Simple example reading a list of 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("ReadListFromLocal")
sc = SparkContext(conf = conf)
In [3]:
path = "../../resources/mmtf_full_sample/"
pdbIds = ["1M4L", "1LXJ", "4XPX"]
pdb = mmtfReader.read_sequence_file(path, sc, pdbId = pdbIds,)
count = pdb.count()
print(f'number of pdb entries read : {count}')
number of pdb entries read : 3
In [4]:
structures = pdb.keys().collect()
view_structure(structures)
Out[4]:
<function mmtfPyspark.structureViewer.view_structure.<locals>.view3d(i=0)>
In [5]:
sc.stop()