rnaglib.splitters

Splitter objects compute a train, validation, and test split for a given dataset.

Abstract classes

Subclass these to create your own tasks.

Splitter([split_train, split_valid, split_test])

ClusterSplitter([similarity_threshold, ...])

Abstract class for splitting by clustering with a similarity function

Splitters

RandomSplitter([seed])

" Just split a dataset randomly.

RNAalignSplitter(structures_dir[, seed, ...])

Splits based on structural similarity using RNAalign.

CDHitSplitter([similarity_threshold, ...])

Splits based on sequence similarity using CDHit.