def make_map():
# representation types
morg2 = RepresentationType(name='morg2',
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata="""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""")
targets = RepresentationType(name='targets',
representation_func=PIDGIN(),
metadata="""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>.""")
random = RepresentationType(name='random',
representation_func=lambda m: pd.Series(np.random.random(100)),
metadata="""Uniformly distributed random feature vector of length 100"""
"""implemented using <a href="http://www.numpy.org">numpy</a> <a href="http://docs.scipy.org/doc/numpy/reference/generated/numpy.random.random.html#numpy.random.random">random</a> module""")
representation_types = [ morg2, targets, random ]
# reduction types
pca = ReductionMethod(name='PCA',
model=PCA(n_components=2),
metadata="""<a href="http://en.wikipedia.org/wiki/Principal_component_analysis">Principal component analysis</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>\n"""
"""<br/>Default parameters used.""")
mds = ReductionMethod(name='MDS',
model=MDS(),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Multidimensional_scaling" target="_blank">Multidimensional Scaling</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>"""
"""<br/>Default parameters used.""")
tsne = ReductionMethod(name='t-SNE',
model=TSNE(perplexity=1),
metadata=
"""<a href="http://lvdmaaten.github.io/tsne/">Student's t-distributed stochastic neighbour embedding</a>, """
"""implemented according to <a href="http://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf">van der Maartin et al. 2008</a>\n"""
"""<br/>Parameters used: Perplexity = 1, theta=0""")
reduction_types = [ pca, mds, tsne ]
# activity types
pIC20 = ActivityType(name='pIC20', metadata=
"""negative based-10 logarithm of the <a href="http://en.wikipedia.org/wiki/IC50">IC20</a>, the concentation of"""
"""compound required for 20% inhibition of growth of Lymphoma cells""")
IC20 = ActivityType(name='IC20', metadata=
"""<a href="http://en.wikipedia.org/wiki/IC50">IC20</a>, the concentation of"""
"""compound required for 20% inhibition of growth of Lymphoma cells""")
activity_types = [ pIC20, IC20 ]
# synergy types
excessOverBliss = SynergyType(name='ExcessOverBliss', metadata=
"""Difference in observed vs expected activity of the component compounds,"""
"""each at the IC20 concentration (when known) assuming the <a href="http://doi.wiley.com/10.1111/j.1744-7348.1939.tb06990.x">Bliss Independence model</a>""")
synergy_types = [ excessOverBliss ]
# data
compound_df = skc.read_smiles(os.path.join(DIRNAME, 'compounds.smiles'), name_column=1, title_line=True)
compound_df['pIC20'] = -np.log10(compound_df['IC20'])
combination_df = pd.read_csv(os.path.join(DIRNAME, 'combinations.csv'))
combination_df.set_index('id', inplace=True)
synergy_map = SynergyMap(compound_df=compound_df,
combination_df=combination_df,
representation_types=representation_types,
reduction_types=reduction_types,
activity_types=activity_types,
synergy_types=synergy_types,
metadata='DREAM Drug Combination Challenge Data')
return synergy_map
def make_map():
# representation types
morg2 = RepresentationType(
name='morg2',
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata=
"""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""")
targets = RepresentationType(
name='targets',
representation_func=PIDGIN(),
metadata=
"""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>."""
)
random = RepresentationType(
name='random',
representation_func=lambda m: pd.Series(np.random.random(100)),
metadata="""Uniformly distributed random feature vector of length 100"""
"""implemented using <a href="http://www.numpy.org">numpy</a> <a href="http://docs.scipy.org/doc/numpy/reference/generated/numpy.random.random.html#numpy.random.random">random</a> module"""
)
representation_types = [morg2, targets, random]
# reduction types
pca = ReductionMethod(
name='PCA',
model=PCA(n_components=2),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Principal_component_analysis">Principal component analysis</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>\n"""
"""<br/>Default parameters used.""")
mds = ReductionMethod(
name='MDS',
model=MDS(),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Multidimensional_scaling" target="_blank">Multidimensional Scaling</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>"""
"""<br/>Default parameters used.""")
