def cluster_dataset(array_like, options=''):
'''cluster dataset
Parameters
----------
array_like : array_like
options : str, cpptraj options
Returns
-------
cluster index for each data point
Examples
--------
>>> import pytraj as pt
>>> import numpy as np
>>> array_like = np.random.randint(0, 10, 1000)
>>> data = pt.cluster.cluster_dataset(array_like, 'clusters 10 epsilon 3.0')
'''
import numpy as np
c_dslist = CpptrajDatasetList()
c_dslist.add('double', '__array_like')
c_dslist[0].resize(len(array_like))
c_dslist[0].values[:] = array_like
act = c_analysis.Analysis_Clustering()
command = 'data __array_like ' + options
act(command, dslist=c_dslist)
return np.array(c_dslist[-2])
def test_1(self):
traj = pt.iterload(fn('Tc5b.x'), fn('Tc5b.top'))
act = adict['distance']
dslist = CpptrajDatasetList()
act.read_input(":2@CA :10@CA", traj.top, dslist=dslist)
act.setup(traj.top)
for frame in traj.iterframe(stop=5):
act.compute(frame)
dslist = CpptrajDatasetList()
act2 = adict['distance']
act2.read_input(":2@CA :10@CA", traj.top, dslist=dslist)
act2.setup(traj.top)
act2.compute(traj.iterframe(stop=5))
assert act2.n_frames == 5
def vector(traj=None,
command="",
frame_indices=None,
dtype='ndarray',
top=None):
"""perform vector calculation. See example below. Same as 'vector' command in cpptraj.
Parameters
----------
traj : Trajectory-like or iterable that produces :class:`pytraj.Frame`
command : str or a list of strings, cpptraj command
frame_indices : array-like, optional, default None
only perform calculation for given frame indices
dtype : output's dtype, default 'ndarray'
top : Topology, optional, default None
Returns
-------
out : numpy ndarray, shape (n_frames, 3) if command is a string
numpy ndarray, shape (n_vectors, n_frames, 3) if command is a list of strings
Examples
--------
>>> import pytraj as pt
>>> traj = pt.datafiles.load_tz2_ortho()
>>> data = pt.vector.vector(traj, "@CA @CB")
>>> data = pt.vector.vector(traj, [("@CA @CB"),])
>>> data = pt.vector.vector(traj, "principal z")
>>> data = pt.vector.vector(traj, "principal x")
>>> data = pt.vector.vector(traj, "ucellx")
>>> data = pt.vector.vector(traj, "boxcenter")
>>> data = pt.vector.vector(traj, "box")
Notes
-----
It's faster to calculate with a list of commands.
For example, if you need to perform 3 calculations for 'ucellx', 'boxcenter', 'box'
like below:
>>> data = pt.vector.vector(traj, "ucellx")
>>> data = pt.vector.vector(traj, "boxcenter")
>>> data = pt.vector.vector(traj, "box")
You should use a list of commands for faster calculation.
>>> comlist = ['ucellx', 'boxcenter', 'box']
>>> data = pt.vector.vector(traj, comlist)
"""
c_dslist = CpptrajDatasetList()
top_ = get_topology(traj, top)
list_of_commands = get_list_of_commands(command)
fi = get_fiterator(traj, frame_indices)
actlist = ActionList()
for command in list_of_commands:
act = c_action.Action_Vector()
actlist.add(act, command, top_, dslist=c_dslist)
actlist.compute(fi)
return get_data_from_dtype(c_dslist, dtype=dtype)
def read_data(cls, filename, arg=""):
'''
>>> from pytraj.datasets.datasetlist import DatasetList
>>> d = DatasetList.read_data('data/tc5b.native_contacts.dat')
'''
df = DataFile()
dslist = CpptrajDatasetList()
df.read_data(filename, ArgList(arg), dslist)
return DatasetList(dslist)
def read_data(cls, filename, arg=""):
'''
>>> from pytraj.datasets.datasetlist import DatasetList
>>> DatasetList.read_data('data/tc5b.native_contacts.dat')
<pytraj.DatasetList with 2 datasets>
Contacts_00001[native]
[ 7095. 5904. 5638. 5600. 5695. 5745. 5611. 5556. 5739. 5748.]
<BLANKLINE>
Contacts_00001[nonnative]
[ 0. 2696. 3065. 3552. 3700. 2624. 4000. 3797. 3482. 4265.]
'''
df = DataFile()
dslist = CpptrajDatasetList()
df.read_data(filename, ArgList(arg), dslist)
return DatasetList(dslist)
def nastruct(traj=None,
ref=0,
resrange=None,
resmap=None,
hbcut=3.5,
frame_indices=None,
pucker_method='altona',
dtype='nupars',
groove_3dna=True,
top=None):
"""compute nucleic acid parameters. (adapted from cpptraj doc)
Parameters
----------
traj : Trajectory-like
ref : {Frame, int}, default 0 (first frame)
resrange : None, str or array-like of integers
resmap : residue map, example: 'AF2:A'
hbcut : float, default=3.5 Angstrong
Distance cutoff for determining basepair hbond
pucker_method : str, {'altona', 'cremer'}, default 'altona'
'altona' : Use method of Altona & Sundaralingam to calculate sugar pucker
'cremer' : Use method of Cremer and Pople to calculate sugar pucker'
frame_indices : array-like, default None (all frames)
groove_3dna : bool, default True
if True, major and minor groove will match 3DNA's output.
dtype : str, {'nupars', 'cpptraj_dataset'}, default 'nupars'
Returns
-------
out : nupars object. One can assess different values (major groove width, xdips values
...) by accessing its attribute. See example below.
