Thank you so much Ben. I’m deeply grateful for your mentorship; you’ve shaped how I think and do science. I hope we get to collaborate again soon!

It’s happening today! Thrilled to share my PhD journey with friends and colleagues—thank you all for being part of it!

Dive into the full thread here 👇

@jhucompsci.bsky.social @hopkinsengineer.bsky.social

A huge thank you to my advisors, Mihaela Pertea and @stevensalzberg.bsky.social for their invaluable mentorship and support. Special shoutout to collaborators and friends Anqi Liu and Alan Mao at Hopkins — this project wouldn’t be possible without you! 11/

OpenSpliceAI offers researchers a comprehensive suite of tools for studying transcript splicing—from creating training datasets and training models to predicting splice sites and assessing the impact of genetic variants.
🔗 Explore our documentation here: ccb.jhu.edu/openspliceai/ 10/

We showed general patterns of donor and acceptor sites across hundreds of splice site motifs learned by OpenSpliceAI. Moreover, it confidently predicts cryptic splicing events—such as acceptor gain in MYBPC3 and novel exon gain in OPA1. 9/

In silico mutagenesis (ISM) confirms that OpenSpliceAI focuses on the same key regions and patterns for splice site prediction at U2SURP and DST as SpliceAI, and effectively capturing a splicing enhancer. We also demonstrate its ability to capture the full gene span of CFTR. 8/

We enhanced model reliability by applying temperature scaling for calibration. Using expected calibration error and reliability diagrams, we observed a smoother probability distribution that aligns more closely with the empirical distribution, making it better! 7/

OpenSpliceAI also supports transfer learning. Our experiments show that models pre-trained on human and applied to species of interest achieve near-optimal performance in just one epoch, drastically reducing compute time while enhancing predictions for species with smaller genomes 6/

Comparing species-specific training versus running SpliceAI directly, our results confirm that one-size-fits-all generalization isn’t enough. OpenSpliceAI’s ability to retrain on specific species sets it apart from SpliceAI. 5/

Our benchmarks show that OpenSpliceAI outperforms SpliceAI in elapsed time, memory usage, and GPU peak memory across various gene lengths. Thanks to dynamic PyTorch graphs, batch prediction, and optimized engineering, full-chromosome predictions are now a reality! 4/

Built with six modular components, OpenSpliceAI lets you:

• Create species-specific datasets
• Train custom models
• Calibrate predictions
• Apply transfer learning from human models
• Predict on genes / entire chromosomes
• Assess variant impacts on cryptic splicing
3/

We’re introducing OpenSpliceAI along with a suite of pre-trained models for Human-MANE, mouse, zebrafish, honeybee, and Arabidopsis. OpenSpliceAI provides a user‐friendly toolkit for studying transcript splicing in any species of interest! 2/

🔗 GitHub: github.com/Kuanhao-Chao...