In [6]:
Copied!
from pprint import pprint
from protein_detective.uniprot import Query, search4af, search4emdb, search4pdb, search4uniprot
from pprint import pprint
from protein_detective.uniprot import Query, search4af, search4emdb, search4pdb, search4uniprot
Search on uniprot¶
In [2]:
Copied!
import logging
logging.basicConfig(level=logging.WARNING)
# Set to WARNING to see only warnings
# Set to INFO to see sparql queries
# Set to DEBUG to see raw results
import logging
logging.basicConfig(level=logging.WARNING)
# Set to WARNING to see only warnings
# Set to INFO to see sparql queries
# Set to DEBUG to see raw results
In [3]:
Copied!
query = Query(
taxon_id="9606",
reviewed=True,
subcellular_location_uniprot="nucleus",
subcellular_location_go="GO:0005634", # Cellular component - Nucleus
molecular_function_go="GO:0003677", # Molecular function - DNA binding
)
query = Query(
taxon_id="9606",
reviewed=True,
subcellular_location_uniprot="nucleus",
subcellular_location_go="GO:0005634", # Cellular component - Nucleus
molecular_function_go="GO:0003677", # Molecular function - DNA binding
)
In [4]:
Copied!
uniprot_accessions = search4uniprot(query, limit=200)
pprint(uniprot_accessions)
uniprot_accessions = search4uniprot(query, limit=200)
pprint(uniprot_accessions)
WARNING:protein_detective.uniprot:Search for uniprot accessions returned 200 results. There may be more results available, but they are not returned due to the limit of 200. Consider increasing the limit to get more results.
{'A0A087WUV0',
'A0A0C5B5G6',
'A0A0U1RQI7',
'A0A1B0GTS1',
'A0A1B0GVZ6',
'A0A1B0GWH4',
'A0A1W2PPF3',
'A0A1W2PPK0',
'A0A1W2PPM1',
'A0A1W2PQ73',
'A0A1W2PQL4',
'A0A1W2PRP0',
'A0A2R8Y619',
'A0A2Z4LIS9',
'A0A3B3IU63',
'A0A5F9ZHS7',
'A1A519',
'A1YPR0',
'A2RRD8',
'A2RU54',
'A3KN83',
'A6NCS4',
'A6NDR6',
'A6NDX5',
'A6NDZ8',
'A6NE82',
'A6NFD8',
'A6NFI3',
'A6NFQ7',
'A6NGD5',
'A6NHJ4',
'A6NHT5',
'A6NI15',
'A6NJ08',
'A6NJ46',
'A6NJG6',
'A6NJL1',
'A6NJT0',
'A6NK53',
'A6NK75',
'A6NKF2',
'A6NLW8',
'A6NM28',
'A6NMT0',
'A6NN14',
'A6NNA5',
'A6NNF4',
'A6NP11',
'A8K0S8',
'A8K830',
'A8K8V0',
'A8MPP1',
'A8MQ14',
'A8MT65',
'A8MT69',
'A8MTJ6',
'A8MTQ0',
'A8MTY0',
'A8MUV8',
'A8MUZ8',
'A8MWA4',
'A8MXY4',
'A8MYZ6',
'A8MZ59',
'A9YTQ3',
'B1APH4',
'B2RD01',
'B2RPK0',
'B2RXF5',
'B4DU55',
'B4DX44',
'B4DXR9',
'C9JN71',
'C9JSJ3',
'E7ETH6',
'E9PAV3',
'E9PGG2',
'O00110',
'O00255',
'O00257',
'O00268',
'O00287',
'O00321',
'O00327',
'O00358',
'O00409',
'O00470',
'O00479',
'O00482',
'O00570',
'O00571',
'O00712',
'O00716',
'O14497',
'O14503',
'O14529',
'O14593',
'O14627',
'O14628',
'O14646',
'O14647',
'O14686',
'O14709',
'O14737',
'O14744',
'O14746',
'O14753',
'O14770',
'O14771',
'O14802',
'O14813',
'O14867',
'O14896',
'O14901',
'O14948',
'O14978',
'O14979',
'O15015',
'O15054',
'O15055',
'O15062',
'O15090',
'O15119',
'O15160',
'O15162',
'O15164',
'O15178',
'O15198',
'O15209',
'O15226',
'O15266',
'O15294'}
Find Protein Data Bank (PDB) entries for uniprot entries¶
In [5]:
Copied!
pdb_results = search4pdb(uniprot_accessions, limit=200)
pprint(pdb_results)
pdb_results = search4pdb(uniprot_accessions, limit=200)
pprint(pdb_results)
WARNING:protein_detective.uniprot:Search for pdbs on uniprot returned 200 results. There may be more results available, but they are not returned due to the limit of 200. Consider increasing the limit to get more results.
