def test6(self):
pdb_6 = self.pdb.flatMap(StructureToPolymerChains())
pdb_6 = pdb_6.filter(SecondaryStructure(
0.70, 0.75, 0.00, 0.40, 0.25, 0.50))
results_6 = pdb_6.keys().collect()
self.assertTrue('2C7M.A' in results_6)
self.assertFalse('2C7M.B' in results_6)
def test1(self):
pdb = self.pdb.filter(ContainsLProteinChain()) \
.flatMap(StructureToPolymerChains()) \
.filter(ContainsLProteinChain())
seq = secondaryStructureExtractor.get_dataset(pdb)
self.assertTrue(seq.count() == 5)
def test2(self):
pdb_2 = self.pdb.filter(BlastCluster(40))
pdb_2 = pdb_2.flatMap(StructureToPolymerChains())
results_2 = pdb_2.keys().collect()
self.assertFalse('1O06' in results_2)
self.assertTrue('1O06.A' in results_2)
self.assertFalse('2ONX' in results_2)
def test1(self):
pdb = self.pdb.flatMap(StructureToPolymerChains())
secStruct = secondaryStructureExtractor.get_dataset(pdb)
dsspQ8 = secStruct.first()["dsspQ8Code"]
dsspQ3 = secStruct.first()["dsspQ3Code"]
self.assertTrue(len(dsspQ8.split('X')) - 1 == 38) # 'X' appears 38 times
self.assertTrue(len(dsspQ8.split('C')) - 1 == 24) # 'C' appears 24 times
self.assertTrue(len(dsspQ3.split('C')) - 1 == 44) # 'C' appears 44 times
def test3(self):
sql = "SELECT e.pdbid, e.chain FROM sifts.pdb_chain_enzyme AS e WHERE e.ec_number = '2.7.11.1'"
pdb = self.pdb.flatMap(StructureToPolymerChains()) \
.filter(PdbjMineSearch(sql))
matches = pdb.keys().collect()
self.assertTrue("5JDE.A" in matches)
self.assertTrue("5JDE.B" in matches)
self.assertTrue("5CU4.A" in matches)
self.assertTrue("5L6W.L" in matches)
self.assertFalse("5L6W.C" in matches)
self.assertTrue("5UFU.A" in matches)
self.assertFalse("5UFU.B" in matches)
self.assertFalse("5UFU.C" in matches)
self.assertFalse("5IHB.A" in matches)
self.assertFalse("5IHB.B" in matches)
self.assertFalse("5IHB.C" in matches)
self.assertFalse("5IHB.D" in matches)
def test3(self):
sql = "select distinct concat(entity_poly.pdbid, '.', unnest(string_to_array(entity_poly.pdbx_strand_id, ','))) as \"structureChainId\" from entity_poly join entity_src_gen on entity_src_gen.pdbid=entity_poly.pdbid and entity_poly.entity_id=entity_poly.entity_id join entity on entity.pdbid=entity_poly.pdbid and entity.id=entity_poly.entity_id where pdbx_ec='2.7.11.1' and pdbx_gene_src_scientific_name='H**o sapiens'"
pdb = self.pdb.flatMap(StructureToPolymerChains()) \
.filter(PdbjMine(sql, pdbidField="structureChainId", chainLevel=True))
matches = pdb.keys().collect()
self.assertTrue("5JDE.A" in matches)
self.assertTrue("5JDE.B" in matches)
self.assertTrue("5CU4.A" in matches)
self.assertTrue("5L6W.L" in matches)
self.assertFalse("5L6W.C" in matches)
self.assertFalse("5UFU.A" in matches)
self.assertFalse("5UFU.B" in matches)
self.assertFalse("5UFU.C" in matches)
self.assertFalse("5IHB.A" in matches)
self.assertFalse("5IHB.B" in matches)
self.assertFalse("5IHB.C" in matches)
self.assertFalse("5IHB.D" in matches)
def test2(self):
# This test runs a chain elvel query and compares chain level results
pdb_2 = self.pdb.flatMap(StructureToPolymerChains())
whereClause = "WHERE ecNo='2.7.11.1' AND source='H**o sapiens'"
fields = ["ecNo", "source"]
pdb_2 = pdb_2.filter(CustomReportQuery(whereClause, fields))
results_2 = pdb_2.keys().collect()
self.assertTrue('5JDE.A' in results_2)
self.assertTrue('5JDE.B' in results_2)
self.assertTrue('5CU4.A' in results_2)
self.assertTrue('5L6W.L' in results_2)
