Releases: seqcode/Bichrom
Releases · seqcode/Bichrom
v0.3.0-alpha
New feature added:
- 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:
- Fix the bug that regions with negative start coordinates were included in the training set
- Set shuffle as False when predicting the test dataset by scan_genome.py
- 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:
- 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.
- Train/Val/Test datasets are saved in TFRecord format now to speed up loading
- MirroredStrategy has been employed to support multi-GPU training
- 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.