def test1(self):
pdb_1 = self.pdb.filter(Pisces(20, 2.0))
results_1 = pdb_1.keys().collect()
self.assertTrue('5X42' in results_1)
self.assertTrue('4R4X' in results_1)
self.assertFalse('2ONX' in results_1)
self.assertFalse('1JLP' in results_1)
def test2(self):
pdb_2 = self.pdb.flatMap(StructureToPolymerChains())
pdb_2 = pdb_2.filter(Pisces(20, 2.0))
results_2 = pdb_2.keys().collect()
self.assertTrue('5X42.B' in results_2)
self.assertTrue('4R4X.A' in results_2)
self.assertFalse('5X42.A' in results_2)
self.assertFalse('2ONX.A' in results_2)
self.assertFalse('1JLP.A' in results_2)
# Create variables
APP_NAME = "MMTF_Spark"
path = "../../resources/mmtf_full_sample/"
# Configure Spark
conf = SparkConf().setAppName(APP_NAME).setMaster("local[*]")
sc = SparkContext(conf=conf)
# ## Read PDB and create PISCES non-redundant set
# In[14]:
pdb = mmtfReader.read_sequence_file(path, sc)
pdb = pdb.filter(Pisces(sequenceIdentity = 30, resolution = 2.5))
# ## Setup criteria for metal interactions
# In[15]:
# Chemical component codes of metals in different oxidation states
metals = {"V","CR","MN","MN3","FE","FE2","CO","3CO","NI","3NI", "CU","CU1","CU3","ZN","MO","4MO","6MO"}
interactions_filter = InteractionFilter(distanceCutoff = 3.0, minInteractions=4, maxInteractions=6)
interactions_filter.set_query_groups(True, metals)
# Exclude non-polar interactions
interactions_filter.set_target_elements(False, ['H','C','P'])
# ## Read MMTF Hadoop sequence file and
#
# Create a non-redundant set(<=20% seq. identity) of L-protein chains
# In[3]:
path = "../../resources/mmtf_reduced_sample/"
sequenceIdentity = 20
resolution = 2.0
fraction = 0.1
seed = 123
pdb = mmtfReader.read_sequence_file(
path, sc).flatMap(StructureToPolymerChains()).filter(
Pisces(sequenceIdentity,
resolution)).filter(ContainsLProteinChain()).sample(
False, fraction, seed)
# ## Get content
# In[4]:
segmentLength = 11
data = secondaryStructureSegmentExtractor.get_dataset(pdb,
segmentLength).cache()
print(f"original data : {data.count()}")
# ## Drop Q3 and sequence duplicates
# In[5]:
path = "../../resources/mmtf_full_sample/" pdb = mmtfReader.read_sequence_file(path, sc) # ## Filter by representative protein chains at 40% sequence identity # In[7]: sequenceIdentity = 40 resolution = 2.0 pdb = pdb.filter(Pisces(sequenceIdentity, resolution)) .flatMap(StructureToPolymerChains()) .filter(Pisces(sequenceIdentity, resolution)) .filter(PolymerComposition(PolymerComposition.AMINO_ACIDS_20)) # ## Show top 10 structures # In[8]: pdb.top(10) # ## Save representative set # In[9]:
# ## Read MMTF Hadoop sequence file and
#
# Create a non-redundant set(<=20% seq. identity) of L-protein chains
# In[3]:
path = "../../resources/mmtf_reduced_sample/"
sequenceIdentity = 20
resolution = 2.0
fraction = 0.1
seed = 123
pdb = mmtfReader .read_sequence_file(path, sc) .flatMap(StructureToPolymerChains()) .filter(Pisces(sequenceIdentity, resolution)) .filter(ContainsLProteinChain()) .sample(False, fraction, seed)
# ## Get content
# In[4]:
segmentLength = 11
data = secondaryStructureSegmentExtractor.get_dataset(pdb, segmentLength).cache()
print(f"original data : {data.count()}")
# ## Drop Q3 and sequence duplicates
# In[5]:
# ## Configure Spark Context
# In[18]:
conf = SparkConf().setMaster("local[*]").setAppName("MachineLearningDemo")
sc = SparkContext(conf=conf)
# ## Read MMTF File and create a non-redundant set (<=40% seq. identity) of L-protein clains
# In[19]:
pdb = mmtfReader.read_sequence_file('../../resources/mmtf_reduced_sample/',
sc).flatMap(
StructureToPolymerChains()).filter(
Pisces(sequenceIdentity=40,
resolution=3.0))
# ## Get secondary structure content
# In[20]:
data = secondaryStructureExtractor.get_dataset(pdb)
# ## Define addProteinFoldType function
# In[21]:
def add_protein_fold_type(data, minThreshold, maxThreshold):
'''
Adds a column "foldType" with three major secondary structure class:
"ProteinFoldDatasetCreatorDemo")
sc = SparkContext(conf=conf)
# ## Read MMTF Hadoop sequence file
#
# Create non-redundant set (<=40% seq. identity) if L-protein chains
# In[15]:
path = "../../resources/mmtf_reduced_sample/"
sequenceIdentity = 40
resolution = 2.0
pdb = mmtfReader.read_sequence_file(path, sc).filter(
Pisces(sequenceIdentity,
resolution)).flatMap(StructureToPolymerChains()).filter(
Pisces(sequenceIdentity,
resolution)).filter(ContainsLProteinChain())
# ## Get secondary structure content
# In[16]:
data = secondaryStructureExtractor.get_dataset(pdb)
# ## Classify chains by secondary structure type
# In[17]:
minThreshold = 0.05
maxThreshold = 0.15
resolution = 2.5
minInteractions = 4
maxInteractions = 6
distanceCutoff = 3.0
# chemical component codes of metals in different oxidation states
metals = {"V","CR","MN","MN3","FE","FE2","CO","3CO","NI","3NI", "CU","CU1","CU3","ZN","MO","4MO","6MO"}
# ## Read PDB and create PISCES non-redundant set
# In[12]:
pdb = mmtfReader.read_sequence_file(path, sc)
pdb = pdb.filter(Pisces(sequenceIdentity = sequenceIdentityCutoff, resolution = resolution))
# ## Setup criteria for metal interactions
# In[13]:
interactions_filter = InteractionFilter()
interactions_filter.set_distance_cutoff(distanceCutoff)
interactions_filter.set_min_interactions(minInteractions)
interactions_filter.set_max_interactions(maxInteractions)
interactions_filter.set_query_groups(True, metals)
#Exclude non-polar interactions
interactions_filter.set_target_elements(False, ['H','C','P'])
# ## Read PDB in MMTF format
# In[3]:
path = "../../resources/mmtf_full_sample/"
pdb = mmtfReader.read_sequence_file(path, sc)
# # Use only representative structures
# In[4]:
seqId = 40
resolution = 2.0
pdb = pdb.filter(Pisces(seqId, resolution))
# ## Extract proteins with Zn interactions
# In[5]:
finder = groupInteractionExtractor("ZN", 3)
interactions = finder.get_dataset(pdb).cache()
# ## List the top 10 residue types that interact with Zn
# In[6]:
interactions.printSchema()