DeepReg: a deep learning hybrid model for predicting transcription factors in eukaryotic and prokaryotic genomes.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
21 Apr 2024
21 Apr 2024
Historique:
received:
13
09
2023
accepted:
11
04
2024
medline:
22
4
2024
pubmed:
22
4
2024
entrez:
21
4
2024
Statut:
epublish
Résumé
Deep learning models (DLMs) have gained importance in predicting, detecting, translating, and classifying a diversity of inputs. In bioinformatics, DLMs have been used to predict protein structures, transcription factor-binding sites, and promoters. In this work, we propose a hybrid model to identify transcription factors (TFs) among prokaryotic and eukaryotic protein sequences, named Deep Regulation (DeepReg) model. Two architectures were used in the DL model: a convolutional neural network (CNN), and a bidirectional long-short-term memory (BiLSTM). DeepReg reached a precision of 0.99, a recall of 0.97, and an F1-score of 0.98. The quality of our predictions, the bias-variance trade-off approach, and the characterization of new TF predictions were evaluated and compared against those produced by DeepTFactor, as well as against experimental data from three model organisms. Predictions based on our DLM tended to exhibit less variance and bias than those from DeepTFactor, thus increasing reliability and decreasing overfitting.
Identifiants
pubmed: 38644393
doi: 10.1038/s41598-024-59487-5
pii: 10.1038/s41598-024-59487-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
9155Subventions
Organisme : Consejo Nacional de Humanidades, Ciencias y Tecnologías
ID : 857463
Organisme : DGAPA-UNAM
ID : IN-220523
Informations de copyright
© 2024. The Author(s).
Références
Privalov, P. L. & Crane-Robinson, C. Forces maintaining the DNA double helix and its complexes with transcription factors. Prog. Biophys. Mol. Biol. 135, 30–48. https://doi.org/10.1016/j.pbiomolbio.2018.01.007 (2018).
doi: 10.1016/j.pbiomolbio.2018.01.007
pubmed: 29378224
Fulton, D. L. et al. TFCat: The curated catalog of mouse and human transcription factors. Genome Biol. 10, R29. https://doi.org/10.1186/gb-2009-10-3-r29 (2009).
doi: 10.1186/gb-2009-10-3-r29
pubmed: 19284633
pmcid: 2691000
Lemon, B. & Tjian, R. Orchestrated response: A symphony of transcription factors for gene control. Genes Dev. 14, 2551–2569. https://doi.org/10.1101/gad.831000 (2000).
doi: 10.1101/gad.831000
pubmed: 11040209
Shelest, E. Transcription factors in fungi. FEMS Microbiol. Lett. 286, 145–151. https://doi.org/10.1111/j.1574-6968.2008.01293.x (2008).
doi: 10.1111/j.1574-6968.2008.01293.x
pubmed: 18789126
Martinez-Liu, L. et al. Comparative genomics of DNA-binding transcription factors in archaeal and bacterial organisms. PLoS One 16, e0254025. https://doi.org/10.1371/journal.pone.0254025 (2021).
doi: 10.1371/journal.pone.0254025
pubmed: 34214112
pmcid: 8253408
Flores-Bautista, E. et al. Deciphering the functional diversity of DNA-binding transcription factors in bacteria and archaea organisms. PLoS One 15, e0237135. https://doi.org/10.1371/journal.pone.0237135 (2020).
doi: 10.1371/journal.pone.0237135
pubmed: 32822422
pmcid: 7446807
Ledesma, L., Hernandez-Guerrero, R. & Perez-Rueda, E. Prediction of DNA-binding transcription factors in bacteria and archaea genomes. In Prokaryotic Gene Regulation (eds Peeters, E. & Bervoets, I.) 103–112 (Springer US, 2022). https://doi.org/10.1007/978-1-0716-2413-5_7 .
doi: 10.1007/978-1-0716-2413-5_7
Kim, G. B., Gao, Y., Palsson, B. O. & Lee, S. Y. DeepTFactor: A deep learning-based tool for the prediction of transcription factors. Proc. Natl. Acad. Sci. https://doi.org/10.1073/pnas.2021171118 (2020).
doi: 10.1073/pnas.2021171118
pubmed: 33443222
pmcid: 7812747
Du, Z., Huang, T., Uversky, V. N. & Li, J. Predicting TF proteins by incorporating evolution information through PSSM. IEEE/ACM Trans. Comput. Biol. Bioinf. https://doi.org/10.1109/tcbb.2022.3199758 (2022).
doi: 10.1109/tcbb.2022.3199758
Wang, S., Cheng, X., Li, Y., Wu, M. & Zhao, Y. Image-based promoter prediction: A promoter prediction method based on evolutionarily generated patterns. Sci. Rep. https://doi.org/10.1038/s41598-018-36308-0 (2018).
doi: 10.1038/s41598-018-36308-0
pubmed: 30591712
pmcid: 6308232
Ryu, J. Y., Kim, H. U. & Lee, S. Y. Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers. Proc. Natl. Acad. Sci. U. S. A. https://doi.org/10.1073/pnas.1821905116 (2019).
doi: 10.1073/pnas.1821905116
pubmed: 31843930
pmcid: 6936484
Zhao, J., Yan, W. & Yang, Y. Deeptp: A deep learning model for thermophilic protein prediction. Int. J. Mol. Sci. https://doi.org/10.3390/ijms24032217 (2023).