{'A8MT69': {PdbResult(id='4DRA',
method='X-Ray_Crystallography',
chain='E/F/G/H=1-81',
resolution='2.41'),
PdbResult(id='4DRB',
method='X-Ray_Crystallography',
chain='J/K/L/M/N/O=1-81',
resolution='2.63'),
PdbResult(id='4E44',
method='X-Ray_Crystallography',
chain='B/D=1-81',
resolution='2.1'),
PdbResult(id='4E45',
method='X-Ray_Crystallography',
chain='B/D/G/I/L/N=1-81',
resolution='2'),
PdbResult(id='4NDY',
method='X-Ray_Crystallography',
chain='B/D/H/L/M/N/U/V/W/X=8-81',
resolution='7'),
PdbResult(id='4NE1',
method='X-Ray_Crystallography',
chain='B/D/H/L/M/N/U/V/W/X/Z/b/d/h/i/j/o/p/q/r=8-81',
resolution='6.5'),
PdbResult(id='4NE3',
method='X-Ray_Crystallography',
chain='B=8-81',
resolution='1.8'),
PdbResult(id='4NE5',
method='X-Ray_Crystallography',
chain='B/D/F/H=8-81',
resolution='2.5'),
PdbResult(id='4NE6',
method='X-Ray_Crystallography',
chain='B/D=8-81',
resolution='2.1')},
'O00255': {PdbResult(id='4GPQ',
method='X-Ray_Crystallography',
chain='A=74-386,A=399-459,A=1-53,A=537-593',
resolution='1.46'),
PdbResult(id='4GQ3',
method='X-Ray_Crystallography',
chain='A=1-53,A=74-386,A=537-593,A=399-459',
resolution='1.56'),
PdbResult(id='4GQ4',
method='X-Ray_Crystallography',
chain='A=1-53,A=399-459,A=537-593,A=74-386',
resolution='1.27'),
PdbResult(id='4GQ6',
method='X-Ray_Crystallography',
chain='A=1-53,A=74-386,A=537-593,A=399-459',
resolution='1.55'),
PdbResult(id='4I80',
method='X-Ray_Crystallography',
chain='A=2-458,A=520-610',
resolution='3.1'),
PdbResult(id='4OG3',
method='X-Ray_Crystallography',
chain='A=74-386,A=549-593,A=399-459,A=1-53',
resolution='2.01'),
PdbResult(id='4OG4',
method='X-Ray_Crystallography',
chain='A=74-386,A=1-53,A=399-459,A=549-593',
resolution='1.45'),
PdbResult(id='4OG5',
method='X-Ray_Crystallography',
chain='A=399-459,A=1-53,A=74-386,A=549-593',
resolution='1.63'),
PdbResult(id='4OG6',
method='X-Ray_Crystallography',
chain='A=74-386,A=549-593,A=399-459,A=1-53',
resolution='1.49'),
PdbResult(id='4OG7',
method='X-Ray_Crystallography',
chain='A=74-386,A=1-53,A=549-593,A=399-459',
resolution='2.08'),
PdbResult(id='4OG8',
method='X-Ray_Crystallography',
chain='A=1-53,A=74-386,A=549-593,A=399-459',
resolution='1.53'),
PdbResult(id='4X5Y',
method='X-Ray_Crystallography',
chain='A=1-53,A=74-386,A=537-593,A=399-459',
resolution='1.59'),
PdbResult(id='4X5Z',
method='X-Ray_Crystallography',
chain='A=1-53,A=399-459,A=537-593,A=74-386',
resolution='1.86'),
PdbResult(id='5DB0',
method='X-Ray_Crystallography',
chain='A=1-53,A=399-459,A=74-386,A=537-593',
resolution='1.5'),
PdbResult(id='5DB1',
method='X-Ray_Crystallography',
chain='A=537-593,A=74-386,A=399-459,A=1-53',
resolution='1.86'),
PdbResult(id='5DB2',
method='X-Ray_Crystallography',
chain='A=537-593,A=399-459,A=1-53,A=74-386',
resolution='1.54'),
PdbResult(id='5DB3',
method='X-Ray_Crystallography',
chain='A=74-386,A=537-593,A=399-459,A=1-53',
resolution='1.71'),
PdbResult(id='5DD9',
method='X-Ray_Crystallography',
chain='A=1-53,A=399-459,A=537-593,A=74-386',
resolution='1.62'),
PdbResult(id='5DDA',
method='X-Ray_Crystallography',
chain='A=1-53,A=399-459,A=537-593,A=74-386',
resolution='1.83'),
PdbResult(id='5DDB',
method='X-Ray_Crystallography',
chain='A=399-459,A=74-386,A=537-593,A=1-53',
resolution='1.54'),
PdbResult(id='5DDC',
method='X-Ray_Crystallography',
chain='A=74-386,A=1-53,A=537-593,A=399-459',
resolution='1.62'),
PdbResult(id='5DDD',
method='X-Ray_Crystallography',
chain='A=399-459,A=537-593,A=1-53,A=74-386',
resolution='2.14'),
PdbResult(id='5DDE',
method='X-Ray_Crystallography',
chain='A=399-459,A=1-53,A=74-386,A=537-593',
resolution='1.78'),
PdbResult(id='5DDF',
method='X-Ray_Crystallography',
chain='A=399-459,A=74-386,A=537-593,A=1-53',
resolution='1.66'),
PdbResult(id='3U85',
method='X-Ray_Crystallography',
