Bhartiya Krishi Anusandhan Patrika

Bhartiya Krishi Anusandhan Patrika cover
Volume 41 · Issue 2 · 2026/04/08

Machine Learning Framework for Automated Simple Sequence Repeat (SSR) Marker Quality Assessment in Pigeonpea ( Cajanus cajan L.)

Madhu Bala Priyadarshi
126 Views

Submitted

2025/10/27

First Online

2026/04/08

doi

10.18805/BKAP892

Cite article - Madhu Bala Priyadarshi. (2026). Machine Learning Framework for Automated Simple Sequence Repeat (SSR) Marker Quality Assessment in Pigeonpea ( Cajanus cajan L.). Bhartiya Krishi Anusandhan Patrika. 41(2): 202–210. doi: 10.18805/BKAP892

Abstract

Background: Simple Sequence Repeat (SSR) markers are essential for molecular breeding in pigeonpea ( Cajanus cajan L.) compared to traditional development methods, which exhibit 30-70% marker failure rates. Moreover, no quantitative frameworks exist for predicting marker quality in this orphan legume crop. Therefore, the objective of this study was to develop the first machine learning framework for automated SSR marker quality prediction in pigeonpea and identify key determinants of marker success.

Methods: Fifteen predictive features were engineered features from 2,770 computationally designed pigeonpea SSR markers, including primer design parameters, compatibility metrics and SSR structural characteristics. Quality scores (0-100) integrated predicted amplification success, specificity and polymorphism likelihood. Three algorithms (Random forest, support vector regression, neural network) were trained using five-fold cross-validation.

Result: Support Vector Regression (SVR) achieved the best performance (R² = 0.487, MAE = 2.341, CV R² = 0.441± 0.032). Feature importance analysis revealed primer compatibility as the dominant predictor (72.9% combined importance): melting temperature difference (25.2%), average melting temperature (23.0%) and primer length difference (17.8%). The framework enables prioritization of top 554 markers (20%), potentially reducing experimental validation costs by 40-60%. This study presents the first quantitative framework for SSR marker quality assessment in pigeonpea. The finding that primer pair compatibility accounts for 72.9% of predictive importance fundamentally shifts understanding from individual primer optimization to primer pair harmony. This validated framework provides scalable methodology for resource-limited breeding programs and is transferable to other orphan legume species.

References

  1. Azodi, C.B., Tang, J. and Shiu, S.H. (2019). Opening the black box: Interpretable machine learning for geneticists. Trends in Genetics . 35(11): 852-870. Bohra, A., Jha, U.C., Godwin, I.D, and Varshney, R.K. (2020). Genomic interventions for sustainable agriculture. Plant Biotechnology Journal . 18(12): 2388-2405. Chowdhury, M.M., Haque, M.A., Malek, M.A. et al . (2020). Morphological and SSR marker based diversity analysis of lentil ( Lens esculenta ) genotypes using yield and yield contributing characters. Indian Journal of Agricultural Research . 54(4): 429-436. doi: 10.18805/IJARe.A-464 . Crossa, J., Pérez-Rodríguez, P., Cuevas, J. et al. (2017). Genomic selection in plant breeding: methods, models and perspectives. Trends in Plant Science. 22(11): 961-975. Crossa, J., Montesinos-López, O. A., Montesinos-López, A. et al. (2024). Expanding genomic prediction in plant breeding: Harnessing big data, machine learning and advanced software. Trends in Plant Science . 30(2): 163-181. Gupta, P.K., Rustgi, S., Sharma, S. et al. (2003). Transferable EST-SSR markers for the study of polymorphism and genetic diversity in bread wheat. Molecular Genetics and Genomics . 270(4): 315-323. Kaur, G., Sharma, S., Kahlon, J.G. and Dhillon, G.S. (2020). Genetic divergence studies through microsatellite markers in pigeonpea [ Cajanus cajan (L.) Millsp.]. Legume Research . 43(3): 312-319. doi: 10.18805/LR-4022 . Metagar, M.S. and Walikar, A.G. (2024). Machine learning models for plant disease prediction and detection: A review. Agricultural Science Digest . 44(4): 591-602. doi: 10.18805/ag.D-5893 . Montesinos-López, A., Crespo-Herrera, L., Dreisigacker, S. et al. (2024). Deep learning methods improve genomic prediction of wheat breeding. Frontiers in Plant Science. 15: 1324090. Mula, M.G., Saxena, R.K., Prabhavathi, A. et al. (2020). Analysis of genetic diversity and population structure of pigeonpea accessions using SSR markers. Plants. 9(12): 1643. Odeny, D.A. (2007). The potential of pigeonpea [ Cajanus cajan (L.) Millsp.] in Africa. Natural Resources Forum . 31(4): 297-305. Saxena, R.K., Penmetsa, R.V., Upadhyaya, H.D. et al . (2012). Large scale development of cost effective single nucleotide polymorphism marker assays for genetic mapping in pigeonpea. DNA Research . 19(6): 449-461. Singh, N., Rani, S., Sharma, A. et al. (2024). Ppomicsdb: A multi- omics database for genetic and molecular breeding applications in pigeonpea. Legume Science . 6(2): e220. Uma, M.S., Hegde, N. and Hittalmani, S. (2016). Identification of SSR marker associated with rust resistance in cowpea ( Vigna unguiculata L.) using bulk segregant analysis. Legume Research. 39(1): 39-42. doi: 10.18805/lr.v39i1.8861 . Squirrell, J., Hollingsworth, P.M., Woodhead, M. et al. (2003). How much effort is required to isolate nuclear microsatellites from plants? Molecular Ecology . 12(6): 1339-1348. Varshney, R.K., Chen, W., Li, Y. et al . (2012). Draft genome sequence of pigeonpea (Cajanus cajan), an orphan legume crop of resource-poor farmers. Nature Biotechnology . 30(1): 83-89. Wang, K., Abid, M.A., Rasheed, A., Crossa, J., Hearne, S. and Li, H. (2023). DNNGP, a deep neural network-based method for genomic prediction using multi-omics data in plants. Molecular Plant. 16(1): 279-293. Xu, Y., Zhang, X., Li, H., Zheng, H., Zhang, J., Olsen, M.S. et al . (2022). Smart breeding driven by big data, artificial intelligence and integrated genomic-enviromic prediction. Molecular Plant. 15(11): 1664-1695. Zavinon, F., Adoukonou-Sagbadja, H., Ahoton, L., Vodouhè, R. and Ahanhanzo, C. (2024). SSR-marker assisted evaluation of genetic diversity in local and exotic pigeonpea cultivars for parental genotypes selection. Journal of Agriculture and Food Researc h. 15: 100976.
EDITORIAL BOARD

Guided by Experienced Academic Leadership

Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.

View Full Board
Jerald Anthony C. Esteban
Associate chief editor

Jerald Anthony C. Esteban

Asst. ProfessorDAVAO DE ORO STATE COLLEGE, PHILIPPINES

M. L. Dotaniya
Editor

M. L. Dotaniya

Sr. ScientistICAR-Directorate of Rapeseed Mustard Research Sewar, Bharatpur

Polneni Jagan Mohan Rao
Editor

Polneni Jagan Mohan Rao

ProfessorProfessor Jayashankar Telangana state Agri. Uni.,Hyderabad, INDIA

Sarika
Editor

Sarika

Pr. ScientistCentre for Agri. Bioinformatics, IASRI, PUSA, New Delhi, INDIA