Why SpliceAI-toolkit❓#

1. Easy-to-retrain framework: Transitioning from the outdated Python 2.7, along with older versions of TensorFlow and Keras, the SpliceAI-toolkit is built on Python 3.7 and leverages the powerful PyTorch library. This simplifies the retraining process significantly. Say goodbye to compatibility issues and hello to efficiency — retrain your models with just two simple commands.

2. Pretrained on new dataset: SpliceAI is great, but SpliceAI-toolkit makes it even better! Pretrained with the latest MANE annotations (released in 2022), it ensures your research is powered by the most accurate and up-to-date genomic information available.

3. Pretrained on various species: Concerned that the SpliceAI model does not generalize to your study species because you are not studying humans? No problem! The SpliceAI-toolkit is released with models pretrained on various species, including human MANE, mouse, thale cress, honey bee, and zebrafish.

4. Predict the impact of genetic variants on splicing: Similar to SpliceAI, the SpliceAI-toolkit can take genetic variants in VCF format and predict the impact of these variants on splicing with any of the pretrained models.

SpliceAI-toolkit is open-source, free, and combines the ease of Python with the power of PyTorch for accurate splicing predictions.

Who is it for❓#

1. If you want to study splicing in humans, just use the newly pretrained human SpliceAI-MANE! Better annotation, better results!

2. If you want to do splicing research in other species, the SpliceAI-toolkit has you covered! It comes with models pretrained on various species! And you can easily train your own SpliceAI with your own genome & annotation data.

3. If you are interested in predicting the impact of genetic variants on splicing, SpliceAI-toolkit is the perfect tool for you!

What does SpliceAI-toolkit do❓#

• The spliceai-toolkit create-data command takes a genome and annotation file as input and generates a dataset for training and testing your SpliceAI model.

• The spliceai-toolkit train command uses the created dataset to train your own SpliceAI model.

• The spliceai-toolkit predict command takes a random gene sequence and predicts the score of each position, determining whether it is a donor, acceptor, or neither.

• The spliceai-toolkit variant command takes a VCF file and predicts the impact of genetic variants on splicing.

Cite us#

Chao, Kua-Hao, Alan Mao, Anqi Liu, Mihaela Pertea, and Steven L. Salzberg. "SpliceAI-toolkit" bioRxiv.

Jaganathan, K., Panagiotopoulou, S.K., McRae, J.F., Darbandi, S.F., Knowles, D., Li, Y.I., Kosmicki, J.A., Arbelaez, J., Cui, W., Schwartz, G.B. and Chow, E.D."Predicting splicing from primary sequence with deep learning" Cell.

User support#

Please go through the documentation below first. If you have questions about using the package, a bug report, or a feature request, please use the GitHub issue tracker here:

https://github.com/Kuanhao-Chao/spliceAI-toolkit/issues

Key contributors#

SpliceAI-toolkit was designed and developed by Kuan-Hao Chao. This documentation was written by Kuan-Hao Chao. The LiftOn logo was designed by Kuan-Hao Chao.

Table of contents#