chain='A=2-459,A=520-610',
resolution='3'),
PdbResult(id='3U86',
method='X-Ray_Crystallography',
chain='A=2-459,A=520-610',
resolution='2.84'),
PdbResult(id='3U88',
method='X-Ray_Crystallography',
chain='A/B=520-610,A/B=2-459',
resolution='3'),
PdbResult(id='3U84',
method='X-Ray_Crystallography',
chain='A/B=2-459,A/B=520-610',
resolution='2.5')},
'O00257': {PdbResult(id='5EPL',
method='X-Ray_Crystallography',
chain='A/B=8-65',
resolution='1.81'),
PdbResult(id='3I8Z',
method='X-Ray_Crystallography',
chain='A=8-62',
resolution='1.51'),
PdbResult(id='2K28',
method='NMR_Spectroscopy',
chain='A=8-65',
resolution=None)},
'O00268': {PdbResult(id='2P6V',
method='X-Ray_Crystallography',
chain='A=575-688',
resolution='2'),
PdbResult(id='1H3O',
method='X-Ray_Crystallography',
chain='A/C=872-945',
resolution='2.3')},
'O00287': {PdbResult(id='2KW3',
method='NMR_Spectroscopy',
chain='C=214-272',
resolution=None)},
'O00327': {PdbResult(id='4H10',
method='X-Ray_Crystallography',
chain='A=66-128',
resolution='2.4')},
'O00470': {PdbResult(id='4XRS',
method='X-Ray_Crystallography',
chain='A/B=279-336',
resolution='3.5'),
PdbResult(id='5EGO',
method='X-Ray_Crystallography',
chain='A=279-333',
resolution='2.54')},
'O00482': {PdbResult(id='4DOR',
method='X-Ray_Crystallography',
chain='A/B=290-541',
resolution='1.9'),
PdbResult(id='4DOS',
method='X-Ray_Crystallography',
chain='A=299-538',
resolution='2'),
PdbResult(id='4IS8',
method='X-Ray_Crystallography',
chain='A/B=300-538',
resolution='2.78'),
PdbResult(id='4ONI',
method='X-Ray_Crystallography',
chain='A/B=291-541',
resolution='1.8'),
PdbResult(id='4PLD',
method='X-Ray_Crystallography',
chain='A=301-541',
resolution='1.75'),
PdbResult(id='4PLE',
method='X-Ray_Crystallography',
chain='A/C/E/G=301-541',
resolution='1.75'),
PdbResult(id='4RWV',
method='X-Ray_Crystallography',
chain='A=294-541',
resolution='1.86'),
PdbResult(id='5L0M',
method='X-Ray_Crystallography',
chain='A=79-187',
resolution='2.2'),
PdbResult(id='5L11',
method='X-Ray_Crystallography',
chain='A=299-541',
resolution='1.85'),
PdbResult(id='3TX7',
method='X-Ray_Crystallography',
chain='B=191-541',
resolution='2.76'),
PdbResult(id='3PLZ',
method='X-Ray_Crystallography',
chain='A/B=300-541',
resolution='1.75'),
PdbResult(id='2A66',
method='X-Ray_Crystallography',
chain='A=79-187',
resolution='2.2'),
PdbResult(id='1YOK',
method='X-Ray_Crystallography',
chain='A=300-541',
resolution='2.5'),
PdbResult(id='1YUC',
method='X-Ray_Crystallography',
chain='A/B=290-541',
resolution='1.9'),
PdbResult(id='1ZDU',
method='X-Ray_Crystallography',
chain='A=297-541',
resolution='2.5')},
'O00571': {PdbResult(id='4O2C',
method='X-Ray_Crystallography',
chain='C=2-10',
resolution='1.8'),
PdbResult(id='4O2E',
method='X-Ray_Crystallography',
chain='C/F=2-10',
resolution='1.98'),
PdbResult(id='4O2F',
method='X-Ray_Crystallography',
chain='C/F=3-10',
resolution='1.9'),
PdbResult(id='4PX9',
method='X-Ray_Crystallography',
chain='A/B/C=135-407',
resolution='2.31'),
PdbResult(id='4PXA',
method='X-Ray_Crystallography',
chain='A=135-582',
resolution='3.2'),
PdbResult(id='5E7I',
method='X-Ray_Crystallography',
chain='A/B/C=133-584',
resolution='2.22'),
PdbResult(id='5E7J',
method='X-Ray_Crystallography',
chain='A=133-584',
resolution='2.23'),
PdbResult(id='5E7M',
method='X-Ray_Crystallography',
chain='A=133-584',
resolution='2.3'),
PdbResult(id='3JRV',
method='X-Ray_Crystallography',
chain='C/D/E=71-90',
resolution='1.6'),
PdbResult(id='2JGN',
method='X-Ray_Crystallography',
chain='A/B/C=409-580',
resolution='1.91'),
PdbResult(id='2I4I',
method='X-Ray_Crystallography',
chain='A=168-582',
resolution='2.2')},
'O14497': {PdbResult(id='1RYU',
method='NMR_Spectroscopy',
chain='A=1000-1119',
resolution=None)},
'O14529': {PdbResult(id='1WH6',
