Spliceator: multi-species splice site prediction using convolutional neural networks

• DOI: 10.1186/s12859-021-04471-3
• Publication Date: 2021-11-23T11:02:44Z
• Authors: Nicolas Scalzitti; Arnaud Kress; Romain Orhand; Thomas Weber; Luc Moulinier; Anne Jeannin-Gira...; Pierre Collet; Olivier Poch; Julie D. Thompson
• Keywords: Genome; QH301-705.5; Computer applications to medicine. Medical informatics; 0206 medical engineering; Data quality; R858-859.7; Deep learning; Convolutional neural network; 02 engineering and technology; [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]; [SDV.BBM.GTP]Life Sciences [q-bio]/Biochemistry, Molecular Biology/Genomics [q-bio.GN]; Splice site prediction; Animals; Humans; Neural Networks, Computer; Biology (General); Software; Algorithms; Genome annotation

Abstract Background Ab initio prediction of splice sites is an essential step in eukaryotic genome annotation. Recent predictors have exploited Deep Learning algorithms and reliable gene structures from model organisms. However, Deep Learning methods for non-model organisms are lacking.

Results We developed Spliceator to predict splice sites in a wide range of species, including model and non-model organisms. Spliceator uses a convolutional neural network and is trained on carefully validated data from over 100 organisms. We show that Spliceator achieves consistently high accuracy (89–92%) compared to existing methods on independent benchmarks from human, fish, fly, worm, plant and protist organisms.

Conclusions Spliceator is a new Deep Learning method trained on high-quality data, which can be used to predict splice sites in diverse organisms, ranging from human to protists, with consistently high accuracy.