The prediction of genetic values of chickpea genotypes in F4 generation by REML/BLUP and FAI–BLUP from mixed analysis models and feature importance ranking by boruta–random forest model
Sibel Ipekesen
A * and Behiye Tuba Bicer A
A
Abstract
Selection indices are frequently used in plant breeding programs to evaluate multiple traits simultaneously. These indices allow the selection of genotypes that combine desirable characteristics for the product and show high yields.
The paper aimed to predict genetic parameters of 29 chickpea genotypes in the F4 generation, to determine genotypic and phenotypic correlation and genotypic and phenotypic path coefficients and to select superior chickpea genotypes by using mixed linear models.
The experiment was conducted in Diyarbakir, south-eastern Anatolia of Türkiye. The experiment was arranged as a randomized complete blocks design with three replications. The selection of features and superior genotypes was analyzed using some mixed analysis models, including restricted maximum likelihood–best linear unbiased prediction (REML/BLUP,) genotype–ideotype distance index (FAI–BLUP), principal component analysis (PCA), feature importance ranking (boruta–random forest) and classifying features and genotypes (Ward’s clustering).
These mixed analysis models effectively selected the best chickpea genotypes that have advantageous genetic gains for all examined features. The selection accuracy for predicting genetic values was quite high (>96%) in the REML/BLUP model; however, it was lower (78.2%) in the PCA. In the boruta–random forest, the superior features closely related to seed yield plant−1 were determined in chickpea genotypes. The FAI–BLUP index showed that G3, G7, G10, G23, G27, and G28 genotypes were closest to the ideotype for the features. Additionally, in Ward’s clustering analysis, these genotypes had a wide genetic diversity and high similarity.
The results of this paper indicated that the used models are effective in selecting features contributing to seed yield in chickpea breeding programs.
This paper evaluated mixed linear models to predict genetic parameters of chickpea genotypes and provides recommendations on the best models.
Keywords: Boruta-random forest, chickpea, Cicer arietinum, FAI-BLUP, mixed models, REML-BLUP, selection, Ward’s clustering.
References
Agrawal T, Kumar A, Kumar S, Kumar A, Kumar RR, Kumar S, Singh PK (2018) Correlation and path coefficient analysis for grain yield and yield components in chickpea (Cicer arietinum L.) under normal and late sown conditions of Bihar, India. International Journal of Current Microbiology and Applied Sciences (IJCMAS) 7, 1633-1642.
| Crossref | Google Scholar |
Ahmed AAM, Deo RC, Ghahramani A, Raj N, Feng Q, Yin Z, Yang L (2021) LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios. Stochastic Environmental Research and Risk Assessment 35, 1851-1881.
| Crossref | Google Scholar |
Ambrósio M, Daher RF, Santos RM, Santana JGS, Vidal AKF, Nascimento MR, et al. (2024) Multi-trait index: selection and recommendation of superior black bean genotypes as new improved varieties. BMC Plant Biology 24, 525.
| Crossref | Google Scholar |
Amrate PK, Nataraj V, Shivakumar M, Shrivastava MK, Rajput LS, Mohare S, et al. (2025) Best linear unbiased prediction (BLUP)-based models aided in selection of high yielding charcoal rot and yellow mosaic resistant soybean genotypes. Genetic Resources and Crop Evolution 72, 5593-5611.
| Crossref | Google Scholar |
Breiman L (2001) Random forests. Machine Learning 45, 5-32.
| Crossref | Google Scholar |
Cortes DFM, Santa-Catarina R, Vettorazzi JCF, Ramos HCCR, Viana AP, Pereira MG (2019) Development of superior lines of papaya from the Formosa group using the pedigree method and REML/Blup procedure. Bragantia 78, 350-360.
| Crossref | Google Scholar |
Dehbaoui NE, Gentzbittel L, Drevon JJ, Lazali M (2024) Diversity analyses of chickpea (Cicer arietinum L.) through agro-morphological traits. Plant Genetic Resources: Characterization and Utilization 22, 1-7.