method='NMR_Spectroscopy',
chain='A=887-974',
resolution=None),
PdbResult(id='1WH8',
method='NMR_Spectroscopy',
chain='A=1028-1125',
resolution=None),
PdbResult(id='1X2L',
method='NMR_Spectroscopy',
chain='A=544-631',
resolution=None)},
'O14593': {PdbResult(id='3V30',
method='X-Ray_Crystallography',
chain='A=90-260',
resolution='1.57'),
PdbResult(id='3UXG',
method='X-Ray_Crystallography',
chain='A=90-260',
resolution='1.85')},
'O14646': {PdbResult(id='2B2T',
method='X-Ray_Crystallography',
chain='C=268-373,A/B=268-443',
resolution='2.45'),
PdbResult(id='4B4C',
method='X-Ray_Crystallography',
chain='A=1119-1327',
resolution='1.62'),
PdbResult(id='4NW2',
method='X-Ray_Crystallography',
chain='A/C=268-443',
resolution='1.9'),
PdbResult(id='4O42',
method='X-Ray_Crystallography',
chain='A=268-443',
resolution='1.87'),
PdbResult(id='5AFW',
method='X-Ray_Crystallography',
chain='A=270-443',
resolution='1.6'),
PdbResult(id='2B2V',
method='X-Ray_Crystallography',
chain='C=268-373,A/B=268-443',
resolution='2.65'),
PdbResult(id='2N39',
method='NMR_Spectroscopy',
chain='A=1409-1511',
resolution=None),
PdbResult(id='2B2W',
method='X-Ray_Crystallography',
chain='C=268-373,A/B=268-443',
resolution='2.4'),
PdbResult(id='2B2U',
method='X-Ray_Crystallography',
chain='C=268-373,A/B=268-443',
resolution='2.95'),
PdbResult(id='2B2Y',
method='X-Ray_Crystallography',
chain='C=268-373,A/B=268-443',
resolution='2.35')},
'O14686': {PdbResult(id='4ERQ',
method='X-Ray_Crystallography',
chain='D/E/F=5333-5346',
resolution='1.91'),
PdbResult(id='4Z4P',
method='X-Ray_Crystallography',
chain='A=5382-5536',
resolution='2.2'),
PdbResult(id='3UVK',
method='X-Ray_Crystallography',
chain='B=5337-5347',
resolution='1.4')},
'O14737': {PdbResult(id='2CRU',
method='NMR_Spectroscopy',
chain='A=9-113',
resolution=None),
PdbResult(id='2K6B',
method='NMR_Spectroscopy',
chain='A=2-112',
resolution=None),
PdbResult(id='1YYB',
method='NMR_Spectroscopy',
chain='A=1-26',
resolution=None)},
'O14744': {PdbResult(id='4GQB',
method='X-Ray_Crystallography',
chain='A=1-637',
resolution='2.06'),
PdbResult(id='4X60',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.35'),
PdbResult(id='4X61',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.85'),
PdbResult(id='4X63',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='3.05'),
PdbResult(id='5C9Z',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.36'),
PdbResult(id='5EMJ',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.27'),
PdbResult(id='5EMK',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.52'),
PdbResult(id='5EML',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.39'),
PdbResult(id='5EMM',
method='X-Ray_Crystallography',
chain='A=2-637',
resolution='2.37'),
PdbResult(id='5FA5',
method='X-Ray_Crystallography',
chain='A=1-637',
resolution='2.34')},
'O14746': {PdbResult(id='4B18',
method='X-Ray_Crystallography',
chain='B=222-240',
resolution='2.52'),
PdbResult(id='4MNQ',
method='X-Ray_Crystallography',
chain='C=540-548',
resolution='2.74'),
PdbResult(id='5MEN',
method='X-Ray_Crystallography',
chain='C=540-548',
resolution='2.81'),
PdbResult(id='5MEO',
method='X-Ray_Crystallography',
chain='C=540-548',
resolution='1.77'),
PdbResult(id='5MEP',
method='X-Ray_Crystallography',
chain='C/F=540-548',
resolution='2.71'),
PdbResult(id='5MEQ',
method='X-Ray_Crystallography',
chain='C=540-546',
resolution='2.27'),
PdbResult(id='5MER',
method='X-Ray_Crystallography',
chain='C/F=540-546',
resolution='1.88'),
PdbResult(id='2BCK',
method='X-Ray_Crystallography',
chain='C/F=461-469',
resolution='2.8')},
'O14770': {PdbResult(id='4XRM',
method='X-Ray_Crystallography',
chain='A/B=281-342',
resolution='1.6'),
PdbResult(id='5BNG',
method='X-Ray_Crystallography',
chain='A/B=283-342',
