Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 23;12(1):71.
doi: 10.3390/plants12010071.

An Evidence Theory and Fuzzy Logic Combined Approach for the Prediction of Potential ARF-Regulated Genes in Quinoa

Nesrine Sghaier  1   2   3 , Jemaa Essemine  2 , Rayda Ben Ayed  4   5 , Mustapha Gorai  6 , Riadh Ben Marzoug  7 , Ahmed Rebai  7 , Mingnan Qu  1   2
Affiliations

An Evidence Theory and Fuzzy Logic Combined Approach for the Prediction of Potential ARF-Regulated Genes in Quinoa

Nesrine Sghaier et al. Plants (Basel). .

Abstract

Quinoa constitutes among the tolerant plants to the challenging and harmful abiotic environmental factors. Quinoa was selected as among the model crops destined for bio-saline agriculture that could contribute to the staple food security for an ever-growing worldwide population under various climate change scenarios. The auxin response factors (ARFs) constitute the main contributors in the plant adaptation to severe environmental conditions. Thus, the determination of the ARF-binding sites represents the major step that could provide promising insights helping in plant breeding programs and improving agronomic traits. Hence, determining the ARF-binding sites is a challenging task, particularly in species with large genome sizes. In this report, we present a data fusion approach based on Dempster-Shafer evidence theory and fuzzy set theory to predict the ARF-binding sites. We then performed an "In-silico" identification of the ARF-binding sites in Chenopodium quinoa. The characterization of some known pathways implicated in the auxin signaling in other higher plants confirms our prediction reliability. Furthermore, several pathways with no or little available information about their functions were identified to play important roles in the adaptation of quinoa to environmental conditions. The predictive auxin response genes associated with the detected ARF-binding sites may certainly help to explore the biological roles of some unknown genes newly identified in quinoa.

Keywords: ARF-binding sites; Chenopodium quinoa; data fusion; evidence theory; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Feature space of the position and significance score representing the training sets distribution of the ARF-binding sites (red color) and false positives (blue color). Three fuzzy sets and their corresponding membership degree functions (μSc(i) and P(j)). The latter parameters were defined for each feature (position and score) and found to yield nine regions. The boundaries of the different sets were determined through a learning step as much as possible to define the discriminative regions.
Figure 2
Figure 2
Feature space of the occurrence and density defining the training sets distribution of the ARF-binding sites (rx cq ed color) and false positives (blue color). Three fuzzy sets and their corresponding membership degree functions (μO(i) and D(j)). μO(i) and D(j) were defined for the occurrence and density, respectively, yielding twelve regions. The boundaries of the different sets were determined through a learning step as much as we could to find the discriminative regions.
Figure 3
Figure 3
Feature space of the two first discriminative functions linear discriminant analysis of the represented training sets distribution of the ARF-binding sites (red color) and false positives (blue color). Three fuzzy sets and their corresponding membership degree functions (μF1(i) and F2(j)) were defined for each feature, yielding nine regions. The different sets of boundaries were determined through a learning step as much as possible to delimit discriminative regions.
Figure 4
Figure 4
The receiver operating characteristic (ROC) curves of ARF-binding sites predicted using our data fusion method. The ARF members (4, 13, 14, 18, 35, and 39) were depicted by the alphabetic letters from (A–F), respectively. The true positive rate was evaluated as follows: TPR = TP/(TP + FN) and the false positive one FPR = TN/(TN + FP). The reference lines are displayed in green color for all the ARFs members.
Figure 5
Figure 5
Boxplot of the average AUC of 6 different ARFs members studied herein before and after combination using specific features of ARF-binding. Data fusion method is a combination of method_1 and method_2. Method_1 represents the prediction using overrepresented motifs, and method_2 corresponds to the prediction based on linear discriminant analysis (LDA).
Figure 6
Figure 6
The accuracy of Data fusion methodology (blue curve) was compared to Fimo (green curve) and Matrix scan (yellow curve) using ROC curves for the ARF39 binding sites. Higher curve (close to the top left corner) represents the ROC curve of our method corresponding to the model with better ARF-binding sites prediction quality.
Figure 7
Figure 7
GO and KEGG analyses performed on the ARF4. (A), GO analysis showing the top 20 enriched pathways for the biological process, cellular component, and molecular function. (B), KEGG analysis displaying the top 20 enriched metabolic pathways based on the ARF4 gate.
Figure 8
Figure 8
GO and KEGG analyses performed on the ARF39. (A), GO analysis displaying the top 20 enriched pathways for the biological process, cellular component, and molecular function. (B), KEGG analysis displaying the top 20 enriched metabolic pathways based on the ARF39 gate.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Raza A., Razzaq A., Mehmood S.S., Zou X., Zhang X., Lv Y., Xu J. Impact of climate change on crops adaptation and strategies to tackle its outcome: A review. Plants. 2019;8:34. doi: 10.3390/plants8020034. - DOI - PMC - PubMed
    1. Pareek A., Dhankher O.P., Foyer C.H. Mitigating the impact of climate change on plant productivity and ecosystem sustainability. J. Exp. Bot. 2020;71:451–456. doi: 10.1093/jxb/erz518. - DOI - PMC - PubMed
    1. Manaa A., Goussi R., Derbali W., Cantamessa S., Abdelly C., Barbato R. Salinity tolerance of quinoa (Chenopodium quinoa Willd) as assessed by chloroplast ultrastructure and photosynthetic performance. Environ. Exp. Bot. 2019;162:103–114. doi: 10.1016/j.envexpbot.2019.02.012. - DOI
    1. Ruiz K.B., Biondi S., Oses R., Acuña-Rodríguez I.S., Antognoni F., Martinez-Mosqueira E.A., Coulibaly A., CanahuaMurillo A., Pinto M., Zurita-Silva A., et al. Quinoa biodiversity and sustainability for food security under climate change. A review. Agron. Sustain. Dev. 2014;34:349–359. doi: 10.1007/s13593-013-0195-0. - DOI
    1. Bazile D., Bertero D., Nieto C., editors. State of the Art Report on Quinoa around the World in 2013. FAO; Roma, Italy: 2015. [(accessed on 17 September 2020)]. 589p. Available online: https://www.academia.edu/21134586/Bazile_D_ed_Bertero_H_D_ed_Nieto_C_ed_....

LinkOut - more resources

-