self.assertFalse('5L6W.C' in results_2)
self.assertFalse('5UFU.A' in results_2)
self.assertFalse('5UFU.B' in results_2)
self.assertFalse('5UFU.C' in results_2)
self.assertFalse('5IHB.A' in results_2)
self.assertFalse('5IHB.B' in results_2)
self.assertFalse('5IHB.C' in results_2)
self.assertFalse('5IHB.D' in results_2)
def test4(self):
query = "<orgPdbQuery>" + \
"<queryType>org.pdb.query.simple.EnzymeClassificationQuery</queryType>" + \
"<Enzyme_Classification>2.7.11.1</Enzyme_Classification>" + \
"</orgPdbQuery>"
pdb_4 = self.pdb.flatMap(StructureToPolymerChains()) \
.filter(AdvancedQuery(query))
results_4 = pdb_4.keys().collect()
self.assertFalse('1PEN.A' in results_4)
self.assertFalse('1OCZ.A' in results_4)
self.assertFalse('2ONX.A' in results_4)
self.assertTrue('5L6W.L' in results_4)
self.assertFalse('5L6W.C' in results_4)
self.assertFalse('5KHU.A' in results_4)
self.assertFalse('5KHU.B' in results_4)
self.assertTrue('5KHU.Q' in results_4)
self.assertTrue('1F3M.A' in results_4)
self.assertTrue('1F3M.B' in results_4)
self.assertTrue('1F3M.C' in results_4)
self.assertTrue('1F3M.D' in results_4)
# ## 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]:
def test1(self):
pdb_1 = self.pdb.flatMap(StructureToPolymerChains())
results_1 = pdb_1.keys().collect()
self.assertTrue(len(results_1) == 10)
path = "../../resources/mmtf_reduced_sample/"
pdb = mmtfReader.read_sequence_file(path, sc)
# ## flat map structure to polymer chains, filter by polymer composition and count
#
# ### Supported polymer composition type:
#
# ** polymerComposition.AMINO_ACIDS_20 **= ["ALA","ARG","ASN","ASP","CYS","GLN","GLU","GLY","HIS","ILE","LEU","LYS","MET","PHE","PRO","SER","THR","TRP","TYR","VAL"]
#
# ** polymerComposition.AMINO_ACIDS_22 **= ["ALA","ARG","ASN","ASP","CYS","GLN","GLU","GLY","HIS","ILE","LEU","LYS","MET","PHE","PRO","SER","THR","TRP","TYR","VAL","SEC","PYL"]
#
# ** polymerComposition.DNA_STD_NUCLEOTIDES **= ["DA","DC","DG","DT"]
#
# ** polymerComposition.RNA_STD_NUCLEOTIDES **= ["A","C","G","U"]
#
# In[4]:
count = pdb.flatMap(StructureToPolymerChains(False, True)).filter(
PolymerComposition(PolymerComposition.AMINO_ACIDS_20)).count()
print(f"Chains with standard amino acids: {count}")
# ## Terminate Spark
# In[5]:
sc.stop()
"SecondaryStructureElementsWord2VecEncoderDemo")
sc = SparkContext(conf=conf)
# ## 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/"
fraction = 0.05
seed = 123
pdb = mmtfReader.read_sequence_file(path, sc).flatMap(
StructureToPolymerChains(False,
True)).filter(ContainsLProteinChain()).sample(
False, fraction, seed)
# ## Extract Element "H" from Secondary Structure
# In[4]:
label = "H"
data = secondaryStructureElementExtractor.get_dataset(pdb, label).cache()
print(f"original data : {data.count()}")
data.show(10, False)
# ## Word2Vec encoded feature Vector
# In[6]:
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
def test1(self):
pdb = self.pdb.flatMap(StructureToPolymerChains())
seq = polymerSequenceExtractor.get_dataset(pdb)
self.assertTrue(seq.count() == 5)
conf = SparkConf().setMaster("local[*]").setAppName("DSSPDemo")
sc = SparkContext(conf=conf)
# ## Download single protein (1STP)
# In[11]:
pdbIds = ["1STP"]
pdb = mmtfReader.download_mmtf_files(pdbIds, sc).cache()
# ## Flatmap to polymer chains
# In[12]:
pdb = pdb.flatMap(StructureToPolymerChains())
