 35.4 207.0 NaN ... 13735.0 0.748 538371.0 66905.0 605276.0 6590.0 12.0 subtropical tropical False
TARA_066_SRF_0.22-3 TARA_B000000475 TARA_066_SRF_0.22-3 7/15/10 12:26 -34.94 17.94 5.4 15.0 35.3 238.9 2.5 ... 13082.0 0.752 564191.0 32703.0 596894.0 15397.0 11.0 subtropical temperate False
TARA_067_SRF_0.22-3 TARA_B100000497 TARA_067_SRF_0.22-3 9/7/10 6:35 -32.23 17.71 5.5 12.8 34.8 249.4 0.4 ... 14423.0 0.755 1840174.0 113647.0 1953821.0 46597.0 13.0 subtropical temperate False
TARA_068_SRF_0.22-3 TARA_B100000475 TARA_068_SRF_0.22-3 9/14/10 9:14 -31.03 4.69 5.4 16.8 35.7 231.9 NaN ... 16906.0 0.738 439221.0 192777.0 631998.0 18473.0 10.0 subtropical temperate False
TARA_007_SRF_0.22-1.6 TARA_A200000113 TARA_007_SRF_0.22-1.6 9/23/09 15:06 37.02 1.95 7.5 23.8 37.5 NaN NaN ... 15495.0 0.746 1004684.0 50586.0 1055270.0 813.0 14.0 subtropical tropical False
TARA_070_SRF_0.22-3 TARA_B100000459 TARA_070_SRF_0.22-3 9/21/10 7:05 -20.44 -3.19 5.4 19.8 36.4 215.7 0.2 ... 16493.0 0.737 572821.0 117261.0 690082.0 9740.0 9.0 tropical temperate False
TARA_072_SRF_0.22-3 TARA_B100000424 TARA_072_SRF_0.22-3 10/5/10 8:10 -8.78 -17.91 5.8 25.0 36.4 199.1 0.3 ... 17255.0 0.730 NaN NaN NaN NaN 16.0 tropical tropical False
TARA_076_SRF_0.22-3 TARA_B100000513 TARA_076_SRF_0.22-3 10/16/10 10:07 -20.94 -35.20 5.5 23.3 37.1 206.2 0.0 ... 17695.0 0.733 418710.0 191229.0 609939.0 2215.0 16.0 tropical tropical False
TARA_078_SRF_0.22-3 TARA_B100000524 TARA_078_SRF_0.22-3 11/4/10 10:24 -30.14 -43.29 5.6 19.9 36.3 221.5 -0.4 ... 15863.0 0.736 447396.0 213507.0 660903.0 5498.0 14.0 subtropical temperate False
TARA_082_SRF_0.22-3 TARA_B100000768 TARA_082_SRF_0.22-3 12/6/10 10:25 -47.18 -58.30 5.5 7.3 34.0 305.0 17.1 ... 12924.0 0.761 10639.0 0.0 10639.0 0.0 10.0 temperate polar False
TARA_084_SRF_0.22-3 TARA_B100000780 TARA_084_SRF_0.22-3 1/3/11 11:10 -60.23 -60.65 5.9 1.8 33.7 338.3 24.4 ... 12175.0 0.766 265149.0 0.0 265149.0 1506.0 9.0 temperate polar False
TARA_085_SRF_0.22-3 TARA_B100000787 TARA_085_SRF_0.22-3 1/6/11 10:26 -62.03 -49.54 5.9 0.7 34.4 343.4 27.5 ... 10111.0 0.776 411065.0 0.0 411065.0 0.0 8.0 temperate polar False
TARA_009_SRF_0.22-1.6 TARA_X000000950 TARA_009_SRF_0.22-1.6 9/28/09 13:36 39.07 5.86 5.8 23.9 38.0 NaN NaN ... 15315.0 0.750 901463.0 39330.0 940793.0 1231.0 17.0 subtropical tropical False
TARA_093_SRF_0.22-3 TARA_B100001063 TARA_093_SRF_0.22-3 3/12/11 11:49 -34.05 -73.08 5.3 18.0 34.3 244.9 -1.5 ... 17398.0 0.751 1495550.0 223179.0 1718729.0 8666.0 9.0 subtropical temperate False
TARA_094_SRF_0.22-3 TARA_B100001057 TARA_094_SRF_0.22-3 3/18/11 14:16 -32.78 -87.09 5.4 21.1 34.7 219.2 -0.4 ... 16192.0 0.741 NaN NaN NaN NaN 17.0 subtropical tropical False
TARA_096_SRF_0.22-3 TARA_B100000989 TARA_096_SRF_0.22-3 3/24/11 13:07 -29.72 -101.16 5.5 23.8 35.8 204.1 -0.4 ... 14496.0 0.741 384614.0 0.0 384614.0 948.0 16.0 subtropical tropical False
TARA_098_SRF_0.22-3 TARA_B100001027 TARA_098_SRF_0.22-3 4/3/11 18:10 -25.83 -111.78 5.6 25.1 36.4 200.5 -1.6 ... 14079.0 0.742 387346.0 0.0 387346.0 436.0 15.0 subtropical tropical False
TARA_099_SRF_0.22-3 TARA_B100000886 TARA_099_SRF_0.22-3 4/9/11 14:09 -21.15 -104.79 5.4 23.8 36.1 204.0 -1.7 ... 13751.0 0.746 NaN NaN NaN NaN 15.0 tropical tropical False

