josejimenezluna

def get_protein_features(usercoords, usercenters, userchannels, rotate_over=None, boxsize=[BOXSIZE]*3):
    """
    Featurizes protein pocket using 3D voxelization
    """
    if rotate_over is not None:
        alpha = np.random.uniform(0, 2 * np.pi)
        beta = np.random.uniform(0, 2 * np.pi)
        gamma = np.random.uniform(0, 2 * np.pi)        
        
        usercoords = (usercoords.squeeze() - rotate_over)

josejimenezluna

import numpy as np
from numpy.linalg import norm, solve
from scipy.spatial.distance import cdist
from sklearn.neighbors import kneighbors_graph


def phi(l, mu):
    return (mu * (np.sqrt(l) - 1)**2)

josejimenezluna

def parse(process):
    out = process.stdout.decode('utf8')
    out = out.split('\n')
    for line in out:
        if line[:2] == 'HP':
            hp = float(line.split('=')[1])
        elif line[:2] == 'HM':
            hm = float(line.split('=')[1])
        elif line[:2] == 'HS':
            hs = float(line.split('=')[1])

josejimenezluna

from htmd.molecule.molecule import Molecule 
target = '/shared/jose/databases/bindingdb_val/3IBU/target_0.pdbqt'
mol = Molecule(target)

josejimenezluna

import numpy as np
from pyGPGO.covfunc import matern32
from pyGPGO.acquisition import Acquisition
from pyGPGO.surrogates.GaussianProcess import GaussianProcess
from pyGPGO.GPGO import GPGO


def f(x, y):
    # Franke's function (https://www.mathworks.com/help/curvefit/franke.html)
    one = 0.75 * np.exp(-(9 * x - 2) ** 2 / 4 - (9 * y - 2) ** 2 / 4)

josejimenezluna

import numpy as np
from pyGPGO.covfunc import matern32
from pyGPGO.acquisition import Acquisition
from pyGPGO.surrogates.GaussianProcess import GaussianProcess
from pyGPGO.GPGO import GPGO


def f(x, y):
    # Franke's function (https://www.mathworks.com/help/curvefit/franke.html)
    one = 0.75 * np.exp(-(9 * x - 2) ** 2 / 4 - (9 * y - 2) ** 2 / 4)

josejimenezluna

def pairCor(distances, bins = 50):
        distances = distances.flatten()
        c, breaks = np.histogram(distances, bins = bins)
        dr = breaks[1] - breaks[0]
        N = len(distances)
        V = 4 * np.pi* breaks**2 * dr
        rho = N/(np.max(V))

        c = c/N
        c = c/V[:bins]