resolution='3.5'),
PdbResult(id='5EG0',
method='X-Ray_Crystallography',
chain='A=284-338',
resolution='3.1'),
PdbResult(id='3K2A',
method='X-Ray_Crystallography',
chain='A/B=281-345',
resolution='1.95')},
'O14867': {PdbResult(id='2IHC',
method='X-Ray_Crystallography',
chain='A/B/C/D=7-128',
resolution='2.44')},
'O15054': {PdbResult(id='4ASK',
method='X-Ray_Crystallography',
chain='A/B=1141-1643',
resolution='1.86'),
PdbResult(id='5FP3',
method='X-Ray_Crystallography',
chain='A/B=1141-1643',
resolution='2.05'),
PdbResult(id='5OY3',
method='X-Ray_Crystallography',
chain='A=1141-1643',
resolution='2.14'),
PdbResult(id='2XXZ',
method='X-Ray_Crystallography',
chain='A/B=1176-1505',
resolution='1.8'),
PdbResult(id='2XUE',
method='X-Ray_Crystallography',
chain='A/B=1141-1643',
resolution='2')},
'O15119': {PdbResult(id='1H6F',
method='X-Ray_Crystallography',
chain='A/B=101-311',
resolution='1.7')},
'O15162': {PdbResult(id='1Y2A',
method='X-Ray_Crystallography',
chain='P=257-266',
resolution='2.2')},
'O15164': {PdbResult(id='4YAB',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='1.9'),
PdbResult(id='4YAD',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='1.73'),
PdbResult(id='4YAT',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='2.18'),
PdbResult(id='4YAX',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='2.25'),
PdbResult(id='4YBM',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='1.46'),
PdbResult(id='4YBS',
method='X-Ray_Crystallography',
chain='A=824-1006',
resolution='1.83'),
PdbResult(id='4YBT',
method='X-Ray_Crystallography',
chain='A=824-1006',
resolution='1.82'),
PdbResult(id='4YC9',
method='X-Ray_Crystallography',
chain='A=824-1006',
resolution='1.82'),
PdbResult(id='4ZQL',
method='X-Ray_Crystallography',
chain='A/B=825-1006',
resolution='1.79'),
PdbResult(id='5H1T',
method='X-Ray_Crystallography',
chain='A/B/C/D=824-1006',
resolution='1.95'),
PdbResult(id='5H1U',
method='X-Ray_Crystallography',
chain='A/B/C/D=824-1006',
resolution='1.9'),
PdbResult(id='5H1V',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='2'),
PdbResult(id='3O37',
method='X-Ray_Crystallography',
chain='A/B/C/D=824-1006',
resolution='2'),
PdbResult(id='3O35',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='1.76'),
PdbResult(id='3O33',
method='X-Ray_Crystallography',
chain='A/B/C/D=824-1006',
resolution='2'),
PdbResult(id='3O34',
method='X-Ray_Crystallography',
chain='A=824-1006',
resolution='1.9'),
PdbResult(id='3O36',
method='X-Ray_Crystallography',
chain='A/B=824-1006',
resolution='1.7'),
PdbResult(id='2YYN',
method='X-Ray_Crystallography',
chain='A/B/C/D=891-1012',
resolution='2.5')},
'O15178': {PdbResult(id='5QRF',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='2.03'),
PdbResult(id='5QRG',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.95'),
PdbResult(id='5QRH',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.81'),
PdbResult(id='5QRI',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.83'),
PdbResult(id='5QRJ',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.81'),
PdbResult(id='5QRK',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.63'),
PdbResult(id='5QRL',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.76'),
PdbResult(id='5QRM',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.55'),
PdbResult(id='5QRN',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.62'),
PdbResult(id='5QRO',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.61'),
PdbResult(id='5QRP',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.67'),
PdbResult(id='5QRQ',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='2.1'),
PdbResult(id='5QRR',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.69'),
PdbResult(id='5QRS',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='2.06'),
