def test_records():
"""Test private _read_pdb."""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.to_pdb(path=OUTFILE, records=["HETATM"])
with open(OUTFILE, "r") as f:
f1 = f.read()
os.remove(OUTFILE)
assert f1 == hetatm
def test_anisou():
"""Test writing ANISOU entries."""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME2)
ppdb.to_pdb(path=OUTFILE, records=None)
with open(OUTFILE, "r") as f:
f1 = f.read()
# os.remove(OUTFILE)
assert f1 == four_eiy
def test_defaults():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.to_pdb(path=OUTFILE, records=None)
with open(TESTDATA_FILENAME, "r") as f:
f1 = f.read()
with open(OUTFILE, "r") as f:
f2 = f.read()
assert f1 == f2
os.remove(OUTFILE)
def test_fetch_pdb():
"""Test fetch_pdb"""
try:
ppdb = PandasPDB()
txt = ppdb._fetch_pdb('3eiy')
except HTTPError:
pass
if txt: # skip if PDB down
txt[:100] == three_eiy[:100]
ppdb.fetch_pdb('3eiy')
assert ppdb.pdb_text == txt
def test_fetch_pdb():
"""Test fetch_pdb"""
try:
ppdb = PandasPDB()
txt = ppdb._fetch_pdb('3eiy')
except HTTPError:
pass
if txt: # skip if PDB down
txt[:100] == three_eiy[:100]
ppdb.fetch_pdb('3eiy')
assert ppdb.pdb_text == txt
def test_fetch_pdb():
"""Test fetch_pdb"""
try:
ppdb = PandasPDB()
txt = ppdb._fetch_pdb('3eiy')
except HTTPError:
pass
if txt: # skip if PDB down
txt[:100] == three_eiy[:100]
ppdb.fetch_pdb('3eiy')
assert ppdb.pdb_text == txt
txt = ppdb._fetch_pdb('3ey')
err = "We're sorry, but the requested file is not available"
assert err in txt
def _gen_anisou(self):
''' Generate information to mimic the ANISOU part of a pdb file.
Not implemented because not needed as of current version (1/31/2017)
'''
self.df = PandasPDB().read_pdb('./test.pdb').df['ANISOU']
return
def test__construct_df():
"""Test pandas dataframe construction"""
ppdb = PandasPDB()
dfs = ppdb._construct_df(three_eiy.splitlines())
assert set(dfs.keys()) == {'OTHERS', 'ATOM', 'ANISOU', 'HETATM'}
assert set(dfs['ATOM'].columns) == set(ATOM_DF_COLUMNS)
assert set(dfs['HETATM'].columns) == set(ATOM_DF_COLUMNS)
assert set(dfs['ANISOU'].columns) == set(ANISOU_DF_COLUMNS)
exp = pd.Series(np.array(['ATOM', 1, '', 'N', '', 'SER', '', 'A', 2, '', '',
2.527, 54.656, -1.667, 1.0, 52.73, '', '', 'N', None, 609]),
index=['record_name', 'atom_number', 'blank_1',
'atom_name', 'alt_loc', 'residue_name',
'blank_2', 'chain_id', 'residue_number',
'insertion', 'blank_3',
'x_coord', 'y_coord', 'z_coord',
'occupancy', 'b_factor', 'blank_4',
'segment_id', 'element_symbol',
'charge', 'line_idx'])
assert exp.equals(dfs['ATOM'].loc[0, :])
def _gen_others(self):
''' Essentialy the 'meta information' at the top of pdb files
Will add 'OTHER' information to self.df dict
Returns: None
'''
# essentially load the headers from the test.pdb file
# which is PDB with some things chagned to make it look obviously wrong
self.df['OTHERS'] = PandasPDB().read_pdb('./test.pdb').df['OTHERS']
