def get_dataset(structure, label, length=None):
'''Returns a dataset of continuous segments of protein sequence with the
specified DSSP secondary structure code (E, H, C) of a minimum length.
Attributes
----------
structure: structure data
label (char): DSSP secondary structure label (E, H, C)
length (int): minimum length of secondary structure segment
Returns
-------
dataset of continuous segments of protein sequence
'''
colNames = ["sequence", "label"]
if length == None:
rows = secondaryStructureExtractor.get_python_rdd(structure) \
.flatMap(StructureToSecondaryStructureElements(label))
return pythonRDDToDataset.get_dataset(rows, colNames)
else:
rows = secondaryStructureExtractor.get_python_rdd(structure) \
.flatMap(StructureToSecondaryStructureElements(label, length))
return pythonRDDToDataset.get_dataset(rows, colNames)
def get_dataset(structureRDD, length):
'''Returns a dataset of sequence segments of the specified length and
the DSSP Q8 and Q3 code of the center residue in a segment.
Parameters
----------
structureRDD : structure
length : int
segment length, must be an odd number
Returns
-------
dataset
dataset of segments
Raises
------
Exception
Segment length must be an odd number
'''
if length % 2 == 0:
raise Exception("Segment length must be an odd number %i" % length)
rows = secondaryStructureExtractor.get_python_rdd(structureRDD) \
.flatMap(StructureToSecondaryStructureSegments(length))
colNames = ["structureChainId", "sequence", "labelQ8", "labelQ3"]
return pythonRDDToDataset.get_dataset(rows, colNames)