# In[2]:
conf = SparkConf().setMaster("local[*]").setAppName("FilterByReleaseDate")
sc = SparkContext(conf=conf)
# ## Read in MMTF Files, filter and count
# In[3]:
path = "../../resources/mmtf_reduced_sample/"
structures = mmtfReader.read_sequence_file(path, sc).filter(
ReleaseDate("2000-01-28", "2017-02-28"))
print(
f"Number of structure released between 2000-01-28 and 2017-02-28 is: {structures.count()}"
)
# ## Visualize Structures
# In[4]:
structure_names = structures.keys().collect()
view_structure(structure_names, style='line')
# ## Terminate Spark
# In[5]:
sc.stop()
# ## Filter proteins that cotinas Dna chain and L protein chain
#
# 1) Retain pdb entires that exclusively contain L-peptide chains
# 2) Retain pdb entries that exclusively contain L-Dna
# In[4]:
structures = pdb.filter(ContainsLProteinChain()).filter(ContainsDnaChain())
# ## Count number of entires
# In[5]:
count = structures.count()
print(f"Number of entires that contain L-protein and L-DNA: {count}")
# ## Visualize Structures
# In[7]:
structure_names = structures.keys().collect()
view_structure(structure_names)
# ## Terminate Spark
# In[6]:
sc.stop()
# * ExperimentalMethods.SOLUTION_NMR
# * ExperimentalMethods.SOLUTION_SCATTERING
# * ExperimentalMethods.THEORETICAL_MODEL
# * ExperimentalMethods.X_RAY_DIFFRACTION
# In[4]:
pdb = pdb.filter(
ExperimentalMethods(ExperimentalMethods.NEUTRON_DIFFRACTION,
ExperimentalMethods.X_RAY_DIFFRACTION))
# ## Print out entries
# In[5]:
filtered_structures = pdb.keys().collect()
print(filtered_structures)
# ## Visualize 3D structures of filtered structures
# In[6]:
view_structure(filtered_structures)
# ## Terminate Spark
# In[7]:
sc.stop()
structures = structures.filter(NotFilter(ContainsDnaChain()))
# ## Count number of entires
# In[10]:
count = structures.count()
print(f"PDB entires without DNA chains : {count}")
# ## Visualize Structures
# In[11]:
view_structure(structures.keys().collect())
# ## Terminate Spark
# In[7]:
sc.stop()
conf = SparkConf().setMaster("local[*]").setAppName("ReadLocalMMTFReduced")
sc = SparkContext(conf=conf)
# ## Read in local Hadoop Sequence Files and count number of entries
# In[3]:
path = "../../resources/mmtf_reduced_sample/"
pdb = mmtfReader.read_sequence_file(path, sc)
count = pdb.count()
print(f'number of pdb entries read : {count}')
# In[ ]:
## Visualize Structures
# In[5]:
structures = pdb.keys().collect()
view_structure(structures, style='sphere')
# ## Terminate Spark
# In[6]:
sc.stop()
# ## Retain high resolution X-ray structures
# In[4]:
pdb = pdb.filter(ExperimentalMethods(
ExperimentalMethods.X_RAY_DIFFRACTION)).filter(Resolution(0, 2.0)).filter(
RFree(0, 2.0))
print(f'number of pdb entries left : {pdb.count()}')
# ## Visualize Structures
# In[5]:
structures = pdb.keys().collect()
view_structure(structures)
# ## Save this subset in a Hadoop Sequence File
# In[7]:
write_path = "./mmtf_subset_xray"
# Reduce RDD to 8 partitiions
pdb = pdb.coalesce(8)
mmtfWriter.write_sequence_file(write_path, sc, pdb)
# ## Terminate Spark
# In[8]:
path = "../../resources/mmtf_full_sample/"
fraction = 0.5
seed = 123
pdb = mmtfReader.read_sequence_file(path, sc, fraction=fraction, seed=seed)
count = pdb.count()
print(f'number of pdb entries read : {count}')
# ## Visualize Structures
# In[5]:
structures = pdb.keys().collect()
view_structure(structures, style='stick')
# ## Save this subset in a Hadoop Sequence File
# In[4]:
write_path = "./mmtf_subset"
mmtfWriter.write_sequence_file(write_path, sc, pdb)
# ## Terminate Spark
# In[5]:
sc.stop()
# ## Filter by deposition date
# In[4]:
pdb = pdb.filter(DepositionDate('1999-02-26', '1999-02-28'))
# ## Count number of entires
# In[5]:
count = pdb.count()
print(
f"Number of structure desposited between 1999-02-26 and 1999-02-28 is : {count}"
)
# ## View 3D structures
# In[6]:
pdbIds = pdb.keys().collect()
view_structure(pdbIds)
# ## Terminate Spark
# In[7]:
sc.stop()