return
def test__construct_df():
"""Test pandas dataframe construction"""
ppdb = PandasPDB()
dfs = ppdb._construct_df(three_eiy.splitlines())
assert set(dfs.keys()) == {'OTHERS', 'ATOM', 'ANISOU', 'HETATM'}
assert set(dfs['ATOM'].columns) == set(ATOM_DF_COLUMNS)
assert set(dfs['HETATM'].columns) == set(ATOM_DF_COLUMNS)
assert set(dfs['ANISOU'].columns) == set(ANISOU_DF_COLUMNS)
exp = pd.Series(np.array([
'ATOM', 1, '', 'N', '', 'SER', '', 'A', 2, '', '', 2.527, 54.656,
-1.667, 1.0, 52.73, '', '', 'N', None, 609
]),
index=[
'record_name', 'atom_number', 'blank_1', 'atom_name',
'alt_loc', 'residue_name', 'blank_2', 'chain_id',
'residue_number', 'insertion', 'blank_3', 'x_coord',
'y_coord', 'z_coord', 'occupancy', 'b_factor',
'blank_4', 'segment_id', 'element_symbol', 'charge',
'line_idx'
])
assert exp.equals(dfs['ATOM'].loc[0, :])
def test_get_df():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
shape = ppdb.get('c-alpha').shape
assert shape == (174, 21), shape
shape = ppdb.get('hydrogen', invert=True).shape
assert shape == (1330, 21), shape
shape = ppdb.get('hydrogen').shape
assert shape == (0, 21), shape
shape = ppdb.get('main chain').shape
assert shape == (696, 21), shape
shape = ppdb.get('heavy').shape
assert shape == (1330, 21), shape
shape = ppdb.get('carbon').shape
assert shape == (473, 21), shape
def test_anisou():
"""Test writing ANISOU entries."""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME2)
ppdb.to_pdb(path=OUTFILE, records=None)
with open(OUTFILE, 'r') as f:
f1 = f.read()
# os.remove(OUTFILE)
assert f1 == four_eiy
def test_records():
"""Test private _read_pdb."""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.to_pdb(path=OUTFILE, records=['HETATM'])
with open(OUTFILE, 'r') as f:
f1 = f.read()
os.remove(OUTFILE)
assert f1 == hetatm
def test_defaults():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.to_pdb(path=OUTFILE, records=None)
with open(TESTDATA_FILENAME, 'r') as f:
f1 = f.read()
with open(OUTFILE, 'r') as f:
f2 = f.read()
assert f1 == f2
os.remove(OUTFILE)
def test_get_df():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
shape = ppdb.get('c-alpha').shape
assert shape == (174, 21), shape
shape = ppdb.get('hydrogen', invert=True).shape
assert shape == (1330, 21), shape
shape = ppdb.get('hydrogen').shape
assert shape == (0, 21), shape
shape = ppdb.get('main chain').shape
assert shape == (696, 21), shape
shape = ppdb.get('heavy').shape
assert shape == (1330, 21), shape
shape = ppdb.get('carbon').shape
assert shape == (473, 21), shape
def check_structure_exists(name):
if not name:
raise ValueError("Empty name, cannot check if structure is valid")
pro = None
for _ in range(3):
try:
pro = PandasPDB().fetch_pdb(name)
if pro: break
except:
continue
if not hasattr(pro, 'df'):
return False
if len(pro.df['HETATM']) == 0 or len(pro.df["ATOM"]) == 0:
return False
# no errors; this structure is probably fine?
return True
def test_fetch_pdb():
"""Test fetch_pdb"""
try:
ppdb = PandasPDB()
txt = ppdb._fetch_pdb('3eiy')
except HTTPError:
pass
if txt: # skip if PDB down
txt[:100] == three_eiy[:100]
ppdb.fetch_pdb('3eiy')
assert ppdb.pdb_text == txt
txt = ppdb._fetch_pdb('3ey')
err = "We're sorry, but the requested file is not available"
assert err in txt
def test_get_exceptions():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.get('main-chai')
def test_get_all():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
for i in ['c-alpha', 'hydrogen', 'main chain']:
ppdb.get(i)
def test__read_pdb():
"""Test private _read_pdb"""
ppdb = PandasPDB()
txt = ppdb._read_pdb(TESTDATA_FILENAME)
print(txt)
assert txt == three_eiy
def test_anisou_input_handling():
"""Test public read_pdb"""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME2)
assert ppdb.pdb_text == four_eiy
assert ppdb.code == '4eiy', ppdb.code
def test_get_exceptions():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
ppdb.get('main-chai')
def test_ligand():
r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'], s='hydrogen', invert=True)
assert r == 2.6444, r
def test_read_pdb():
"""Test public read_pdb"""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
assert ppdb.pdb_text == three_eiy
assert ppdb.code == '3eiy', ppdb.code
def test_ligand_default():
r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'], s=None)
assert r == 2.6444, r
def test_protein():
r = PandasPDB.rmsd(p1t48.df['ATOM'], p1t49.df['ATOM'], s='c-alpha', invert=False)
assert r == 0.4785, r
def test_ligand_default():
r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
s=None)
assert r == 2.6444, r
def test__read_pdb_gz():
"""Test public _read_pdb with gzip files"""
ppdb = PandasPDB()
txt = ppdb._read_pdb(TESTDATA_FILENAME_GZ)
assert txt == three_eiy
# Author: Sebastian Raschka <*****@*****.**>
# License: BSD 3 clause
# Project Website: http://rasbt.github.io/biopandas/
# Code Repository: https://github.com/rasbt/biopandas
from biopandas.pdb import PandasPDB
import os
import numpy as np
import pandas as pd
from nose.tools import raises
TESTDATA_FILENAME = os.path.join(os.path.dirname(__file__), 'data',
'3eiy_stripped_no_ele.pdb')
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
def test_impute_hetatm():
new = ppdb.impute_element(sections=['HETATM'])
assert new['HETATM']['element_symbol'][1] == 'N'
assert new['HETATM']['element_symbol'][10] == 'O'
assert new['ATOM']['element_symbol'][1] == ''
assert new['ATOM']['element_symbol'][10] == ''
def test_impute_atom():
new = ppdb.impute_element(sections=['ATOM'])
assert new['ATOM']['element_symbol'][1] == 'C'
assert new['ATOM']['element_symbol'][10] == 'C'
# Project Website: http://rasbt.github.io/biopandas/
# Code Repository: https://github.com/rasbt/biopandas
from biopandas.pdb import PandasPDB
import os
import numpy as np
import pandas as pd
from nose.tools import raises
TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), 'data', '1t48_995.pdb')
TESTDATA_1t49 = os.path.join(os.path.dirname(__file__), 'data', '1t49_995.pdb')
TESTDATA_lig1 = os.path.join(os.path.dirname(__file__), 'data', 'lig_conf_1.pdb')
TESTDATA_lig2 = os.path.join(os.path.dirname(__file__), 'data', 'lig_conf_2.pdb')
p1t48 = PandasPDB()
p1t48.read_pdb(TESTDATA_1t48)
p1t49 = PandasPDB()
p1t49.read_pdb(TESTDATA_1t49)
pl1 = PandasPDB()
pl1.read_pdb(TESTDATA_lig1)
pl2 = PandasPDB()
pl2.read_pdb(TESTDATA_lig2)
def test_equal():
r = PandasPDB.rmsd(p1t48.df['ATOM'], p1t48.df['ATOM'], s=None)
assert r == 0.000, r
@raises(AttributeError)
def test_wrong_arg():
def test_anisou_input_handling():
"""Test public read_pdb"""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME2)
assert ppdb.pdb_text == four_eiy
assert ppdb.code == '4eiy', ppdb.code
def test__read_pdb():
"""Test private _read_pdb"""
ppdb = PandasPDB()
txt = ppdb._read_pdb(TESTDATA_FILENAME)
print(txt)
assert txt == three_eiy
def test__read_pdb_gz():
"""Test public _read_pdb with gzip files"""
ppdb = PandasPDB()
txt = ppdb._read_pdb(TESTDATA_FILENAME_GZ)
assert txt == three_eiy
def test_wrong_arg():
r = PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
def test_incompatible():
r = PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s=None)
def test_read_pdb():
"""Test public read_pdb"""
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
assert ppdb.pdb_text == three_eiy
assert ppdb.code == '3eiy', ppdb.code
def test_invalid_query():
r = PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
def test_equal():
r = PandasPDB.rmsd(p1t48.df['ATOM'], p1t48.df['ATOM'], s=None)
assert r == 0.000, r
def test_get_all():
ppdb = PandasPDB()
ppdb.read_pdb(TESTDATA_FILENAME)
for i in ['c-alpha', 'hydrogen', 'main chain']:
ppdb.get(i)
