Academic Journal
Προβολή σε EDS

Benchmarking ensemble and deep learning models for drought-responsive gene prioritisation in rice using multi-omics data.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Benchmarking ensemble and deep learning models for drought-responsive gene prioritisation in rice using multi-omics data.
Συγγραφείς: Govaichelvan KN; Institute of Biological Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia., Pathmanathan D; Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia., Zainal-Abidin RA; Biotechnology and Nanotechnology Research Centre, Malaysian Agricultural Research and Development Institute (MARDI), Serdang, Selangor, Malaysia., Abu A; Institute of Biological Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia.; Centre of Research in Systems Biology, Structural Bioinformatics and Human Digital Imaging, Universiti Malaya, Kuala Lumpur, Malaysia.
Πηγή: PloS one [PLoS One] 2026 Oct 09; Vol. 21 (10), pp. e0360052. Date of Electronic Publication: 2026 Oct 09 (Print Publication: 2026).
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
Imprint Name(s): Original Publication: San Francisco, CA : Public Library of Science
Ιατρικοί όροι (MeSH): Oryza*/genetics , Droughts* , Deep Learning* , Genes, Plant*, Stress, Physiological/genetics ; Multiomics ; Random Forest ; Boosting Machine Learning Algorithms ; Benchmarking ; Proteomics ; Multilayer Perceptrons ; Transcriptome ; Algorithms ; Gene Expression Profiling
Περίληψη: Identifying drought-responsive genes is critical for climate-resilient crop breeding, yet computational gene-trait association often relies on single-omics or generalized genomic datasets. Optimal algorithm selection for high-dimensional, small multi-omics datasets also remains a persistent challenge. We present a machine learning framework that extends the QTG-Finder feature set by integrating transcriptomic and proteomic features to classify drought-responsive genes in rice. Using MBKBase annotations, we evaluated the ability of these models to prioritise 336 drought-responsive genes among 2,416 abiotic stress-associated genes, of which the remaining 2,080 constituted an operational background set. We tested four algorithms: Random Forest, XGBoost, one-dimensional convolutional neural network, and multilayer perceptron, while addressing severe class imbalance and assessing model stability. Tree-based ensemble methods achieved higher performance than the deep learning models in this dataset, which showed early overfitting. The fine-tuned Random Forest achieved a recall of 0.67 and an AUC-ROC of 0.87 under nested cross-validation, conditional on a feature matrix assembled before gene-level data splitting. Across repeated evaluations of a small internal holdout of 10 genes, mean accuracy and recall were 0.90 and 0.63; this set is too small to support a generalizability claim and is reported only as a consistency check. The newly added transcriptomic and proteomic features improved recall from 0.47 to 0.67 compared with genomics alone. Feature importance and ablation analyses indicated that transcriptomics-derived features, particularly measures of expression distribution, magnitude, and direction, contributed most to predictive performance. Functional enrichment analysis supported the biological relevance of the prioritised genes. These results demonstrate the value of multi-omics integration for gene prioritisation in small tabular datasets while highlighting current limitations of deep learning in this setting.
(Copyright: © 2026 Govaichelvan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Competing Interests: The authors have declared that no competing interests exist.
References: Bioinformatics. 2014 Apr 1;30(7):923-30. (PMID: 24227677)
Proc Natl Acad Sci U S A. 2011 Nov 8;108(45):18548-53. (PMID: 22042862)
G3 (Bethesda). 2022 Nov 4;12(11):. (PMID: 36149290)
Micromachines (Basel). 2023 Aug 27;14(9):. (PMID: 37763836)
Brief Bioinform. 2024 Jan 22;25(2):. (PMID: 38426322)
Plant Cell. 2015 Aug;27(8):2133-47. (PMID: 26286535)
Nucleic Acids Res. 2020 Jan 8;48(D1):D1085-D1092. (PMID: 31624841)
BMC Bioinformatics. 2008 Dec 29;9:559. (PMID: 19114008)
Mol Biol Evol. 2014 Jun;31(6):1514-25. (PMID: 24659814)
Annu Rev Plant Biol. 2019 Apr 29;70:435-463. (PMID: 30795704)
IEEE/ACM Trans Comput Biol Bioinform. 2023 May-Jun;20(3):2170-2176. (PMID: 37018271)
Front Genet. 2021 Jun 24;12:652189. (PMID: 34249082)
Nat Commun. 2020 Feb 5;11(1):735. (PMID: 32024846)
G3 (Bethesda). 2019 Nov 5;9(11):3691-3702. (PMID: 31533955)
Sensors (Basel). 2023 May 25;23(11):. (PMID: 37299785)
Proc Natl Acad Sci U S A. 2016 Jul 19;113(29):8041-8. (PMID: 27432983)
Bioinformatics. 2014 Aug 1;30(15):2114-20. (PMID: 24695404)
Genome Biol. 2014;15(12):550. (PMID: 25516281)
Front Microbiol. 2024 Feb 08;15:1354190. (PMID: 38389525)
Nucleic Acids Res. 2017 Jan 4;45(D1):D1075-D1081. (PMID: 27899667)
iScience. 2020 Dec 05;24(1):101890. (PMID: 33364579)
Comput Struct Biotechnol J. 2022 Aug 12;20:4369-4375. (PMID: 36051874)
BMC Bioinformatics. 2022 May 5;23(1):162. (PMID: 35513802)
PeerJ. 2023 Mar 24;11:e15100. (PMID: 36992941)
G3 (Bethesda). 2019 Oct 7;9(10):3129-3138. (PMID: 31358562)
Patterns (N Y). 2022 Jul 08;3(7):100520. (PMID: 35845841)
PLoS One. 2019 Nov 7;14(11):e0224365. (PMID: 31697686)
Nat Rev Genet. 2015 Feb;16(2):85-97. (PMID: 25582081)
Nucleic Acids Res. 2011 Jan;39(Database issue):D19-21. (PMID: 21062823)
Cardiovasc Drugs Ther. 2024 Apr;38(2):223-236. (PMID: 37421484)
Bioinformatics. 2020 Apr 15;36(8):2628-2629. (PMID: 31882993)
Front Plant Sci. 2020 Mar 20;11:323. (PMID: 32265970)
Commun Biol. 2020 Sep 10;3(1):502. (PMID: 32913254)
Nat Methods. 2015 Apr;12(4):357-60. (PMID: 25751142)
PeerJ. 2025 Jan 30;13:e18863. (PMID: 39897484)
Heliyon. 2023 Feb 14;9(3):e13744. (PMID: 36879962)
Front Immunol. 2023 Apr 06;14:1167917. (PMID: 37090709)
PeerJ Comput Sci. 2024 Mar 29;10:e1914. (PMID: 38660179)
Sci Rep. 2022 Dec 23;12(1):22236. (PMID: 36564466)
Theor Appl Genet. 2025 Jan 24;138(1):36. (PMID: 39853381)
Asian Pac J Cancer Prev. 2023 Oct 01;24(10):3525-3535. (PMID: 37898859)
NAR Genom Bioinform. 2020 Sep;2(3):lqaa078. (PMID: 33015620)
Entry Date(s): Date Created: 20261009 Date Completed: 20261009 Latest Revision: 20261011
Update Code: 20261011
PubMed Central ID: PMC13652213
DOI: 10.1371/journal.pone.0360052
PMID: 42853794
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1932-6203
DOI:10.1371/journal.pone.0360052