doi: 10.3390/ijms24032217
pubmed: 38203692
pmcid: 10779407
Oubounyt, M., Louadi, Z., Tayara, H. & Chong, K. T. DeePromoter: Robust promoter predictor using deep learning. Front. Genet. https://doi.org/10.3389/fgene.2019.00286 (2019).
doi: 10.3389/fgene.2019.00286
pubmed: 31024615
pmcid: 6460014
Shujaat, M., Wahab, A., Tayara, H. & Chong, K. T. pcPromoter-CNN: A CNN-based prediction and classification of promoters. Genes 11, 1529. https://doi.org/10.3390/genes11121529 (2020).
doi: 10.3390/genes11121529
pubmed: 33371507
pmcid: 7767505
Min, X., Ye, C., Liu, X. & Zeng, X. Predicting enhancer-promoter interactions by deep learning and matching heuristic. Brief. Bioinf. https://doi.org/10.1093/bib/bbaa254 (2020).
doi: 10.1093/bib/bbaa254
Quang, D. & Xie, X. DanQ: A hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences. Nucleic Acids Res. 44, e107–e107. https://doi.org/10.1093/nar/gkw226 (2016).
doi: 10.1093/nar/gkw226
pubmed: 27084946
pmcid: 4914104
Alipanahi, B., Delong, A., Weirauch, M. T. & Frey, B. J. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol. 33, 831–838. https://doi.org/10.1038/nbt.3300 (2015).
doi: 10.1038/nbt.3300
pubmed: 26213851
Min, S., Lee, B. & Yoon, S. Deep learning in bioinformatics. Brief. Bioinf. https://doi.org/10.1093/bib/bbw068 (2016).
doi: 10.1093/bib/bbw068
Routhier, E. & Mozziconacci, J. Genomics enters the deep learning era. PeerJ 10, e13613. https://doi.org/10.7717/peerj.13613 (2022).
doi: 10.7717/peerj.13613
pubmed: 35769139
pmcid: 9235815
Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589. https://doi.org/10.1038/s41586-021-03819-2 (2021).
doi: 10.1038/s41586-021-03819-2
pubmed: 34265844
pmcid: 8371605
Apweiler, R. UniProt: The universal protein knowledgebase. Nucleic Acids Res. 32, 115D – 119. https://doi.org/10.1093/nar/gkh131 (2004).
doi: 10.1093/nar/gkh131
Gal, Y. & Ghahramani, Z. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. arXiv https://doi.org/10.48550/ARXIV.1506.02142 (2015).
doi: 10.48550/ARXIV.1506.02142
Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv https://doi.org/10.48550/ARXIV.1409.0473 (2014).
doi: 10.48550/ARXIV.1409.0473
Rodríguez-Martínez, J. A., Reinke, A. W., Bhimsaria, D., Keating, A. E. & Ansari, A. Z. Combinatorial bzip dimers display complex DNA-binding specificity landscapes. eLife https://doi.org/10.7554/elife.19272 (2017).
doi: 10.7554/elife.19272
pubmed: 28186491
pmcid: 5349851
Bobola, N. & Merabet, S. Homeodomain proteins in action: Similar DNA binding preferences, highly variable connectivity. Curr. Opin. Genet. Dev. 43, 1–8. https://doi.org/10.1016/j.gde.2016.09.008 (2017).
doi: 10.1016/j.gde.2016.09.008
pubmed: 27768937
Teixeira, M. C. et al. YEASTRACT+: A portal for the exploitation of global transcription regulation and metabolic model data in yeast biotechnology and pathogenesis. Nucleic Acids Res. 51, D785–D791 (2022).
doi: 10.1093/nar/gkac1041
pmcid: 9825512
Hu, Y. et al. Corrigendum: fmicb.2018.0271. Curation of transcriptional regulatory interactions in Aspergillus nidulans and Neurospora crassa reveal structural and evolutionary features of the regulatory networks. Front. Microbiol. 9, 2713. https://doi.org/10.3389/fmicb.2018.0271 (2018).
doi: 10.3389/fmicb.2018.0271
pubmed: 30455682
pmcid: 6236125
Ren, C., Zeng, L. & Zhou, M.-M. Preparation, biochemical analysis, and structure determination of the bromodomain, an acetyl-lysine binding domain. In Methods in Enzymology (eds Ren, C. et al.) 321–343 (Elsevier, 2016). https://doi.org/10.1016/bs.mie.2016.01.018 .
doi: 10.1016/bs.mie.2016.01.018
Watanabe, F. The role of charge neutralization and cooperative binding of linker histone in the higher-order structure of chromatin. FEBS Lett. 249, 147–150. https://doi.org/10.1016/0014-5793(89)80612-x (1989).
doi: 10.1016/0014-5793(89)80612-x
pubmed: 2737276
Geman, S., Bienenstock, E. & Doursat, R. Neural networks and the bias/variance dilemma. Neural Comput. 4, 1–58. https://doi.org/10.1162/neco.1992.4.1.1 (1992).
doi: 10.1162/neco.1992.4.1.1
Doroudi, S. The bias-variance tradeoff: How data science can inform educational debates. AERA Open 6, 233285842097720. https://doi.org/10.1177/2332858420977208 (2020).
doi: 10.1177/2332858420977208