PdbResult(id='5QRT',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.77'),
PdbResult(id='5QRU',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.76'),
PdbResult(id='5QRV',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.67'),
PdbResult(id='5QRW',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.74'),
PdbResult(id='5QRX',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.87'),
PdbResult(id='5QRY',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.58'),
PdbResult(id='5QRZ',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.96'),
PdbResult(id='5QS0',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.6'),
PdbResult(id='5QS1',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.66'),
PdbResult(id='5QS2',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.68'),
PdbResult(id='5QS3',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.71'),
PdbResult(id='5QS4',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.65'),
PdbResult(id='5QS5',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.81'),
PdbResult(id='5QS6',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.67'),
PdbResult(id='5QS7',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.66'),
PdbResult(id='5QS8',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.47'),
PdbResult(id='5QS9',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.43'),
PdbResult(id='5QSA',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.55'),
PdbResult(id='5QSB',
method='X-Ray_Crystallography',
chain='A=41-211',
resolution='1.82')},
'O15294': {PdbResult(id='4AY5',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.15'),
PdbResult(id='4AY6',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.3'),
PdbResult(id='4CDR',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.15'),
PdbResult(id='4GYW',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='1.7'),
PdbResult(id='4GYY',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='1.85'),
PdbResult(id='4GZ3',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='1.9'),
PdbResult(id='4GZ5',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.08'),
PdbResult(id='4GZ6',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='2.98'),
PdbResult(id='4N39',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='1.76'),
PdbResult(id='4N3A',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='1.88'),
PdbResult(id='4N3B',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='2.17'),
PdbResult(id='4N3C',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='2.55'),
PdbResult(id='4XI9',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.1'),
PdbResult(id='4XIF',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='3.2'),
PdbResult(id='5BNW',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='2.4'),
PdbResult(id='5C1D',
method='X-Ray_Crystallography',
chain='A=323-1041',
resolution='2.05'),
PdbResult(id='5HGV',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='2.05'),
PdbResult(id='5LVV',
method='X-Ray_Crystallography',
chain='A=325-1046',
resolution='2.54'),
PdbResult(id='5LWV',
method='X-Ray_Crystallography',
chain='A=325-1046',
resolution='1.9'),
PdbResult(id='5NPR',
method='X-Ray_Crystallography',
chain='A=325-1041',
resolution='1.85'),
PdbResult(id='5NPS',
method='X-Ray_Crystallography',
chain='A=324-1041',
resolution='1.68'),
PdbResult(id='3TAX',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='1.88'),
PdbResult(id='3PE3',
method='X-Ray_Crystallography',
chain='A/B/C/D=323-1041',
resolution='2.78'),
PdbResult(id='3PE4',
method='X-Ray_Crystallography',
chain='A/C=323-1041',
resolution='1.95'),
PdbResult(id='1W3B',
method='X-Ray_Crystallography',
chain='A/B=26-410',
resolution='2.85')}}
Find AlphaFold models for uniprot entries¶
In [7]:
Copied!
