Forecasting and optimizing Agrobacterium-mediated genetic transformation via ensemble model- fruit fly optimization algorithm: A data mining approach using chrysanthemum databases.

Mohsen Hesami,Milad Alizadeh,Masoud Tohidfar,Roohangiz Naderi,Vijay Kumar

doi:10.1371/journal.pone.0239901

Mohsen Hesami, Milad Alizadeh + Show 3 more

Open Access

https://doi.org/10.1371/journal.pone.0239901

Copy DOI

Abstract

Optimizing the gene transformation factors can be considered as the first and foremost step in successful genetic engineering and genome editing studies. However, it is usually difficult to achieve an optimized gene transformation protocol due to the cost and time-consuming as well as the complexity of this process. Therefore, it is necessary to use a novel computational approach such as machine learning models for analyzing gene transformation data. In the current study, three individual machine learning models including Multi-Layer Perceptron (MLP), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Radial Basis Function (RBF) were developed for forecasting Agrobacterium-mediated gene transformation in chrysanthemum based on eleven input variables including Agrobacterium strain, optical density (OD), co-culture period (CCP), and different antibiotics including kanamycin (K), vancomycin (VA), cefotaxime (CF), hygromycin (H), carbenicillin (CA), geneticin (G), ticarcillin (TI), and paromomycin (P). Consequently, best-obtained results were used in the fusion process by bagging method. Results showed that ensemble model with the highest R2 (0.83) had superb performance in comparison with all other individual models (MLP:063, RBF:0.69, and ANFIS: 0.74) in the validation set. Also, ensemble model was linked to Fruit fly optimization algorithm (FOA) for optimizing gene transformation, and the results showed that the maximum gene transformation efficiency (37.54%) can be achieved from EHA105 strain with 0.9 OD600, for 3.8 days CCP, 46.43 mg/l P, 9.54 mg/l K, 18.62 mg/l H, and 4.79 mg/l G as selection antibiotics and 109.74 μg/ml VA, 287.63 μg/ml CF, 334.07 μg/ml CA and 87.36 μg/ml TI as antibiotics in the selection medium. Moreover, sensitivity analysis demonstrated that input variables have a different degree of importance in gene transformation system in the order of Agrobacterium strain > CCP > K > CF > VA > P > OD > CA > H > TI > G. Generally, the developed hybrid model in this study (ensemble model-FOA) can be employed as an accurate and reliable approach in future genetic engineering and genome editing studies.

Highlights

Horticulture plants including fruits, vegetables, grapes, and ornamental plants are raw material and used by people for food, either as edible products or for culinary ingredients, for medicinal use or ornamental and aesthetic purposes
Three individual models including Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), and Adaptive Neuro-Fuzzy Inference System (ANFIS) were applied for forecasting gene transformation efficiency in chrysanthemum based on eleven inputs including Agrobacterium strain, optical density (OD), co-culture period (CCP), and different antibiotics including kanamycin (K), vancomycin (VA), cefotaxime (CF), hygromycin (H), carbenicillin (CA), geneticin (G), ticarcillin (TI), and paromomycin (P)
All the R2 of testing, training, and validation datasets were over 63%, 69%, and 73% for MLP, RBF, and ANFIS models, respectively (Table 1)

Summary

Introduction

Horticulture plants including fruits, vegetables, grapes, and ornamental plants are raw material and used by people for food, either as edible products or for culinary ingredients, for medicinal use or ornamental and aesthetic purposes. Optimizing the gene transformation protocol can be considered as the first and foremost step in successful genetic engineering and gene editing studies [6, 7]. Many factors such as in vitro regeneration parameters (temperature, type and age of explant, quality and intensity of light, type and concentration of plant growth regulators, medium compositions), bacterial optical cell density, antibiotic and chemical stimulants concentrations, and inoculation duration (immersion time), play an important role in the efficiency of gene transformation [5]. Machine learning algorithms as a non-linear approach can be considered as a suitable computational methodology for predicting and optimizing different complex biological systems. Data mining can be applied to generate and model rules able to enhance knowledge or further insight from experimental data [21]

Methods

Results

Discussion

Conclusion