Examples
--------
>>> import pytraj as pt
>>> import numpy as np
>>> traj = pt.datafiles.load_rna()
>>> data = pt.nastruct(traj, groove_3dna=False)
>>> data.keys()[:5] # doctest: +SKIP
['buckle', 'minor', 'major', 'xdisp', 'stagger']
>>> # get minor groove width values for each pairs for each snapshot
>>> # data.minor is a tuple, first value is a list of basepairs, seconda value is
>>> # numpy array, shape=(n_frames, n_pairs)
>>> data.minor # doctest: +SKIP
(['1G16C', '2G15C', '3G14C', '4C13G', '5G12C', '6C11G', '7C10G', '8C9G'],
array([[ 13.32927036, 13.403409 , 13.57159901, ..., 13.26655865,
13.43054485, 13.4557209 ],
[ 13.32002068, 13.45918751, 13.63253593, ..., 13.27066231,
13.42743683, 13.53450871],
[ 13.34087658, 13.53778553, 13.57062435, ..., 13.29017353,
13.38542843, 13.46101475]]))
>>> data.twist # doctest: +SKIP
(['1G16C-2G15C', '2G15C-3G14C', '3G14C-4C13G', '4C13G-5G12C', '5G12C-6C11G', '6C11G-7C10G', '7C10G-8C9G'],
array([[ 34.77773666, 33.98158646, 30.18647003, ..., 35.14608765,
33.9628334 , 33.13056946],
[ 33.39176178, 32.68476105, 28.36385536, ..., 36.59774399,
30.20827484, 26.48732948],
[ 36.20665359, 32.58955002, 27.47707367, ..., 33.42843246,
30.90047073, 33.73724365]]))
>>> # change dtype
>>> data = pt.nastruct(traj, dtype='cpptraj_dataset')
"""
from pytraj.datasets.c_datasetlist import DatasetList as CpptrajDatasetList
from .c_action import c_action
from pytraj.array import DataArray
_resrange = get_resrange(resrange)
fi = get_fiterator(traj, frame_indices)
ref = get_reference(traj, ref)
_top = get_topology(traj, top)
_resmap = "resmap " + resmap if resmap is not None else ""
_hbcut = "hbcut " + str(hbcut) if hbcut is not None else ""
_pucker_method = pucker_method
_groove_3dna = 'groovecalc 3dna' if groove_3dna else ''
command = " ".join(
(_resrange, _resmap, _hbcut, _pucker_method, _groove_3dna))
dslist = CpptrajDatasetList()
# need to construct 3 steps so we can pickle this method for parallel
# not sure why?
act = c_action.Action_NAstruct(command, top=_top, dslist=dslist)
act.compute(ref)
act.compute(fi)
if dtype == 'cpptraj_dataset':
return dslist
elif dtype == 'nupars':
dslist_py = []
for d in dslist:
dslist_py.append(DataArray(d))
dslist_py[-1].values = dslist_py[-1].values[1:]
return nupars(_group(dslist_py, lambda x: x.aspect))
else:
raise ValueError("only support dtype = {'nupars', 'cpptraj_dataset'}")
def calc_dssp(traj=None,
mask="",
frame_indices=None,
dtype='ndarray',
simplified=False,
top=None):
"""return dssp profile for frame/traj
Parameters
----------
traj : Trajectory-like
mask: str
atom mask
frame_indices : {None, array-like}, default None, optional
specify frame numbers for calculation.
if None, do all frames
dtype : str, default 'ndarray'
return data type, for regular user, just use default one (ndarray).