63 rows × 41 columns

OG metadata


In [5]:
# proch
# get RS-only OG list ...
df_rsonly = pd.read_csv('/Users/luke/singlecell/notebooks/table_pro_RSonly.tsv', sep='\t')
df_rsonly['Red_Sea_only'] = True
# ... and add to table of all OGs
df_all = pd.read_csv('/Users/luke/singlecell/notebooks/table_pro_all.tsv', sep='\t')
df_og_metadata = df_all.merge(df_rsonly.loc[:,['Ortholog group','Red_Sea_only']], how='left', left_on='Ortholog group', right_on='Ortholog group')
df_og_metadata.drop_duplicates(inplace=True)
df_og_metadata.index = df_og_metadata['Ortholog group']
df_og_metadata.drop(['Ortholog group'], axis=1, inplace=True)
df_og_metadata['Red_Sea_only'].fillna(False, inplace=True)
df_og_metadata['genus'] = 'Prochlorococcus'
df_og_metadata_proch = df_og_metadata

In [6]:
# pelag
# get RS-only OG list ...
df_rsonly = pd.read_csv('/Users/luke/singlecell/notebooks/table_sar_RSonly.tsv', sep='\t')
df_rsonly['Red_Sea_only'] = True
# ... and add to table of all OGs
df_all = pd.read_csv('/Users/luke/singlecell/notebooks/table_sar_all.tsv', sep='\t')
df_og_metadata = df_all.merge(df_rsonly.loc[:,['Ortholog group','Red_Sea_only']], how='left', left_on='Ortholog group', right_on='Ortholog group')
df_og_metadata.drop_duplicates(inplace=True)
df_og_metadata.index = df_og_metadata['Ortholog group']
df_og_metadata.drop(['Ortholog group'], axis=1, inplace=True)
df_og_metadata['Red_Sea_only'].fillna(False, inplace=True)
df_og_metadata['genus'] = 'Pelagibacter'
df_og_metadata_pelag = df_og_metadata

In [7]:
# combine and write to og_metadata.tsv
df_og_metadata = pd.concat([df_og_metadata_pelag, df_og_metadata_proch])
df_og_metadata.to_csv('/Users/luke/singlecell/notebooks/og_metadata.tsv', sep='\t')