| Crossref | Google Scholar |
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological) 39, 1-22.
| Crossref | Google Scholar |
Dewey DR, Lu KH (1959) A correlation and path-coefficient analysis of components of crested wheatgrass seed production. Agronomy Journal 51, 515-518.
| Crossref | Google Scholar |
FAOSTAT (2023) Crops and livestock products. Available at https://www.fao.org/faostat/en/#data/QCL [accessed 10 October 2024]
Geneti GS, Kebede SA, Mekonnen TB (2022) Genetic variability and association of traits in bread wheat (Triticum aestivum L.) genotypes in Gechi district, South West Ethiopia. Advances in Agriculture 2022, 7132424.
| Crossref | Google Scholar |
Ghavidel S, Pour-Aboughadareh A, Mostafavi K (2024) Identification of drought-tolerant genotypes of barley (Hordeum vulgare L.) based on selection indices. CSRAR 5, 671-687.
| Crossref | Google Scholar |
Gurumurthy S, Ashu A, Kruthika S, Solanke AP, Basavaraja T, Soren KR, et al. (2024) An innovative natural speed breeding technique for accelerated chickpea (Cicer arietinum L.) generation turnover. Plant Methods 20, 177.
| Crossref | Google Scholar |
Hawkins DM (2004) The problem of overfitting. Journal of Chemical Information and Computer Sciences 44, 1-12.
| Crossref | Google Scholar | PubMed |
Hussain T, Akram Z, Shabbir G, Manaf A, Ahmed M (2021) Identification of drought tolerant chickpea genotypes through multi trait stability index. Saudi Journal of Biological Sciences 28, 6818-6828.
| Crossref | Google Scholar |
Ipekesen S, Basdemir F, Tunc M, Bicer BT (2022) Minerals, vitamins, protein and amino acids in wild Cicer species and pure line chickpea genotypes selected from a local population. Journal of Elementology 27, 27-140.
| Crossref | Google Scholar |
Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: a tutorial. Computer 29, 31-44.
| Crossref | Google Scholar |
Jakhar DS (2014) Genetic diversity studies in chickpea (Cicer arietinum l.). Bangladesh Journal of Botany 45, 459-464.
| Google Scholar |
Janghel DK, Kumar K, Sunil R, Chhabra AK (2020) Genetic diversity analysis, characterization and evaluation of elite chickpea (Cicer arietinum L.) genotypes. International Journal of Current Microbiology and Applied Sciences 9, 199-209.
| Crossref | Google Scholar |
Jayalakshmi V, Reddy AL, Devi SR, Imran MM (2022) Genetic diversity study through K-Means clustering in germplasm accessions of chickpea (Cicer arietinum L.). Electronic Journal of Plant Breeding 13, 1402-1407.
| Crossref | Google Scholar |
Joshi P, Yasin M, Sundaram P (2018) Genetic variability, heritability and genetic advance study for seed yield and yield component traits in a chickpea recombinant inbred line (RIL) population. International Journal of Pure & Applied Bioscience 6, 136-141.
| Crossref | Google Scholar |
Karimizadeh R, Pezeshkpour P, Mirzaee A, Barzali M, Sharifi P, Khoshkhoy Nilash EA, et al. (2023) Identification of stable chickpeas under dryland conditions by mixed models. Legume Science 5, e206.
| Crossref | Google Scholar |
Kassambara A, Mundt F (2017) Factoextra: extract and visualize the results of multivariate data analyses: R package version 1.0.5.999. Available at http://www.sthda.com/english/rpkgs/factoextra [accessed 13 January 2024]
Kaur R, Prasad K (2023) Characterization and classification of selective Indian chickpea cultivars based on physical and hydration properties, using image and multivariate analysis. Legume Science 5, e168.
| Crossref | Google Scholar |
Mahmood MT, Hussain K, Amin A, Batool A, Aziz A, Kaukab S, et al. (2024) Genetic variability assessment among elite chickpea (Cicer arientinum) genotypes under water deficit conditions. PEJMLS 7, 31-38.
