v0.3.0-alpha

New feature added:

1. Now users can supply bed file to trainNN/predict_bed.py to predict TF binding in regions they want

Full Changelog: v0.2.1...v0.3.0

v0.2.1

Several bug fixes:

1. Fix the bug that regions with negative start coordinates were included in the training set
2. Set shuffle as False when predicting the test dataset by scan_genome.py
3. Fix the bug that the remainder of test dataset was dropped due to the drop_remainder behavior of tensorflow dataset loading.

Full Changelog: v0.2.0...v0.2.1

v0.2.0

Changes:

1. New training sample prep strategy
   • For sequence network, a training set with equal size of positive and negative samples will be generated, positive samples are shifted chip-seq peaks augmented 5x by sampling with replacement, negative samples consist of flanking unbound/random unbound sites, the ratio of samples overlapped with ATAC-seq peaks is the same for pos/neg sets.
   • For bichrom network, positive samples are kept the same, negative samples are replaced with random unbound sites across the genome.
2. Train/Val/Test datasets are saved in TFRecord format now to speed up loading
3. MirroredStrategy has been employed to support multi-GPU training
4. Some bugs fixed

Full Changelog: v0.1.1...v0.2.0

v0.1.2

Adding a new release for Zenodo integration

v0.1.1

First release to support publication

• Minor bug fixes
• Updated documentation

v0.1.0

• First pre-release.
• Apply a bimodal additive network (Bichrom) to predict transcription factor binding using DNA sequence and chromatin track data.