Simple example reading PDB entries from local Hadoop Sequence Files
In [1]:
from pyspark import SparkConf, SparkContext
from mmtfPyspark.io import mmtfReader
from mmtfPyspark.structureViewer import view_structure
In [2]:
conf = SparkConf().setMaster("local[*]") \
.setAppName("ReadLocalMMTFReduced")
sc = SparkContext(conf = conf)
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}')
number of pdb entries read : 5395
In [ ]:
## Visualize Structures
In [5]:
structures = pdb.keys().collect()
view_structure(structures, style = 'sphere')
Out[5]:
<function mmtfPyspark.structureViewer.view_structure.<locals>.view3d>
In [6]:
sc.stop()