keras-biological-gaps-sequence 1.0.0

Python package to generate on-hot encoded biological gaps to use for training and prediction.

Python package to generate on-hot encoded biological gaps to use for training and prediction.

How do I install this package?

As usual, just download it using pip:

pip install keras_biological_gaps_sequences

Tests Coverage

Since some software handling coverages sometimes get slightly different results, here’s three of them:

Available datasets

Currently, there is only a dataset of gaps available within the package: the mapping of known gaps from hg19 to hg38. In the future, we will be adding more mapping.

Usage example

To use the sequence you can do as follows:

biological_gap_sequence = BiologicalGapsSequence(
    source="hg19",
    target="hg38",
    source_window_size=1000,
    target_window_size=1000,
    batch_size=32
)

model = build_my_denoiser()
model.fit_generator(
    biological_gap_sequence,
    steps_per_epoch=biological_gap_sequence.steps_per_epoch,
    epochs=2,
    shuffle=True
)