tsne = ReductionMethod(
name='t-SNE',
model=TSNE(perplexity=1),
metadata=
"""<a href="http://lvdmaaten.github.io/tsne/">Student's t-distributed stochastic neighbour embedding</a>, """
"""implemented according to <a href="http://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf">van der Maartin et al. 2008</a>\n"""
"""<br/>Parameters used: Perplexity = 1, theta=0""")
reduction_types = [pca, mds, tsne]
# activity types
pIC20 = ActivityType(
name='pIC20',
metadata=
"""negative based-10 logarithm of the <a href="http://en.wikipedia.org/wiki/IC50">IC20</a>, the concentation of"""
"""compound required for 20% inhibition of growth of Lymphoma cells""")
IC20 = ActivityType(
name='IC20',
metadata=
"""<a href="http://en.wikipedia.org/wiki/IC50">IC20</a>, the concentation of"""
"""compound required for 20% inhibition of growth of Lymphoma cells""")
activity_types = [pIC20, IC20]
# synergy types
excessOverBliss = SynergyType(
name='ExcessOverBliss',
metadata=
"""Difference in observed vs expected activity of the component compounds,"""
"""each at the IC20 concentration (when known) assuming the <a href="http://doi.wiley.com/10.1111/j.1744-7348.1939.tb06990.x">Bliss Independence model</a>"""
)
synergy_types = [excessOverBliss]
# data
compound_df = skc.read_smiles(os.path.join(DIRNAME, 'compounds.smiles'),
name_column=1,
title_line=True)
compound_df['pIC20'] = -np.log10(compound_df['IC20'])
combination_df = pd.read_csv(os.path.join(DIRNAME, 'combinations.csv'))
combination_df.set_index('id', inplace=True)
synergy_map = SynergyMap(compound_df=compound_df,
combination_df=combination_df,
representation_types=representation_types,
reduction_types=reduction_types,
activity_types=activity_types,
synergy_types=synergy_types,
metadata='DREAM Drug Combination Challenge Data')
return synergy_map
def to_dict(self):
"""produce a dict representation of the type
Args:
None
Returns:
dict: A dictionary of the synergy type's name and metadata.
"""
return {"name": self.name, "metadata": self.metadata}
morg2 = RepresentationType(
name='morg2',
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata=
"""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""")
targets = RepresentationType(
name='targets',
representation_func=PIDGIN(),
metadata="""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>."""
)
random = RepresentationType(
name='random',
def make_map():
morg2 = RepresentationType(name='morg2',
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata="""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""")
targets = RepresentationType(name='targets',
representation_func=PIDGIN(),
metadata="""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>.""")
random = RepresentationType(name='random',
representation_func=lambda m: pd.Series(np.random.random(100)),
metadata="""Uniformly distributed random feature vector of length 100"""
"""implemented using <a href="http://www.numpy.org">numpy</a> <a href="http://docs.scipy.org/doc/numpy/reference/generated/numpy.random.random.html#numpy.random.random">random</a> module""")
representation_types = [ morg2, targets, random ]
# reduction types
pca = ReductionMethod(name='PCA',
model=PCA(n_components=2),
metadata="""<a href="http://en.wikipedia.org/wiki/Principal_component_analysis">Principal component analysis</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>\n"""
"""<br/>Default parameters used.""")
mds = ReductionMethod(name='MDS',
model=MDS(),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Multidimensional_scaling" target="_blank">Multidimensional Scaling</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>"""
"""<br/>Default parameters used.""")
tsne = ReductionMethod(name='t-SNE',
model=TSNE(perplexity=10),
metadata=
"""<a href="http://lvdmaaten.github.io/tsne/">Student's t-distributed stochastic neighbour embedding</a>, """
"""implemented according to <a href="http://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf">van der Maartin et al. 2008</a>\n"""
"""<br/>Parameters used: Perplexity = 10, theta=0""")
reduction_types = [ pca, mds, tsne ]
# activity types
pIC50 = ActivityType(name='pIC50', metadata=
"""<a href="http://en.wikipedia.org/wiki/IC50">IC50</a>, the concentation of"""
"""compound required for 50% inhibition of growth of Malarial cells""")
activity_types = [ pIC50 ]
# synergy types
MedianExcess = SynergyType(name='MedianExcess', metadata="")
NumExcess = SynergyType(name='NumExcess', metadata="")
LS3x3 = SynergyType(name='LS3x3', metadata="")
DBSumPos = SynergyType(name='DBSumPos', metadata="")
DBSumNeg = SynergyType(name='DBSumNeg', metadata="")
pGamma = SynergyType(name='pGamma', metadata="")
ExcessHSA = SynergyType(name='-ExcessHSA', metadata="")
ExcessCRX = SynergyType(name='-ExcessCRX', metadata="")
pGamma_scrambled = SynergyType(name='pGamma_scrambled', metadata="")
synergy_types = [ pGamma, MedianExcess, NumExcess, LS3x3, DBSumPos, DBSumNeg, ExcessHSA, ExcessCRX, pGamma_scrambled ]
# data
compound_df = skc.read_sdf('compounds.sdf')
compound_df['name'] = compound_df.Name
compound_df.drop('Name', axis=1, inplace=True)
compound_df['id'] = compound_df.index
compound_df.drop('NCGC_ID', axis=1, inplace=True)
compound_df.set_index('id', inplace=True)
compound_df['pIC50'] = compound_df['pIC50'].apply(float)
compound_df['IC50'] = compound_df.IC50.apply(float)
combination_df = pd.read_csv('combinations.csv')
combination_df.set_index('id', inplace=True)
synergy_map = SynergyMap(compound_df=compound_df,
combination_df=combination_df,
representation_types=representation_types,
reduction_types=reduction_types,
activity_types=activity_types,
synergy_types=synergy_types,
metadata="Malaria NCATS dataset")
return synergy_map
def to_dict(self):
"""produce a dict representation of the type
Args:
None
Returns:
dict: A dictionary of the synergy type's name and metadata.
