Impact of U2-type introns on splice site prediction in A. thaliana species using deep learning.

Arabidopsis thaliana; CNN; Splice site prediction; U2-type introns; RNA Splice Sites; Genome, Plant; Computational Biology/methods; RNA Splicing; Introns; Deep Learning; Arabidopsis/genetics; Acceptor sites; Biological observations; Learning models; Plant genomes; Spatial complexity; Splice site; Thaliana; U2-type intron; Arabidopsis; Computational Biology; Structural Biology; Biochemistry; Molecular Biology; Computer Science Applications; Applied Mathematics

Abstract :

[en] [en] BACKGROUND: Splice site prediction in plant genomes poses substantial challenges that can be addressed using deep learning models. U2-type introns are especially useful for such studies given their ubiquity in plant genomes and the availability of rich datasets. We formulated two hypotheses: one proposing that short introns may enhance prediction effectiveness due to reduced spatial complexity, and another suggesting that sequences with multiple introns provide a richer context for splicing events. RESULTS: Our findings demonstrate that (1) models trained on datasets containing shorter introns achieve improved effectiveness for acceptor splice sites, but not for donor splice sites, indicating a more nuanced relationship between intron length and splice site prediction than initially hypothesized, and (2) models trained on datasets with multiple introns per sequence show higher effectiveness compared to those trained on datasets with a single intron per sequence. Notably, among the 402 bp sequences analyzed, 72% contained single introns while 28% contained multiple introns for donor sites (36,399 versus 13,987 sequences), with similar proportions observed for acceptor sites (37,236 versus 14,112 sequences). These computational insights align with biological observations, particularly regarding the conserved spatial relationship between branch points and acceptor splice sites, as well as the synergistic effects of multiple introns on splicing efficiency. CONCLUSIONS: The obtained results contribute to a deeper understanding of how intronic features influence splice site prediction and suggest that future prediction models should consider factors such as intron length, multiplicity, and the spatial arrangement of splice-related signals.

Disciplines :

Computer science
Biotechnology
Biochemistry, biophysics & molecular biology

Author, co-author :

Kabanga, Espoir; Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, 21985, Republic of Korea. espoir.kabanga@ghent.ac.kr ; IDLab, Department of Electronics and Information Systems, Ghent University, Ghent, 9000, Belgium. espoir.kabanga@ghent.ac.kr

Jee, Seonil; Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, 21985, Republic of Korea

Yun, Soeun; Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, 21985, Republic of Korea

Depuydt, Stephen; Department of Health Care, HOGENT University of Applied Sciences and Arts, Ghent, 9000, Belgium

Van Messem, Arnout ; Université de Liège - ULiège > Mathematics

De Neve, Wesley; Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, 21985, Republic of Korea ; IDLab, Department of Electronics and Information Systems, Ghent University, Ghent, 9000, Belgium

Language :

English

Title :

Impact of U2-type introns on splice site prediction in A. thaliana species using deep learning.

Publication date :

28 November 2025

Journal title :

BMC Bioinformatics

eISSN :

1471-2105

Publisher :

BioMed Central Ltd, England

Volume :

Issue :

Pages :

288

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://link.springer.com/content/pdf/10.1186/s12859-025-06315-w.pdf

Available on ORBi :

since 30 January 2026

Statistics

Number of views

6 (0 by ULiège)

