Back

Bisbee: A proteomics validated analysis package for detecting differential splicing, identifying splice outliers, and predicting splice event protein effects

Halperin, R. F.; Hedge, A.; Lang, J. D.; Raupach, E. A.; C4RCD Research Group, ; Legendre, C.; Liang, W. S.; LoRusso, P.; Sekulic, A.; Sosman, J. A.; Trent, J. M.; Rangasamy, S.; Pirrotte, P.; Schork, N. J.

2020-08-14 bioinformatics
10.1101/2020.08.13.250167 bioRxiv
Show abstract

Here we present a novel statistical approach to splicing outlier and differential splicing detection, implemented in a software package called Bisbee. We leverage Bisbees prediction of protein level effects to benchmark using matched RNAseq and mass spectrometry data from normal tissues. Bisbee exhibits improved sensitivity and specificity over existing approaches. We applied Bisbee to confirm a pathogenic splicing event in a rare disease and to identify tumor-specific splice isoforms associated with an oncogenic splice factor mutation. We also identified common tumor associated splice isoforms replicated in an independent dataset, demonstrating the utility of Bisbee in discovering disease relevant splice variants.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.