"""
return {"name": self.name, "metadata": self.metadata}
morg2 = RepresentationType(
name="morg2",
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata="""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""",
)
targets = RepresentationType(
name="targets",
representation_func=PIDGIN(),
metadata="""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>.""",
)
random = RepresentationType(
name="random",
def make_map():
morg2 = RepresentationType(
name='morg2',
representation_func=skchemize(morg, radius=2, nBits=2048),
metadata=
"""Hashed Circular fingerprint generated by the Morgan algorithm, """
"""implemented in <a href="http://www.rdkit.org">RDKit</a>. <br/>"""
"""Parameters used: Radius = 2, Bit length = 2048""")
targets = RepresentationType(
name='targets',
representation_func=PIDGIN(),
metadata=
"""Bayes affinity fingerprint for 1080 human targets, produced """
"""using the <a href="https://github.com/lhm30/PIDGIN">PIDGIN (Prediction of targets IncluDinG INactives)</a>"""
"""Target Prediction algorithm, implemented in <a href="https://github.com/richlewis42/scikit-chem">scikit-chem</a>."""
)
random = RepresentationType(
name='random',
representation_func=lambda m: pd.Series(np.random.random(100)),
metadata="""Uniformly distributed random feature vector of length 100"""
"""implemented using <a href="http://www.numpy.org">numpy</a> <a href="http://docs.scipy.org/doc/numpy/reference/generated/numpy.random.random.html#numpy.random.random">random</a> module"""
)
representation_types = [morg2, targets, random]
# reduction types
pca = ReductionMethod(
name='PCA',
model=PCA(n_components=2),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Principal_component_analysis">Principal component analysis</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>\n"""
"""<br/>Default parameters used.""")
mds = ReductionMethod(
name='MDS',
model=MDS(),
metadata=
"""<a href="http://en.wikipedia.org/wiki/Multidimensional_scaling" target="_blank">Multidimensional Scaling</a> implemented in <a href="http://scikit-learn.org/stable/" target="_blank">scikit-learn</a>"""
"""<br/>Default parameters used.""")
tsne = ReductionMethod(
name='t-SNE',
model=TSNE(perplexity=10),
metadata=
"""<a href="http://lvdmaaten.github.io/tsne/">Student's t-distributed stochastic neighbour embedding</a>, """
"""implemented according to <a href="http://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf">van der Maartin et al. 2008</a>\n"""
"""<br/>Parameters used: Perplexity = 10, theta=0""")
reduction_types = [pca, mds, tsne]
# activity types
pIC50 = ActivityType(
name='pIC50',
metadata=
"""<a href="http://en.wikipedia.org/wiki/IC50">IC50</a>, the concentation of"""
"""compound required for 50% inhibition of growth of Malarial cells""")
activity_types = [pIC50]
# synergy types
MedianExcess = SynergyType(name='MedianExcess', metadata="")
NumExcess = SynergyType(name='NumExcess', metadata="")
LS3x3 = SynergyType(name='LS3x3', metadata="")
DBSumPos = SynergyType(name='DBSumPos', metadata="")
DBSumNeg = SynergyType(name='DBSumNeg', metadata="")
pGamma = SynergyType(name='pGamma', metadata="")
ExcessHSA = SynergyType(name='-ExcessHSA', metadata="")
ExcessCRX = SynergyType(name='-ExcessCRX', metadata="")
pGamma_scrambled = SynergyType(name='pGamma_scrambled', metadata="")
synergy_types = [
pGamma, MedianExcess, NumExcess, LS3x3, DBSumPos, DBSumNeg, ExcessHSA,
ExcessCRX, pGamma_scrambled
]
# data
compound_df = skc.read_sdf('compounds.sdf')
compound_df['name'] = compound_df.Name
compound_df.drop('Name', axis=1, inplace=True)
compound_df['id'] = compound_df.index
compound_df.drop('NCGC_ID', axis=1, inplace=True)
compound_df.set_index('id', inplace=True)
compound_df['pIC50'] = compound_df['pIC50'].apply(float)
compound_df['IC50'] = compound_df.IC50.apply(float)
combination_df = pd.read_csv('combinations.csv')
combination_df.set_index('id', inplace=True)
synergy_map = SynergyMap(compound_df=compound_df,
combination_df=combination_df,
representation_types=representation_types,
reduction_types=reduction_types,
activity_types=activity_types,
synergy_types=synergy_types,
metadata="Malaria NCATS dataset")
return synergy_map