use dtype='dataset' if wanting to get secondary structure in integer format
simplified : bool, default False
if True, use simplified codes, only has 'H', 'E' and 'C'
if False, use all DSSP codes
Returns
-------
out_0: ndarray, shape=(n_residues,)
residue names
out_1: ndarray, shape=(n_frames, n_residues)
DSSP for each residue
out_2 : pytraj.DatasetList
average value for each secondary structure type
Examples
--------
>>> import pytraj as pt
>>> traj = pt.load_pdb_rcsb('1l2y')
>>> residues, ss, _ = pt.dssp(traj, ":2-10")
>>> residues # doctest: +SKIP
array(['LEU:2', 'TYR:3', 'ILE:4', 'GLN:5', 'TRP:6', 'LEU:7', 'LYS:8',
'ASP:9', 'GLY:10'],
dtype='<U6')
>>> ss # doctest: +SKIP
array([['0', 'H', 'H', ..., 'H', 'T', '0'],
['0', 'H', 'H', ..., 'H', 'T', '0'],
['0', 'H', 'H', ..., 'H', 'T', '0'],
...,
['0', 'H', 'H', ..., 'H', 'T', '0'],
['0', 'H', 'H', ..., 'H', 'H', '0'],
['0', 'H', 'H', ..., 'H', 'T', '0']],
dtype='<U1')
>>> residues, ss, _ = pt.dssp(traj, mask=range(100))
>>> traj = pt.fetch_pdb('1l2y')
>>> residues, ss, _ = pt.dssp(traj, simplified=True)
>>> ss[0].tolist() # first frame
['C', 'H', 'H', 'H', 'H', 'H', 'H', 'H', 'C', 'C', 'H', 'H', 'H', 'H', 'C', 'C', 'C', 'C', 'C', 'C']
Notes
-----
========= ======= ========= =======================
Character Integer DSSP_Char Seconday structure type
========= ======= ========= =======================
0 0 '0' None
b 1 'E' Parallel Beta-sheet
B 2 'B' Anti-parallel Beta-sheet
G 3 'G' 3-10 helix
H 4 'H' Alpha helix
I 5 'I' Pi (3-14) helix
T 6 'T' Turn
S 7 'S' Bend
========= ======= ========= =======================
Simlified codes::
- 'H': include 'H', 'G', 'I' (helix)
- 'E': include 'E', 'B' (strand)
- 'C': include 'T', 'S' or '0' (coil)
Simlified codes will be mostly used for visulization in other packages.
"""
from pytraj.datasets.c_datasetlist import DatasetList as CpptrajDatasetList
from pytraj.c_action.c_action import Action_DSSP
command = mask
dslist = CpptrajDatasetList()
Action_DSSP()(command, traj, top=top, dslist=dslist)
# replace key to something nicer
for key, dset in dslist.iteritems():
if 'DSSP' in key:
key = key.replace("DSSP_00000[", "")
key = key.replace("]", "_avg")
dset.key = key.lower()
dtype = dtype.lower()
if dtype == 'ndarray':
# get all dataset from DatSetList if dtype == integer
arr0 = dslist.grep("integer", mode='dtype').values
keys = dslist.grep("integer", mode='dtype').keys()
avg_dict = DatasetList(dslist.grep('_avg'))
ss_array = np.asarray([
_to_string_secondary_structure(arr, simplified=simplified)
for arr in arr0
]).T
return np.asarray(keys), ss_array, avg_dict
else:
return get_data_from_dtype(dslist, dtype=dtype)
def vector_mask(traj=None,
mask="",
frame_indices=None,
dtype='ndarray',
top=None):
"""compute vector between two maskes
Parameters
----------
traj : Trajectory-like or iterable that produces Frame
mask: str or array of string or array of intergers, shape (n_vectors, 2)
vector maskes
frame_indices : array-like or iterable that produces integer number
frame indices
dtype : str, default 'ndarray'
output dtype
top : Topology, optional, default None
Returns
-------
if mask is a string, return 2D ndarray, shape (n_frames, 3)
if mask is a list of strings or a 2D ndarray, return 3D ndarray, shape (n_vectors, n_frames, 3)
Examples
--------
>>> # calcualte N-H vector
>>> import pytraj as pt
>>> import numpy as np
>>> traj = pt.load_sample_data('tz2')
>>> from pytraj import vector as va
>>> n_indices = pt.select_atoms('@N', traj.top)
>>> h_indices = n_indices + 1
>>> # create n-h pair for vector calculation
>>> n_h_pairs = np.array(list(zip(n_indices, h_indices)))
>>> data_vec = va.vector_mask(traj, n_h_pairs, dtype='ndarray')
>>> # compute vectors for specific frame indices (0, 4)
>>> data_vec = va.vector_mask(traj, n_h_pairs, frame_indices=[0, 4], dtype='ndarray')
"""
from pytraj.utils.get_common_objects import get_topology, get_data_from_dtype, get_fiterator
from pytraj.utils.get_common_objects import get_list_of_commands
from pytraj.datasets.c_datasetlist import DatasetList as CpptrajDatasetList
from pytraj.analysis.c_action.c_action import Action_Vector
from pytraj.analysis.c_action.actionlist import ActionList
fi = get_fiterator(traj, frame_indices)
_top = get_topology(fi, top)
dslist = CpptrajDatasetList()
template_command = ' mask '
cm_arr = np.asarray(mask)
if cm_arr.dtype.kind != 'i':
list_of_commands = get_list_of_commands(mask)
else:
if cm_arr.ndim != 2:
raise ValueError(
'if mask is a numpy.ndarray, it must have ndim = 2')
list_of_commands = _2darray_to_atommask_groups(cm_arr)
actlist = ActionList()
for command in list_of_commands:
act = Action_Vector()
_command = command + template_command
actlist.add(act, _command, _top, dslist=dslist)
actlist.compute(fi)
return get_data_from_dtype(dslist, dtype=dtype)