# ## Extract Secondary Structures
# In[13]:
ds = secondaryStructureExtractor.get_dataset(pdb)
ds.printSchema()
ds.show(2, False)
# ## Terminate Spark
# In[14]:
sc.stop()
sc = SparkContext(conf=conf)
# ## 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
"secondaryStructureElementDemo") sc = SparkContext(conf=conf) # ## Download protein (1STP) # # ### Note: Need to use SparkContext as parameter to download Mmtf files # In[12]: pdb = mmtfReader.download_mmtf_files(['1STP'], sc).cache() # ## Map protein to polymer chains and apply LProteinChain filter # In[13]: pdb = pdb.flatMap(StructureToPolymerChains()).filter(ContainsLProteinChain()) # ## Extract secondary structure element 'E' # In[14]: ds = secondaryStructureElementExtractor.get_dataset(pdb, 'E', 6) ds.show(50, False) # ## Terminate Spark # In[15]: sc.stop()
def test1(self):
pdb = self.pdb.flatMap(StructureToPolymerChains())
seq = secondaryStructureSegmentExtractor.get_dataset(pdb, 25)
self.assertTrue("DPSKDSKAQVSAAEAGITGTWYNQL" == seq.head()[1])
# ## Configure Spark
# In[2]:
conf = SparkConf().setMaster("local[*]").setAppName("polypeptideCahinStats")
sc = SparkContext(conf=conf)
# ## Read in mmtf files, flatMap to polymer chains, filter by polymer composition, and get number of groups
# In[4]:
path = "../../resources/mmtf_full_sample/"
chainLengths = mmtfReader.read_sequence_file(path, sc).flatMap(
StructureToPolymerChains(False, True)).filter(
PolymerComposition(PolymerComposition.AMINO_ACIDS_20)).map(
lambda t: t[1].num_groups).cache()
# ## Print out poly-peptide chain statistics
# In[5]:
print(f"Total number of chains: {chainLengths.count()}")
print(f"Total number of groups: {chainLengths.sum()}")
print(f"Min chain length: {chainLengths.min()}")
print(f"Mean chain length: {chainLengths.mean()}")
print(f"Max chain length: {chainLengths.max()}")
# ## Terminate Spark
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]:
# ## Configure Spark Context
# In[2]:
conf = SparkConf().setMaster("local[*]").setAppName(
"SequenceSimilaritySearchDemo")
sc = SparkContext(conf=conf)
# ## Read PDB in MMTF format, split into polymer chain, search by sequence similarity, and print sequence found
# In[6]:
path = "../../resources/mmtf_reduced_sample/"
pdb = mmtfReader.read_sequence_file(path, sc).flatMap(
StructureToPolymerChains()).filter(
SequenceSimilarity(sequence="NLVQFGVMIEKMTGKSALQYNDYGCYCGIGGSHWPVDQ",
searchTool=SequenceSimilarity.BLAST,
eValueCutoff=0.001,
sequenceIdentityCutoff=40,
maskLowComplexity=True)).collect()
for pdbId, structure in pdb:
print(f"{pdbId} : {structure.entity_list[0]['sequence']}")
# ## Terminate Spark Context
# In[7]:
sc.stop()
# ## Configure Spark Context
# In[3]:
conf = SparkConf().setMaster("local[*]").setAppName("KinaseDemo")
sc = SparkContext(conf=conf)
# ## Query for human protein-serine/threonine kinases using SIFTS data
# In[4]:
sql = "SELECT t.pdbid, t.chain FROM sifts.pdb_chain_taxonomy AS t " + "JOIN sifts.pdb_chain_enzyme AS e ON (t.pdbid = e.pdbid AND t.chain = e.chain) " + "WHERE t.scientific_name = 'H**o sapiens' AND e.ec_number = '2.7.11.1'"
# ## Read PDB and filter by author
# In[6]:
path = "../../resources/mmtf_reduced_sample/"
pdb = mmtfReader.read_sequence_file(path, sc).flatMap(
StructureToPolymerChains()).filter(PdbjMineSearch(sql))
print(f"Number of entries matching query: {pdb.count()}")
# ## Terminate Spark Context
# In[7]:
sc.stop()