afresults = search4af(uniprot_accessions, limit=200)
pprint(afresults)
afresults = search4af(uniprot_accessions, limit=200)
pprint(afresults)
{'A0A087WUV0': {'A0A087WUV0'},
'A0A0C5B5G6': {'A0A0C5B5G6'},
'A0A0U1RQI7': {'A0A0U1RQI7'},
'A0A1B0GTS1': {'A0A1B0GTS1'},
'A0A1B0GVZ6': {'A0A1B0GVZ6'},
'A0A1B0GWH4': {'A0A1B0GWH4'},
'A0A1W2PPF3': {'A0A1W2PPF3'},
'A0A1W2PPK0': {'A0A1W2PPK0'},
'A0A1W2PPM1': {'A0A1W2PPM1'},
'A0A1W2PQ73': {'A0A1W2PQ73'},
'A0A1W2PQL4': {'A0A1W2PQL4'},
'A0A1W2PRP0': {'A0A1W2PRP0'},
'A0A2R8Y619': {'A0A2R8Y619'},
'A0A2Z4LIS9': {'A0A2Z4LIS9'},
'A0A3B3IU63': {'A0A3B3IU63'},
'A0A5F9ZHS7': {'A0A5F9ZHS7'},
'A1A519': {'A1A519'},
'A1YPR0': {'A1YPR0'},
'A2RRD8': {'A2RRD8'},
'A2RU54': {'A2RU54'},
'A3KN83': {'A3KN83'},
'A6NCS4': {'A6NCS4'},
'A6NDR6': {'A6NDR6'},
'A6NDX5': {'A6NDX5'},
'A6NDZ8': {'A6NDZ8'},
'A6NE82': {'A6NE82'},
'A6NFD8': {'A6NFD8'},
'A6NFI3': {'A6NFI3'},
'A6NFQ7': {'A6NFQ7'},
'A6NGD5': {'A6NGD5'},
'A6NHJ4': {'A6NHJ4'},
'A6NHT5': {'A6NHT5'},
'A6NI15': {'A6NI15'},
'A6NJ08': {'A6NJ08'},
'A6NJ46': {'A6NJ46'},
'A6NJG6': {'A6NJG6'},
'A6NJL1': {'A6NJL1'},
'A6NJT0': {'A6NJT0'},
'A6NK53': {'A6NK53'},
'A6NK75': {'A6NK75'},
'A6NKF2': {'A6NKF2'},
'A6NLW8': {'A6NLW8'},
'A6NM28': {'A6NM28'},
'A6NMT0': {'A6NMT0'},
'A6NN14': {'A6NN14'},
'A6NNA5': {'A6NNA5'},
'A6NNF4': {'A6NNF4'},
'A6NP11': {'A6NP11'},
'A8K0S8': {'A8K0S8'},
'A8K830': {'A8K830'},
'A8K8V0': {'A8K8V0'},
'A8MPP1': {'A8MPP1'},
'A8MQ14': {'A8MQ14'},
'A8MT65': {'A8MT65'},
'A8MT69': {'A8MT69'},
'A8MTJ6': {'A8MTJ6'},
'A8MTQ0': {'A8MTQ0'},
'A8MTY0': {'A8MTY0'},
'A8MUV8': {'A8MUV8'},
'A8MUZ8': {'A8MUZ8'},
'A8MWA4': {'A8MWA4'},
'A8MXY4': {'A8MXY4'},
'A8MYZ6': {'A8MYZ6'},
'A8MZ59': {'A8MZ59'},
'A9YTQ3': {'A9YTQ3'},
'B1APH4': {'B1APH4'},
'B2RD01': {'B2RD01'},
'B2RPK0': {'B2RPK0'},
'B2RXF5': {'B2RXF5'},
'B4DU55': {'B4DU55'},
'B4DX44': {'B4DX44'},
'B4DXR9': {'B4DXR9'},
'C9JN71': {'C9JN71'},
'C9JSJ3': {'C9JSJ3'},
'E7ETH6': {'E7ETH6'},
'E9PAV3': {'E9PAV3'},
'E9PGG2': {'E9PGG2'},
'O00110': {'O00110'},
'O00255': {'O00255'},
'O00257': {'O00257'},
'O00268': {'O00268'},
'O00287': {'O00287'},
'O00321': {'O00321'},
'O00327': {'O00327'},
'O00358': {'O00358'},
'O00409': {'O00409'},
'O00470': {'O00470'},
'O00479': {'O00479'},
'O00482': {'O00482'},
'O00570': {'O00570'},
'O00571': {'O00571'},
'O00712': {'O00712'},
'O00716': {'O00716'},
'O14497': {'O14497'},
'O14503': {'O14503'},
'O14529': {'O14529'},
'O14593': {'O14593'},
'O14627': {'O14627'},
'O14628': {'O14628'},