In [8]:
df_og_metadata


Out[8]:
Number of genomes Example accession Description Red_Sea_only genus
Ortholog group
pelag10000 75 AAA024N17_00354 GDP-perosamine synthase False Pelagibacter
pelag10001 71 AAA288G21_00327 Cold shock-like protein CspLA False Pelagibacter
pelag10002 55 HIMB083_00082 Sarcosine oxidase subunit alpha False Pelagibacter
pelag10003 55 HIMB083_00539 3-succinoylsemialdehyde-pyridine dehydrogenase False Pelagibacter
pelag10004 52 HIMB083_00335 Ammonia channel False Pelagibacter
pelag10005 48 AAA280B11_00334 Sulfate/thiosulfate import ATP-binding protein... False Pelagibacter
pelag10006 46 AAA024N17_00229 Acetylornithine aminotransferase False Pelagibacter
pelag10007 46 AAA280B11_00519 Putative peroxiredoxin False Pelagibacter
pelag10008 46 AAA280B11_00536 Peptide methionine sulfoxide reductase MsrB False Pelagibacter
pelag10009 45 AAA024N17_00179 Release factor glutamine methyltransferase False Pelagibacter
pelag10010 45 AAA024N17_00228 Inner membrane transport permease YadH False Pelagibacter
pelag10011 44 Pelagibacter_AAA795-C10_00011 Daunorubicin/doxorubicin resistance ATP-bindin... False Pelagibacter
pelag10012 44 AAA024N17_00178 hypothetical protein False Pelagibacter
pelag10013 44 AAA024N17_00206 Penicillin-binding protein 2 False Pelagibacter
pelag10014 44 AAA024N17_00207 Rod shape-determining protein RodA False Pelagibacter
pelag10015 44 AAA280P20_00391 Thymidylate synthase ThyX False Pelagibacter
pelag10016 43 AAA288N07_00669 Signal recognition particle receptor FtsY False Pelagibacter
pelag10017 43 AAA024N17_00095 UDP-N-acetylglucosamine 1-carboxyvinyltransferase False Pelagibacter
pelag10018 43 AAA024N17_00121 Pyruvate, phosphate dikinase False Pelagibacter
pelag10019 43 AAA024N17_00256 Cytochrome b/c1 False Pelagibacter
pelag10020 43 AAA024N17_00269 2-oxoglutarate dehydrogenase E1 component False Pelagibacter
pelag10021 43 QL1_00137 Dihydrolipoyllysine-residue succinyltransferas... False Pelagibacter
pelag10022 43 AAA280B11_00771 Protein translocase subunit SecY False Pelagibacter
pelag10023 43 AAA280P20_00520 Protein translocase subunit SecA False Pelagibacter
pelag10024 42 HIMB114_00223 Aconitate hydratase 1 False Pelagibacter
pelag10025 42 AAA024N17_00079 Lipoprotein signal peptidase False Pelagibacter
pelag10026 42 AAA024N17_00086 ATP phosphoribosyltransferase False Pelagibacter
pelag10027 42 AAA024N17_00254 Ribosome-binding ATPase YchF False Pelagibacter
pelag10028 42 AAA024N17_00255 Cytochrome b/c1 False Pelagibacter
pelag10029 42 AAA024N17_00257 Ubiquinol-cytochrome c reductase iron-sulfur s... False Pelagibacter
... ... ... ... ... ...
proch20409 1 Prochlorococcus_AAA795-J16_01544 UDP-4-amino-4-deoxy-L-arabinose--oxoglutarate ... True Prochlorococcus
proch20410 1 Prochlorococcus_AAA795-J16_01545 hypothetical protein True Prochlorococcus
proch20411 1 Prochlorococcus_AAA795-J16_01547 hypothetical protein True Prochlorococcus
proch20412 1 Prochlorococcus_AAA795-J16_01550 hypothetical protein True Prochlorococcus
proch20413 1 Prochlorococcus_AAA795-J16_01648 hypothetical protein True Prochlorococcus
proch20414 1 Prochlorococcus_AAA795-M23_00140 hypothetical protein True Prochlorococcus
proch20415 1 Prochlorococcus_AAA795-M23_00149 hypothetical protein True Prochlorococcus
proch20416 1 Prochlorococcus_AAA795-M23_00293 hypothetical protein True Prochlorococcus
proch20417 1 Prochlorococcus_AAA795-M23_00318 hypothetical protein True Prochlorococcus
proch20418 1 Prochlorococcus_AAA795-M23_00405 hypothetical protein True Prochlorococcus
proch20419 1 Prochlorococcus_AAA795-M23_00526 hypothetical protein True Prochlorococcus
proch20420 1 Prochlorococcus_AAA795-M23_00566 hypothetical protein True Prochlorococcus
proch20421 1 Prochlorococcus_AAA795-M23_01055 Glucosylglycerol-phosphate synthase True Prochlorococcus
proch20422 1 Prochlorococcus_AAA795-M23_01060 hypothetical protein True Prochlorococcus
proch20423 1 Prochlorococcus_AAA795-M23_01063 hypothetical protein True Prochlorococcus
proch20424 1 Prochlorococcus_AAA795-M23_01182 hypothetical protein True Prochlorococcus
proch20425 1 Prochlorococcus_AAA795-M23_01207 UvrABC system protein B True Prochlorococcus
proch20426 1 Prochlorococcus_AAA795-M23_01473 hypothetical protein True Prochlorococcus
proch20427 1 Prochlorococcus_AAA795-M23_01474 hypothetical protein True Prochlorococcus
proch20428 1 Prochlorococcus_AAA795-M23_01483 hypothetical protein True Prochlorococcus
proch20429 1 Prochlorococcus_AAA795-M23_01489 hypothetical protein True Prochlorococcus
proch20430 1 Prochlorococcus_AAA795-M23_01493 hypothetical protein True Prochlorococcus
proch20431 1 Prochlorococcus_AAA795-M23_01494 hypothetical protein True Prochlorococcus
proch20432 1 Prochlorococcus_AAA795-M23_01495 hypothetical protein True Prochlorococcus
proch20433 1 Prochlorococcus_AAA795-M23_01500 hypothetical protein True Prochlorococcus
proch20434 1 Prochlorococcus_AAA795-M23_01510 hypothetical protein True Prochlorococcus
proch20435 1 Prochlorococcus_AAA795-M23_01511 hypothetical protein True Prochlorococcus
proch20436 1 Prochlorococcus_AAA795-M23_01521 hypothetical protein True Prochlorococcus
proch20437 1 Prochlorococcus_AAA795-M23_01523 hypothetical protein True Prochlorococcus
proch20438 1 Prochlorococcus_AAA795-M23_01524 hypothetical protein True Prochlorococcus

