mmtfPyspark.datasets.jpredDataset module

jpredDataset.py

This class downloads the dataset used to train the secondary structure predictor. It can be used as a reference dataset for machine learning applications.

This dataset includes the ScopID, sequence, DSSP secondary structure assignment, and a flag that indicates if data point was part of the training set.

References

get_dataset()[source]

Gets JPred 4/JNet (v.2.3.1) secondary structure dataset.

Returns:

dataset

secondaryStructure dataset