'O14646': {'O14646'},
'O14647': {'O14647'},
'O14709': {'O14709'},
'O14737': {'O14737'},
'O14744': {'O14744'},
'O14746': {'O14746'},
'O14753': {'O14753'},
'O14770': {'O14770'},
'O14771': {'O14771'},
'O14802': {'O14802'},
'O14813': {'O14813'},
'O14867': {'O14867'},
'O14896': {'O14896'},
'O14901': {'O14901'},
'O14948': {'O14948'},
'O14978': {'O14978'},
'O14979': {'O14979'},
'O15015': {'O15015'},
'O15054': {'O15054'},
'O15055': {'O15055'},
'O15062': {'O15062'},
'O15090': {'O15090'},
'O15119': {'O15119'},
'O15160': {'O15160'},
'O15162': {'O15162'},
'O15164': {'O15164'},
'O15178': {'O15178'},
'O15198': {'O15198'},
'O15209': {'O15209'},
'O15226': {'O15226'},
'O15266': {'O15266'},
'O15294': {'O15294'}}
Find Electron Microscopy Data Bank (EMDB) entries for uniprot entries¶
In [8]:
Copied!
uniprot_accessions = search4emdb(uniprot_accessions, limit=200)
pprint(uniprot_accessions)
uniprot_accessions = search4emdb(uniprot_accessions, limit=200)
pprint(uniprot_accessions)
{'A8MT69': {'EMD-14351', 'EMD-33196', 'EMD-33197', 'EMD-14336'},
'O00255': {'EMD-34195'},
'O00268': {'EMD-31075',
'EMD-31107',
'EMD-31108',
'EMD-31109',
'EMD-31110',
'EMD-31111',
'EMD-31112',
'EMD-31113',
'EMD-31114',
'EMD-31115',
'EMD-31116',
'EMD-31118',
'EMD-31119',
'EMD-31204',
'EMD-31207',
'EMD-34359',
'EMD-34360',
'EMD-37395',
'EMD-37396',
'EMD-37398',
'EMD-37399',
'EMD-37400',
'EMD-37401',
'EMD-37402',
'EMD-37403',
'EMD-9298',
'EMD-9302',
'EMD-9305',
'EMD-9306'},
'O00482': {'EMD-17740'},
'O14497': {'EMD-0974'},
'O14744': {'EMD-29677', 'EMD-27078', 'EMD-20764', 'EMD-7137', 'EMD-23609'},
'O14746': {'EMD-12174',
'EMD-14196',
'EMD-14197',
'EMD-14198',
'EMD-14199',
'EMD-2310',
'EMD-2311',
'EMD-2312',
'EMD-26086',
'EMD-26087',
'EMD-26088',
'EMD-31811',
'EMD-31812'},
'O14802': {'EMD-11673',
'EMD-11736',
'EMD-11738',
'EMD-11742',
'EMD-11904',
'EMD-30577',
'EMD-30578',
'EMD-30779',
'EMD-30865',
'EMD-31621',
'EMD-31622',
'EMD-35712',
'EMD-35719',
'EMD-35722'},
'O14867': {'EMD-19766',
'EMD-42049',
'EMD-42051',
'EMD-42064',
'EMD-42102',
'EMD-42105',
'EMD-42106'},
'O14979': {'EMD-14738'},
'O15062': {'EMD-44389'},
'O15160': {'EMD-11673',
'EMD-11736',
'EMD-11738',
'EMD-11742',
'EMD-11904',
'EMD-12795',
'EMD-12796',
'EMD-12797',
'EMD-15135',
'EMD-30577',
'EMD-30578',
'EMD-30779',
'EMD-30865',
'EMD-31621',
'EMD-31622',
'EMD-31876',
'EMD-31877',
'EMD-31878',
'EMD-35712',
'EMD-35719',
'EMD-35722'},
'O15294': {'EMD-33768', 'EMD-12588', 'EMD-33773'}}
In [ ]:
Copied!