| Crossref | Google Scholar |
Manikanteswara O, Lavanya GR, Ranganatha YH, Chandu MMS (2018) Estimation of genetic variability, correlation and path analysis for seed yield characters in chickpea (Cicer arietinum L.). International Journal of Current Microbiology and Applied Sciences 7, 843-849.
| Crossref | Google Scholar |
Mascarenhas SNAdP, Almeida ÍFd, Almeida RVd, Pinto BRC, Fernandes GA (2024) Prediction of genotypic values via REML/BLUP and path analysis in maize half-sib families. Revista Caderno Pedagógico 21, e11165.
| Crossref | Google Scholar |
Meier C, Marchioro VS, Meira D, Olivoto T, Klein LA (2021) Genetic parameters and multiple-trait selection in wheat genotypes. Pesquisa Agropecuária Tropical 51, e67996.
| Crossref | Google Scholar |
Mesfin S, Gebresamuel G, Haile M, Zenebe A (2023) Potentials of legume rotation on yield and nitrogen uptake of subsequent wheat crop in northern Ethiopia. Heliyon 9, e16126.
| Crossref | Google Scholar |
Nakazawa M (2018) Fmsb: functions for medical statistics book with some demographic data. Available at https://cran.r-project.org/package/fmsb [accessed 25 December 2024]
Naveen A, Singh SP, Singhal T, Reddy S, Bhargavi HA, Yadav S, et al. (2025) Delineation of selection efficiency and coincidence of multi-trait-based models in a global germplasm collection of pearl millet for a comprehensive assessment of stability and high performing genotypes. Genetic Resources and Crop Evolution 72, 4843-4859.
| Crossref | Google Scholar |
Olivoto T, Nardino M (2020) MGIDI: toward an effective multivariate selection in biological experiments. Bioinformatics 37, 1383-1389.
| Crossref | Google Scholar |
Olivoto T, Lúcio ADC, da Silva JAG, Sari BG, Diel MI (2019) Mean performance and stability in multi-environment trials II: selection based on multiple traits. Agronomy Journal 111, 2961-2969.
| Crossref | Google Scholar |
Parida G, Saghfi S, Eivazi A, Akbarzadeh A (2018) Study of genetic advance and broad-sense heritability for grain yield and yield components of chickpea (Cicer arietinum L.) genotypes. Advances in Biology & Earth Sciences 3, 5-12.
| Google Scholar |
Patel RRS, Sharma D, Das BK, Mondal S, Sahu PK, Vishwakarma G, et al. (2021) Study of coefficient of variation (GCV & PCV), heritability and genetic advance in advanced generation mutant line of rice (Oryza sativa L.). The Pharma Innovation Journal 10, 784-787.
| Crossref | Google Scholar |
Paulan SDC, Pupin S (2019) ‘Genética e Melhoramento de Plantas e Animais.’ (Editora e Distribuidora Educacional: Londrina, Brazil) doi:10.22533/at.ed.192191710 [accessed 11 December 2024] (In Spanish)
Prasanthi G, Jayalakshmi V, Reddy AT, Khayumahammed S (2024) Genetic variability parameters and character association studies among phenological traits, yield traits and quality traits under different dates of planting in chickpea (Cicer arietinum L.). Journal of Food Legumes 36, 126-135.
| Crossref | Google Scholar |
Praween N, Kumar Y, Sikarwar RS, Basu PS, Bharadwaj C, Mondal B, Dixit GP (2024) Genetic analysis of chickpea (Cicer arietinum L.) genotypes for seed yield under changing cropping environments. Journal of Food Legumes 37, 373-382.
| Crossref | Google Scholar |
Qulmamatova DE (2023) Chickpea (Cicer arietinum L.) genotypes evaluation for high yield through multivariate analysis. SABRAO Journal of Breeding and Genetics 55, 107-114.
| Crossref | Google Scholar |
Rajković D, Marjanović Jeromela A, Pezo L, Lončar B, Zanetti F, Monti A, Kondić Špika A (2022) Yield and quality prediction of winter rapeseed: artificial neural network and random forest models. Agronomy 12, 58.
| Crossref | Google Scholar |
Resende MDVd, Duarte JB (2007) Precisão e controle de qualidade em experimentos de avaliação de cultivares. Pesquisa Agropecuária Tropical 37, 182-194 [In Spanish].
| Google Scholar |
Resende MDV, Silva FF, Azevedo CF (2014) Estatística matemática, biométrica e computacional: modelos mistos, multivariados, categóricos e generalizados (REML/BLUP), inferência bayesiana, regressão aleatória, seleção genômica, qtl-gwas, estatística espacial e temporal, competição, sobrevivência. Editora UFV, Viçosa, MG, Brazil. [in Portuguese]
Robinson HF, Comstock RE, Harvey PH (1949) Estimates of heritability and the degree of dominance in corn. Agronomy Journal 41, 353-359.
| Crossref | Google Scholar |
Rocha JRDASDC, Machado JC, Carneıro PCS (2018) Multitrait index based on factor analysis and ideotype-design: proposal and application on elephant grass breeding for bioenergy. GCB Bioenergy 10, 52-60.
| Crossref | Google Scholar |
Singh B, Kumar V, Mishra SP (2021) Genetic variability, path analysis and relationship among quantitative traits in chickpea (Cicer arietinum L.) genotypes. The Pharma Innovation Journal 10, 1564-1568.
| Google Scholar |
Strobl C, Boulesteix A-L, Kneib T, Augustin T, Zeileis A (2008) Conditional variable importance for random forests. BMC Bioinformatics 9, 307.
| Crossref | Google Scholar |
Subramanian M, Sivasubramanian P (1975) X-ray-induced fused perianth in Ricinus communis (L). Radiation Botany 15, 307-308.
| Crossref | Google Scholar |
Tunc M, Rufaioglu SB, Ipekesen S, Yakar M, Yorulmaz L, Bicer BT (2025) Evaluation of the possibility of using fuzzy C-means clustering, AMMI analysis and GGE biplot methods to predict the yield of chickpea genotypes cultivated in different environments. Agronomy 15, 300.
| Crossref | Google Scholar |
Tutlani A, Kumar R, Banshidhar , Kumari S, Chouhan S (2023) Correlation and path analysis for yield and its phenological, physiological, morphological and biochemical traits under salinity stress in chickpea (Cicer arietinum L.). IJBSM 14, 878-890.
| Crossref | Google Scholar |
Vigneshwari R, Shanthi RM, Pathy TL, Mohanraj K (2025) Estimates of genetic parameters and prediction of breeding values among full-sib sugarcane families for commercial cane sugar yield traits through REML/BLUP analysis. Sugar Tech 27, 67-77.
| Crossref | Google Scholar |
Ward JH, Jr (1963) Hierarchical grouping to optimize an objective function. Journal of the American Statistical Association 58, 236-244.
| Crossref | Google Scholar |
Woyann LG, Meira D, Matei G, Zdziarski AD, Dallacorte LV, Madella LA, Benin G (2020) Selection indexes based on linear–bilinear models applied to soybean breeding. Agronomy Journal 112, 175-182.
| Crossref | Google Scholar |
Xposit team (2025) RStudio: Integrated Development Environment for R. Posit Software, PBC, Boston, MA, USA. Available at http://www.posit.co/
Ying X (2019) An overview of overfitting and its solutions. Journal of Physics: Conference Series 1168, 022022.
| Crossref | Google Scholar |
Yorulmaz L, Ipekesen S, Oner M, Akinci C, Bicer BT (2025) Screening of drought-tolerant level of some wheat cultivars (Triticum durum Desf.) under water stress. Journal of Animal & Plant Sciences 35, 197-208.
| Crossref | Google Scholar |
Zali H, Pour-Aboughadareh A, Gholipour A, Kohkan S, Barati A, Jabari M, et al. (2023) Selection of barley superior promising lines using selection indexes of multi-trait. SAPS 33, 1-16.
| Crossref | Google Scholar |