15711 rows × 5 columns

Genome metadata


In [99]:
# read genome_metadata.tsv
df_genome_metadata = pd.read_csv('/Users/luke/singlecell/notebooks/genome_metadata.tsv', sep='\t', index_col=0)

In [100]:
df_genome_metadata


Out[100]:
genus orthomcl-v3 orthomcl-v4 jellyfish clade red_sea latitude longitude depth_meters reference
strain
AAA024N17 Pelagibacter NaN S001 NaN IIIb False NaN NaN NaN NaN
AAA280B11 Pelagibacter NaN S002 NaN IIIb False NaN NaN NaN NaN
AAA280P20 Pelagibacter NaN S003 NaN IIIb False NaN NaN NaN NaN
AAA288G21 Pelagibacter NaN S004 NaN Ic False NaN NaN NaN NaN
AAA288N07 Pelagibacter NaN S005 NaN Ic False NaN NaN NaN NaN
AAA288E13 Pelagibacter NaN NaN NaN Ic False NaN NaN NaN NaN
AAA240E13 Pelagibacter NaN NaN NaN Ic False NaN NaN NaN NaN
HIMB058 Pelagibacter NaN S006 NaN II False NaN NaN NaN NaN
HIMB083 Pelagibacter NaN S007 Pelub83DRAFT Ia False NaN NaN NaN NaN
HIMB114 Pelagibacter SARE S008 HIMB114 IIIa False 21.46 -157.79 NaN NaN
HIMB122 Pelagibacter NaN S009 NaN Ia False NaN NaN NaN NaN
HIMB1321 Pelagibacter NaN S010 NaN Ia False NaN NaN NaN NaN
HIMB140 Pelagibacter NaN S011 HIMB140 Ia False NaN NaN NaN NaN
HIMB4 Pelagibacter NaN S012 HIMB4 Ia False NaN NaN NaN NaN
HIMB5 Pelagibacter SARF S013 CP003809 Ia False 21.46 -157.79 NaN NaN
HIMB59 Pelagibacter SARG NaN HIMB59b V False 21.46 -157.79 NaN NaN
HTCC1002 Pelagibacter SARA S014 Ga0076703 Ia False 44.65 -124.05 10.0 NaN
HTCC1013 Pelagibacter NaN S015 HTCC1013 Ia False NaN NaN NaN NaN
HTCC1016 Pelagibacter NaN S016 NaN Ia False NaN NaN NaN NaN
HTCC1040 Pelagibacter NaN S017 NaN Ia False NaN NaN NaN NaN
HTCC1062 Pelagibacter SARB S018 Ga0076388 Ia False NaN NaN NaN Giovannoni et al., 2005
HTCC7211 Pelagibacter SARC S019 HTCC7211 Ia False NaN NaN NaN NaN
HTCC7214 Pelagibacter NaN S020 NaN Ia False 32.10 -64.30 NaN NaN
HTCC7217 Pelagibacter NaN S021 NaN Ia False NaN NaN NaN NaN
HTCC8051 Pelagibacter NaN S022 HTC8051 Ia False NaN NaN NaN NaN
HTCC9022 Pelagibacter NaN S023 HTCC9022 Ia False NaN NaN NaN NaN
HTCC9565 Pelagibacter SARH S024 HTCC9565 Ia False NaN NaN NaN NaN
IMCC9063 Pelagibacter SARD S025 NC_015380 IIIa False 79.00 11.31 0.0 Oh et al. (2011)
Pelagibacter_SCGC_AAA795-A08 Pelagibacter SA08 SA08 Pelagibacter_SCGC_AAA795-A08_contigs Ia True 19.75 40.05 0.0 This study
Pelagibacter_SCGC_AAA795-A20 Pelagibacter SA20 SA20 Pelagibacter_SCGC_AAA795-A20_contigs Ia True 19.75 40.05 0.0 This study
... ... ... ... ... ... ... ... ... ... ...
MIT9201 Prochlorococcus NaN P117 Ga0062500 HLII False -12.00 -145.42 0.0 Moore et al. 1999
MIT9202 Prochlorococcus PROC P118 Ga0076803 HLII False -12.00 -145.42 79.0 Moore et al. 1999
MIT9211 Prochlorococcus PROD P119 Ga0076499 LLII/III False 0.00 -139.97 83.0 Kettler et al. 2007
