In [1]:
from pyspark import SparkConf, SparkContext
from mmtfPyspark.io import mmtfReader
from mmtfPyspark.filters import DepositionDate
from mmtfPyspark.structureViewer import view_structure
In [2]:
conf = SparkConf().setMaster("local[*]") \
.setAppName("FilterByDepositionDate")
sc = SparkContext(conf = conf)
In [3]:
path = "../../resources/mmtf_reduced_sample/"
pdb = mmtfReader.read_sequence_file(path, sc)
In [4]:
pdb = pdb.filter(DepositionDate('1999-02-26','1999-02-28'))
In [5]:
count = pdb.count()
print(f"Number of structure desposited between 1999-02-26 and 1999-02-28 is : {count}")
Number of structure desposited between 1999-02-26 and 1999-02-28 is : 5
In [6]:
pdbIds = pdb.keys().collect()
view_structure(pdbIds)
Out[6]:
<function mmtfPyspark.structureViewer.view_structure.<locals>.view3d>
In [7]:
sc.stop()