Predicting transcriptional responses to heat and drought stress from genomic features using a machine learning approach in rice

被引:3
|
作者
Smet, Dajo [1 ,2 ]
Opdebeeck, Helder [1 ,2 ]
Vandepoele, Klaas [1 ,2 ,3 ]
机构
[1] Univ Ghent, Dept Plant Biotechnol & Bioinformat, Ghent, Belgium
[2] VIB, Ctr Plant Syst Biol, Ghent, Belgium
[3] Univ Ghent, Bioinformat Inst Ghent, Ghent, Belgium
来源
关键词
rice; regulatory elements; regulation of heat stress; regulation of drought stress; machine learning interpretation; GENE-EXPRESSION; ARABIDOPSIS; NETWORKS; E2F;
D O I
10.3389/fpls.2023.1212073
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Plants have evolved various mechanisms to adapt to adverse environmental stresses, such as the modulation of gene expression. Expression of stress-responsive genes is controlled by specific regulators, including transcription factors (TFs), that bind to sequence-specific binding sites, representing key components of cis-regulatory elements and regulatory networks. Our understanding of the underlying regulatory code remains, however, incomplete. Recent studies have shown that, by training machine learning (ML) algorithms on genomic sequence features, it is possible to predict which genes will transcriptionally respond to a specific stress. By identifying the most important features for gene expression prediction, these trained ML models allow, in theory, to further elucidate the regulatory code underlying the transcriptional response to abiotic stress. Here, we trained random forest ML models to predict gene expression in rice (Oryza sativa) in response to heat or drought stress. Apart from thoroughly assessing model performance and robustness across various input training data, the importance of promoter and gene body sequence features to train ML models was evaluated. The use of enriched promoter oligomers, complementing known TF binding sites, allowed us to gain novel insights in DNA motifs contributing to the stress regulatory code. By comparing genomic feature importance scores for drought and heat stress over time, general and stress-specific genomic features contributing to the performance of the learned models and their temporal variation were identified. This study provides a solid foundation to build and interpret ML models accurately predicting transcriptional responses and enables novel insights in biological sequence features that are important for abiotic stress responses.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Molecular and Physiological Responses of Rice and Weedy Rice to Heat and Drought Stress
    Piveta, Leonard Bonilha
    Roma-Burgos, Nilda
    Noldin, Jose Alberto
    Viana, Vivian Ebeling
    Oliveira, Claudia de
    Lamego, Fabiane Pinto
    Avila, Luis Antonio de
    AGRICULTURE-BASEL, 2021, 11 (01): : 1 - 23
  • [2] Predicting dairy cattle heat stress using machine learning techniques
    Becker, C. A.
    Aghalari, A.
    Marufuzzaman, M.
    Stone, A. E.
    JOURNAL OF DAIRY SCIENCE, 2021, 104 (01) : 501 - 524
  • [3] The effect of drought stress of sorghum grains on the textural features evaluated using machine learning
    Ropelewska, Ewa
    Nazari, Leyla
    EUROPEAN FOOD RESEARCH AND TECHNOLOGY, 2021, 247 (11) : 2787 - 2798
  • [4] The effect of drought stress of sorghum grains on the textural features evaluated using machine learning
    Ewa Ropelewska
    Leyla Nazari
    European Food Research and Technology, 2021, 247 : 2787 - 2798
  • [5] An advanced approach for predicting selective sweep in the genomic regions using machine learning techniques
    Sarkar, Abhik
    Mishra, Dwijesh Chandra
    Sinha, Dipro
    Chaturvedi, Krishna Kumar
    Lal, Shashi Bhushan
    Kumar, Sanjeev
    Jha, Girish Kumar
    Budhlakoti, Neeraj
    GENETIC RESOURCES AND CROP EVOLUTION, 2024, 71 (07) : 3931 - 3942
  • [6] Genome-wide investigation on transcriptional responses to drought stress in wild and cultivated rice
    Geng, Mu-Fan
    Wang, Xiu-Hua
    Wang, Mei-Xia
    Cai, Zhe
    Meng, Qing-Lin
    Wang, Xin
    Zhou, Lian
    Han, Jing-Dan
    Li, Ji-Long
    Zhang, Fu-Min
    Guo, Ya-Long
    Ge, Song
    ENVIRONMENTAL AND EXPERIMENTAL BOTANY, 2021, 189
  • [7] Resolving the structural features of genomic islands: A machine learning approach
    Vernikos, Georgios S.
    Parkhill, Julian
    GENOME RESEARCH, 2008, 18 (02) : 331 - 342
  • [8] Combined Drought and Heat Stress in Rice: Responses, Phenotyping and Strategies to Improve Tolerance
    Maria Vera Jesus DA COSTA
    Yamunarani RAMEGOWDA
    Venkategowda RAMEGOWDA
    Nataraja N.KARABA
    Sheshshayee M.SREEMAN
    Makarla UDAYAKUMAR
    Rice Science, 2021, 28 (03) : 233 - 242
  • [9] Combined Drought and Heat Stress in Rice: Responses, Phenotyping and Strategies to Improve Tolerance
    DA COSTA, Maria Vera Jesus
    RAMEGOWDA, Yamunarani
    RAMEGOWDA, Venkategowda
    KARABA, Nataraja N.
    SREEMAN, Sheshshayee M.
    UDAYAKUMAR, Makarla
    RICE SCIENCE, 2021, 28 (03) : 233 - 242
  • [10] Predicting Terrorism with Machine Learning: Lessons from "Predicting Terrorism: A Machine Learning Approach"
    Basuchoudhary, Atin
    Bang, James T.
    PEACE ECONOMICS PEACE SCIENCE AND PUBLIC POLICY, 2018, 24 (04)