MIT9215 Prochlorococcus PROE P120 Ga0065692 HLII False 0.00 -139.97 0.0 Kettler et al. 2007
MIT9301 Prochlorococcus PROF P121 Ga0076500 HLII False NaN NaN 90.0 Kettler et al. 2007
MIT9302 Prochlorococcus NaN P122 Ga0062504 HLII False 34.76 -66.19 100.0 Moore et al. 1998
MIT9303 Prochlorococcus PROG P123 Ga0076501 LLIV False 34.76 -66.19 100.0 Kettler et al. 2007
MIT9311 Prochlorococcus NaN P124 Ga0062462 HLII False 37.51 -64.24 135.0 Rocap et al., 2002
MIT9312 Prochlorococcus PROH P125 NC_007577 HLII False 37.50 -68.23 135.0 Kettler et al. 2007
MIT9313 Prochlorococcus PROI P126 NC_005071 LLIV False 37.50 -68.23 135.0 Rocap et al. 2003, Kettler et al. 2007
MIT9314 Prochlorococcus NaN P127 Ga0062474 HLII False 37.51 -64.24 180.0 Rocap et al., 2002
MIT9321 Prochlorococcus NaN P128 Ga0062467 HLII False 1.00 -92.00 50.0 Rocap et al., 2002
MIT9322 Prochlorococcus NaN P129 Ga0062463 HLII False 0.27 -93.00 0.0 Rocap et al., 2002
MIT9401 Prochlorococcus NaN P130 Ga0062470 HLII False 35.50 -70.40 0.0 Rocap et al., 2002
MIT9515 Prochlorococcus PROJ P131 Ga0067215 HLI False NaN NaN 15.0 Kettler et al. 2007
NATL1A Prochlorococcus PROK P132 Ga0067212 LLI False 38.54 -39.85 30.0 Kettler et al. 2007
NATL2A Prochlorococcus PROL P133 NC_007335 LLI False 38.98 -40.55 10.0 Kettler et al. 2007
PAC1 Prochlorococcus NaN P134 Ga0062468 LLI False 22.75 -158.00 100.0 Parpais et al. 1996, Penno et al. 2000
Prochlorococcus_SCGC_AAA795-F05 Prochlorococcus PF05 PF05 Prochlorococcus_SCGC_AAA795-F05_contigs HLII True 19.75 40.05 0.0 This study
Prochlorococcus_SCGC_AAA795-I06 Prochlorococcus PI06 PI06 Prochlorococcus_SCGC_AAA795-I06_contigs HLII True 19.75 40.05 0.0 This study
Prochlorococcus_SCGC_AAA795-I15 Prochlorococcus PI15 PI15 Prochlorococcus_SCGC_AAA795-I15_contigs HLII True 19.75 40.05 0.0 This study
Prochlorococcus_SCGC_AAA795-J16 Prochlorococcus PJ16 PJ16 Prochlorococcus_SCGC_AAA795-J16_contigs HLII True 19.75 40.05 0.0 This study
Prochlorococcus_SCGC_AAA795-M23 Prochlorococcus PM23 PM23 Prochlorococcus_SCGC_AAA795-M23_contigs HLII True 19.75 40.05 0.0 This study
PRS50 Prochlorococcus PR50 NaN NaN HLII True 19.75 40.05 0.0 Shibl et al. (unpublished)
SB Prochlorococcus NaN P135 Ga0062469 HLII False 35.00 138.30 40.0 Shimada et al. 1995
SS120 Prochlorococcus PROM P136 Ga0076506 LLII/III False 28.99 -64.35 120.0 Dufresne et al. 2003, Kettler et al. 2007
SS2 Prochlorococcus NaN P137 Ga0062475 LLII/III False 28.98 -64.35 120.0 Rocap et al., 2002
SS35 Prochlorococcus NaN P138 Ga0062478 LLII/III False 28.98 -64.35 120.0 Rocap et al., 2002
SS51 Prochlorococcus NaN P139 Ga0062477 LLII/III False 28.98 -64.35 120.0 Rocap et al., 2002
SS52 Prochlorococcus NaN P140 Ga0062476 LLII/III False 28.98 -64.35 120.0 Rocap et al., 2002

200 rows × 10 columns


In [ ]: