Kivi’de (Actinidia deliciosa L.) Farklı Bitki Büyüme Düzenleyicilerine Karşı Polen Çimlenmesi ve Tüp Uzama Yanıtlarının Random Forest Regresyonu ile Tahmin Edilmesi

Öz

Bu çalışma, 24-epibrassinolid, metil jasmonat, spermidin, spermin ve putresinin 0.005, 0.05 ve 0.5 mM konsantrasyonlarında 3 saatlik invitro çimlenme sonunda elde edilen polen çimlenme oranı ve polen tüpü uzunluğu verilerini kullanarak Random Forest Regresyon modelini eğitmeyi ve modelin 0.025, 0.25 ve 2.5 mM konsantrasyonlarındaki yanıtları tahmin etme doğruluğunu değerlendirmeyi amaçlamıştır. Deneysel veriler model tahminleriyle karşılaştırılmış; modelin performansı mutlak hata ve kök ortalama kare hatası değerleriyle değerlendirilmiştir. Tahmin doğruluğu, hem polen çimlenmesi hem de polen tüpü uzunluğu için uygulanan ortak mutlak hata eşik değerleri (0-6, 6-15, ≥15) ile; polen çimlenmesi için ayrı olarak tanımlanan kök ortalama kare hatası eşik değerleri (0-10, 10-20, ≥20) ve polen tüpü uzunluğu için ayrı olarak tanımlanan kök ortalama kare hatası eşik değerleri (0-20, 20-40, ≥40) temel alınarak iyi, orta veya düşük olarak sınıflandırılmıştır. Bulgular, modelin düşük ve orta düzeydeki büyüme düzenleyici konsantrasyonlarında güvenilir tahminler sağladığını ve özellikle 24-epibrassinolid ile putresin uygulamalarında deneysel verilerle yüksek uyum gösterdiğini ortaya koymuştur. Ancak metil jasmonat, spermidin ve sperminin yüksek konsantrasyonlarında model, özellikle inhibitör dozlarda polen çimlenme oranlarını tahmin etmede aşırı tahmin eğilimi göstermiştir. Çalışma, polen biyolojisi araştırmalarında makine öğrenmesi yaklaşımlarının potansiyelini ortaya koymakta ve yüksek doz tahminlerinde model parametrelerinin optimize edilmesi gerekliliğine dikkat çekmektedir. Bu bulgular, yapay tozlaşma uygulamaları ve bitki büyüme düzenleyici stratejilerinde veri odaklı karar verme süreçlerinin entegrasyonuna katkı sağlamaktadır.

Anahtar Kelimeler

• 24-epibrassinolid
• Metil jasmonat
• Putresin
• Random Forest
• Spermin
• Spermidin

Predicting Pollen Germination and Tube Elongation Responses to Different Plant Growth Regulators in Kiwifruit (Actinidia deliciosa L.) Using Random Forest Regression

Abstract

This study aimed to train a Random Forest regression model using pollen germination rate and pollen tube length data obtained after 3 h of in vitro germination at 0.005, 0.05, and 0.5 mM concentrations of 24-epibrassinolide, methyl jasmonate, spermidine, spermine, and putrescine, and to evaluate the model’s accuracy in predicting responses at 0.025, 0.25, and 2.5 mM concentrations. Experimental data were compared with Random Forest Regression model predictions, and model performance was assessed using Absolute Error and Root Mean Square Error. Prediction accuracy was classified as good, moderate, or low based on Absolute Error thresholds applied to both pollen germination and pollen tube length (0-6, 6-15, ≥15), and Root Mean Square Error thresholds defined separately for pollen germination (0-10, 10-20, ≥20) and pollen tube length (0-20, 20-40, ≥40). Results indicated that the Random Forest Regression model provided reliable predictions at low and moderate plant growth regülatör concentrations, with 24-epibrassinolide and putrescine treatments aligning closely with experimental data. However, for methyl jasmonate, spermidine, and spermine at higher concentrations, the model exhibited overestimations, particularly in predicting pollen germination rates at inhibitory doses. The study highlights the potential of machine learning approaches in pollen biology research and demonstrates the necessity of optimizing model parameters for high-dose predictions. These findings contribute to the integration of data-driven decision-making in artificial pollination and plant growth regulators treatment strategies.

Keywords

• 24-epibrassinolide
• Methyl jasmonate
• Putrescine
• Random forest
• Spermine
• Spermidine

References

1. Abbate, A. P., Campbell, J. W., & Williams, G. R. (2023). Artificial pollination of kiwifruit (Actinidia chinensis Planch. var. chinensis) (Ericales: Actinidiaceae) results in greater fruit set compared to flowers pollinated by managed bees (Apis mellifera L. (Hymenoptera: Apidae) and Bombus impatiens Cresson (Hymenoptera: Apidae)). Journal of Economic Entomology, 116(3), 674-685. https://doi.org/10.1093/jee/toad044
2. Benkő, P., Jee, S., Kaszler, N., Fehér, A., & Gémes, K. (2020). Polyamines treatment during pollen germination and pollen tube elongation in tobacco modulate reactive oxygen species and nitric oxide homeostasis. Journal of Plant Physiology, 244, 153085. https://doi.org/10.1016/j.jplph.2019.153085
3. Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324 Broussard, M. A., Coates, M., & Martinsen, P. (2023). Artificial pollination technologies: A Review. Agronomy, 13(5), 1351. https://doi.org/10.3390/agronomy13051351
4. Carrizo García, C., Nepi, M., & Pacini, E. (2017). It is a matter of timing: asynchrony during pollen development and its consequences on pollen performance in angiosperms-a review. Protoplasma, 254(1), 57-73. https://doi.org/10.1007/s00709-016-0950-6
5. Castro, H., Siopa, C., Casais, V., Castro, M., Loureiro, J., Gaspar, H. & Castro, S. (2021). Pollination as a key management tool in crop production: Kiwifruit orchards as a study case. Scientia Horticulturae, 290, 110533. https://doi.org/10.1016/j.scienta.2021.110533
6. Chautá-Mellizo, A., Campbell, S. A., Bonilla, M. A., Thaler, J. S., & Poveda, K. (2012). Effects of natural and artificial pollination on fruit and offspring quality. Basic and Applied Ecology, 13(6), 524-532. https://doi.org/10.1016/j.baae.2012.08.013
7. Çetinbaş-Genç, A., & Vardar, F. (2020). Effect of methyl jasmonate on in-vitro pollen germination and tube elongation of Pinus nigra. Protoplasma, 257(6), 1655-1665. https://doi.org/10.1007/s00709-020-01539-4
8. Çetinbaş-Genç, A., Cai, G., Vardar, F., & Ünal, M. (2019). Differential effects of low and high temperature stress on pollen germination and tube length of hazelnut (Corylus avellana L.) genotypes. Scientia Horticulturae, 255, 61-69. https://doi.org/10.1016/j.scienta.2019.05.024

9. Grouh, M. S. H., Vahdati, K., Lotfi, M., Hassani, D., & Biranvand, N. P. (2011). Production of haploids in Persian walnut through parthenogenesis induced by gamma-irradiated pollen. Journal of the American Society for Horticultural Science, 136(3), 198-204. https://doi.org/10.21273/JASHS.136.3.198 Güçlü, S. F. (2025). Modelling of pome fruit pollen performance using machine learning. Scientific Reports, 15(1), 6913. https://doi.org/10.1038/s41598-025-91286-4
10. Güçlü, S. F., Öncü, Z., & Koyuncu, F. (2020). Pollen performance modelling with an artificial neural network on commercial stone fruit cultivars. Horticulture, Environment, and Biotechnology, 61(1), 61-67. https://doi.org/10.1007/s13580-019-00208-7
11. Güçlü, S. F., Sarıkaya, A. G., & Koyuncu, F. (2018). Pollen performances of naturally grown blackberries in Isparta-Turkey. Scientific Papers, 141.
12. Johnson, M. A., Harper, J. F., & Palanivelu, R. (2019). A fruitful journey: Pollen tube navigation from germination to fertilization. Annual Review of Plant Biology, 70, 809-837. https://doi.org/10.1146/annurev-arplant-050718-100133
13. Kweon, H. J., Park, M. Y., Song, Y. Y., Son, K. M., & Sagong, D. H. (2016). Influence of temperature and plant growth regulators on pollen germination and pollen tube growth of apple cultivars bred in Korea. Journal of Bio-Environment Control, 25(3), 184-192. https://doi.org/10.12791/KSBEC.2016.25.3.184 Liu, Y., Zhou, J., Lu, M., Yang, J., & Tan, X. (2022). The Core jasmonic acid-signalling module CoCOI1/CoJAZ1/CoMYC2 are involved in Jas mediated growth of the pollen tube in Camellia oleifera. Current Issues in Molecular Biology, 44(11), 5405-5415. https://doi.org/10.3390/cimb44110366
14. Muradoğlu, F., Yıldız, K., & Balta, F. (2010). Methyl jasmonate influences of pollen germination and pollen tube growth of apricot (Prunus armeniaca L.). Yuzuncu Yil University Journal of Agricultural Sciences, 20, 183-188.
15. Oh, E. U., Kim, S. C., Lee, M. H., & Song, K. J. (2022). Pollen application methods affecting fruit quality and seed formation in artificial pollination of yellow-fleshed kiwifruit. Horticulturae, 8(2), 150. https://doi.org/10.3390/horticulturae8020150
16. Sáez, A., Negri, P., Viel, M., & Aizen, M. A. (2019). Pollination efficiency of artificial and bee pollination practices in kiwifruit. Scientia Horticulturae, 246, 1017-1021. https://doi.org/10.1016/j.scienta.2018.11.072
17. Scoccianti, V., Iacobucci, M., Speranza, A., & Antognoni, F. (2013). Over-accumulation of putrescine induced by cyclohexylamine interferes with chromium accumulation and partially restores pollen tube growth in Actinidia deliciosa. Plant Physiology and Biochemistry, 70, 424-432. https://doi.org/10.1016/j.plaphy.2013.06.004
18. Shastri, K. V., Bhatia, V., Parikh, P. R., & Chaphekar, V. N. (2012). Actinidia deliciosa: A review. International Journal of Pharmaceutical Sciences and Research, 3(10), 3543.
19. Sorkheh, K., Shiran, B., Rouhi, V., Khodambashi, M., Wolukau, J. N., & Ercisli, S. (2011). Response of in vitro pollen germination and pollen tube growth of almond (Prunus dulcis Mill.) to temperature, polyamines and polyamine synthesis inhibitor. Biochemical Systematics and Ecology, 39(4-6), 749-757. https://doi.org/10.1016/j.bse.2011.06.015
20. Sotomayor, C., Castro, J., Velasco, N., & Toro, R. (2012). Influence of seven growth regulators on fruit set, pollen germination and pollen tube growth of almonds. Journal of Agricultural Science and Technology B, 2(9B), 1051.
21. Speranza, A., Crinelli, R., Scoccianti, V., & Geitmann, A. (2012). Reactive oxygen species are involved in pollen tube initiation in kiwifruit. Plant Biology, 14(1), 64-76. https://doi.org/10.1111/j.1438-8677.2011.00479.x
22. Sun, H., Liao, K., An, X., Cheng, X., Liu, J., & Qiu, C. (2013). Influence of plant growth regulators on pollen germination and growth of Xinjiang apricots. Agricultural Science & Technology, 14(2), 262.
23. Tacconi, G., Michelotti, V., Cacioppo, O., & Vittone, G. (2016). Kiwifruit pollination: The interaction between pollen quality, pollination systems and flowering stage. Journal of Berry Research, 6(4), 417-426. https://doi.org/10.3233/JBR-16013
24. Vogler, F., Schmalzl, C., Englhart, M., Bircheneder, M., & Sprunck, S. (2014). Brassinosteroids promote Arabidopsis pollen germination and growth. Plant Reproduction, 27, 153-167. https://doi.org/10.1007/s00497-014-0247-x
25. Zenginbal, H., & Özcan, M. (2005). Kivinin (Actinidia chinensis Planch.) döllenme biyolojisi. Anadolu Tarım Bilimleri Dergisi, 20(2), 98-105. https://doi.org/10.7161/anajas.2005.20.2.98-105