Number of downloads

1 (0 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

Akpokiro V, Oluwadare O, Kalita J. DeepSplicer: An Improved Method of Splice Sites Prediction using Deep Learning. In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), pp 606–609, 2021. https://doi.org/10.1109/ICMLA52953.2021.00101
Akpokiro V Martin T Oluwadare O EnsembleSplice: ensemble deep learning model for splice site prediction BMC Bioinformatics 2022 23 1 413 10.1186/s12859-022-04971-w 36203144 9535948
Albaradei S Magana-Mora A Thafar M et al. Splice2Deep: An ensemble of deep convolutional neural networks for improved splice site prediction in genomic dna Gene. 2020 763 10.1016/j.gene.2020.100035 100035
Amit M Donyo M Hollander D et al. Differential GC content between exons and introns establishes distinct strategies of splice-site recognition 2012 10.1016/j.celrep.2012.03.013
Angermueller C Pärnamaa T Parts L et al. Deep learning for computational biology Molecular Systems Biology 2016 12 7 878 10.15252/msb.20156651 27474269 4965871
Anil AT Pandian R Mishra SK Introns with branchpoint-distant 3’ splice sites: Splicing mechanism and regulatory roles Biophys Chem. 2024 314 10.1016/j.bpc.2024.107307 39173313 107307
Basu MK Rogozin IB Koonin EV Primordial spliceosomal introns were probably u2-type Trends Genet 2008 24 11 525 528 10.1016/j.tig.2008.09.002 18824272 3381341
Bourdon V Harvey A Lonsdale DM Introns and their positions affect the translational activity of mRNA in plant cells EMBO Rep 2001 2 5 394 398 10.1093/embo-reports/kve090 11375930 1083884
Chang N Sun Q Hu J An C Gao H Large introns of 5 to 10 kilo base pairs can be spliced out in arabidopsis Genes. 2017 8 8 200 10.3390/genes8080200 28800125 5575664
Chen W Moore JM The spliceosome: disorder and dynamics defined Curr Opin Struct Biol 2014 24 141 149 10.1016/j.sbi.2014.01.009 24530854
Chen ZJ Wang J Tian L et al. The development of an arabidopsis model system for genome-wide analysis of polyploidy effects Biol J Lin Soc 2004 82 4 689 700 10.1111/j.1095-8312.2004.00351.x
Chung BYW Simons C Firth AE et al. Effect of 5’UTR introns on gene expression in arabidopsis thaliana BMC Genomics 2006 7 1 120 10.1186/1471-2164-7-120 16712733 1482700
Clancy S RNA splicing: Introns, Exons and Spliceosome. Nature Education 2008 1 1 31
Crabb TL Lam BJ Hertel KJ Retention of spliceosomal components along ligated exons ensures efficient removal of multiple introns RNA 2010 16 9 1786 1796 10.1261/rna.2186510 20610656 2924538
Dewey CN Rogozin IB Koonin EV Compensatory relationship between splice sites and exonic splicing signals depending on the length of vertebrate introns BMC Genomics 2006 7 1 311 10.1186/1471-2164-7-311 17156453 1713244
Dietrich RC Incorvaia R Padgett AR Terminal intron dinucleotide sequences do not distinguish between u2- and u12-dependent introns Mol Cell 1997 1 1 151 160 10.1016/S1097-2765(00)80016-7 9659912
Dolata J Guo Y Kołowerzo A et al. NTR 1 is required for transcription elongation checkpoints at alternative exons in arabidopsis The EMBO journal 2015 34 4 544 558 10.15252/embj.201489478 25568310 4331007
Gallegos JE Rose AB The enduring mystery of intron-mediated enhancement Plant Sci 2015 237 8 15 10.1016/j.plantsci.2015.04.017 26089147
Girardini KN Olthof AM Kanadia RN Introns: the “dark matter” of the eukaryotic genome Front Genet 2023 14 1150212 10.3389/fgene.2023.1150212 37260773 10228655
Goodall GJ Filipowicz W The AU-rich sequences present in the introns of plant nuclear pre-mRNAs are required for splicing Cell 1989 58 3 473 483 10.1016/0092-8674(89)90428-5 2758463
Hebsgaard SM Korning PG Tolstrup N et al. Splice site prediction in Arabidopsis thaliana pre-mRNA by combining local and global sequence information Nucleic Acids Res 1996 24 17 3439 3452 10.1093/nar/24.17.3439 8811101 146109
Hoff KJ, Lomsadze A, Borodovsky M, et al. Whole-Genome Annotation with BRAKER. In: Gene prediction: methods and protocols. Springer, 2019 p 65–95, https://doi.org/10.1007/978-1-4939-9173-0_5
Hong X Scofield DG Lynch M Intron size, abundance, and distribution within untranslated regions of genes Mol Biol Evol 2006 23 12 2392 2404 10.1093/molbev/msl111 16980575
James AB Syed NH Bordage S et al. Alternative splicing mediates responses of the arabidopsis circadian clock to temperature changes Plant Cell 2012 24 3 961 981 10.1105/tpc.111.093948 22408072 3336117
Jia J Long Y Zhang H et al. Post-transcriptional splicing of nascent RNA contributes to widespread intron retention in plants Nature Plants 2020 6 7 780 788 10.1038/s41477-020-0688-1 32541953
Jiao Y Peluso P Shi J et al. Improved maize reference genome with single-molecule technologies Nature 2017 546 7659 524 527 10.1038/nature22971 28605751 7052699
JiaYan W JingFa X LingPing W et al. Systematic analysis of intron size and abundance parameters in diverse lineages Science China Life Sciences 2013 56 10 968 974 10.1007/s11427-013-4540-y
Karve R Liu W Willet SG et al. The presence of multiple introns is essential for ERECTA expression in arabidopsis RNA 2011 17 10 1907 1921 10.1261/rna.2825811 21880780 3185922
Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint https://doi.org/10.48550/arXiv.1412.6980 (2004)
Lanchantin J Singh R Wang B et al. Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks Pac Symp Biocomput 2017 22 254 265 10.1142/9789813207813_0025 27896980 5787355
Laxa M Intron-mediated enhancement: a tool for heterologous gene expression in plants? Front Plant Sci 2017 7 1977 10.3389/fpls.2016.01977 28111580 5216049
Lim LP Burge CB A computational analysis of sequence features involved in recognition of short introns Proc Natl Acad Sci 2001 98 20 11193 11198 10.1073/pnas.201407298 11572975 58706
Liu X Zhang H Zeng Y et al. DRANetSplicer: A Splice Site Prediction Model Based on Deep Residual Attention Networks Genes 2024 15 4 404 10.3390/genes15040404 38674339 11048956
Marquez Y Brown JW Simpson C et al. Transcriptome survey reveals increased complexity of the alternative splicing landscape in Arabidopsis Genome Res 2012 22 6 1184 1195 10.1101/gr.134106.111 22391557 3371709
Martín G Márquez Y Mantica F et al. Alternative splicing landscapes in arabidopsis thaliana across tissues and stress conditions highlight major functional differences with animals Genome Biol 2021 22 1 35 10.1186/s13059-020-02258-y 33446251 7807721
Moyer DC Larue GE Hershberger CE et al. Comprehensive database and evolutionary dynamics of U12-type introns Nucleic Acids Res 2020 48 13 7066 7078 10.1093/nar/gkaa464 32484558 7367187
Ner-Gaon H Halachmi R Savaldi-Goldstein S Rubin E Ophir R Fluhr R Intron retention is a major phenomenon in alternative splicing in Arabidopsis The Plant Journal 2004 39 6 877 85 10.1111/j.1365-313X.2004.02172.x 15341630
Ouyang S, Zhu W, Hamilton J, Lin H, Campbell M, Childs K, Thibaud-Nissen F, Malek RL, Lee Y, Zheng L, Orvis J. The TIGR rice genome annotation resource: improvements and new features. Nucleic acids research 35 2007 Jan 1;35(suppl_1):D883-7. https://doi.org/10.1093/nar/gkl976
Patel AA Steitz JA Splicing double: insights from the second spliceosome Nat Rev Mol Cell Biol 2003 4 12 960 970 10.1038/nrm1259 14685174
Reddy AS Marquez Y Kalyna M et al. Complexity of the alternative splicing landscape in plants Plant Cell 2013 25 10 3657 3683 10.1105/tpc.113.117523 24179125 3877793
Rosa S Duncan S Dean C Mutually exclusive sense-antisense transcription at FLC facilitates environmentally induced gene repression Nat Commun 2016 7 1 13031 10.1038/ncomms13031 27713408 5059766
Rose AB Intron-mediated regulation of gene expression Current Topics in Microbiology and Immunology 2008 1 277 90 10.1007/978-3-540-76776-3_15
Rose AB Introns as gene regulators: a brick on the accelerator Front Genet 2019 9 672 10.3389/fgene.2018.00672 30792737 6374622
Roy M Kim N Xing Y et al. The effect of intron length on exon creation ratios during the evolution of mammalian genomes RNA 2008 14 11 2261 2273 10.1261/rna.1024908 18796579 2578852
Sales-Lee J Perry DS Bowser BA et al. Coupling of spliceosome complexity to intron diversity Curr Biol. 2021 31 22 4898 4910.e4 10.1016/j.cub.2021.09.004 34555349 8967684
Sharp PA Burge CB Classification of introns: U2-Type or U12-Type Cell 1997 91 7 875 879 10.1016/S0092-8674(00)80479-1 9428511
Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: Visualising image classification models and saliency maps. In: Workshop at International Conference on Learning Representations, 2014. https://doi.org/10.48550/arXiv.1312.6034
Szeghalmy S Fazekas A A comparative study of the use of stratified cross-validation and distribution-balanced stratified cross-validation in imbalanced learning Sensors 2023 23 4 2333 10.3390/s23042333 36850931 9967638
Tareen A Kinney JB Logomaker: beautiful sequence logos in python Bioinformatics 2019 36 7 2272 2274 10.1093/bioinformatics/btz921 7141850
The Arabidopsis Genome Initiative Analysis of the genome sequence of the flowering plant arabidopsis thaliana Nature 2000 408 6814 796 815 10.1038/35048692
Tolstrup N Rouzé P Brunak S A branch point consensus from Arabidopsis found by non-circular analysis allows for better prediction of acceptor sites Nucleic Acids Res 1997 25 15 3159 3163 10.1093/nar/25.15.3159 9224618 146848
Wang BB Brendel V Genomewide comparative analysis of alternative splicing in plants Proc Natl Acad Sci 2006 103 18 7175 7180 10.1073/pnas.0602039103 16632598 1459036
Wang R Wang Z Wang J et al. SpliceFinder: ab initio prediction of splice sites using convolutional neural network BMC Bioinformatics 2019 20 23 652 10.1186/s12859-019-3306-3 31881982 6933889
Yeo G Burge CB Maximum entropy modeling of short sequence motifs with applications to RNA splicing signals J Comput Biol 2004 11 2–3 377 394 10.1089/1066527041410418 15285897
Zhang Q Li H Zhao XQ et al. The evolution mechanism of intron length Genomics 2016 108 2 47 55 10.1016/j.ygeno.2016.07.004 27449197
Zhu D Mao F Tian Y et al. The Features and Regulation of Co-transcriptional Splicing in Arabidopsis Mol Plant 2020 13 2 278 294 10.1016/j.molp.2019.11.004 31760161
Zuallaert J Godin F Kim M et al. SpliceRover: interpretable convolutional neural networks for improved splice site prediction Bioinformatics 2018 34 24 4180 4188 10.1093/bioinformatics/bty497 29931149