loading page

Benchmarking deep learning splice prediction tools using functional splice assays
  • +2
  • Tabea Riepe,
  • Mubeen Khan,
  • Susanne Roosing,
  • Frans Cremers,
  • Peter 't Hoen
Tabea Riepe
Radboud University Nijmegen Centre for Molecular and Biomolecular Informatics

Corresponding Author:[email protected]

Author Profile
Mubeen Khan
Radboud Universiteit Donders Institute for Brain Cognition and Behaviour
Author Profile
Susanne Roosing
Radboud University Medical Center
Author Profile
Frans Cremers
Radboud University Nijmegen Medical Centre
Author Profile
Peter 't Hoen
Radboud Universiteit Centre for Molecular and Biomolecular Informatics
Author Profile


Hereditary disorders are frequently caused by genetic variants that affect pre-mRNA splicing. Whilst genetic variants in the canonical splice motifs are almost always disrupting splicing, the pathogenicity of variants in the non-canonical splice sites (NCSS) and deep intronic (DI) regions are difficult to predict. Multiple splice prediction tools have been developed for this purpose, with the latest tools employing deep learning algorithms. We benchmarked established and deep learning splice prediction tools on gold standard sets of variants in the ABCA4 and MYBPC3 genes associated with Stargardt disease (STGD1) and cardiomyopathy, respectively, with functional assessment in midigene and minigene splice assays. The best performing splice prediction tool for both NCSS and DI variants in ABCA4 was SpliceAI, whilst SpliceSiteFinder-like performed best for NCSS variants in MYBPC3. Overall, the performance in a real time clinical setting is much more modest than reported by the developers of the tools.
18 Sep 2020Submitted to Human Mutation
22 Sep 2020Submission Checks Completed
22 Sep 2020Assigned to Editor
05 Jan 2021Reviewer(s) Assigned
29 Jan 2021Review(s) Completed, Editorial Evaluation Pending
01 Feb 2021Editorial Decision: Revise Major
16 Mar 20211st Revision Received
17 Mar 2021Submission Checks Completed
17 Mar 2021Assigned to Editor
18 Mar 2021Reviewer(s) Assigned
05 Apr 2021Review(s) Completed, Editorial Evaluation Pending
17 Apr 2021Editorial Decision: Accept
03 May 2021Published in Human Mutation. 10.1002/humu.24212