Introducing a hybrid artificial intelligence method for high-throughput modeling and optimizing plant tissue culture processes: the establishment of a new embryogenesis medium for chrysanthemum, as a case study

Lentinula edodes substrate formulation using multilayer perceptron-genetic algorithm: a critical production checkpoint

Shiitake (Lentinula edodes) is one of the most widely grown and consumed mushroom species worldwide. They are a potential source of food and medicine because they are rich in nutrients and contain various minerals, vitamins, essential macro- and micronutrients, and bioactive compounds. The reuse of agricultural and industrial residues is crucial from an ecological and economic perspective. In this study, the running length (RL) of L. edodes cultured on 64 substrate compositions obtained from different ratios of bagasse (B), wheat bran (WB), and beech sawdust (BS) was recorded at intervals of 5 days after cultivation until the 40th day. Multilayer perceptron-genetic algorithm (MLP-GA), multiple linear regression, stepwise regression, principal component regression, ordinary least squares regression, and partial least squares regression were used to predict and optimize the RL and running rate (RR) of L. edodes. The statistical values showed higher prediction accuracies of the MLP-GA models (92% and 97%, respectively) compared with those of the regression models (52% and 71%, respectively) for RL and RR. The high degree of fit between the forecasted and actual values of the RL and RR of L. edodes confirmed the superior performance of the developed MLP-GA models. An optimization analysis on the established MLP-GA models showed that a substrate containing 15.1% B, 45.1% WB, and 10.16% BS and a running time of 28 days and 10 h could result in the maximum L. edodes RL (10.69 cm). Moreover, the highest RR of L. edodes (0.44 cm d-1) could be obtained by a substrate containing 30.7% B, 90.4% WB, and 0.0% BS. MLP-GA was observed to be an effective method for predicting and consequently selecting the best substrate composition for the maximal RL and RR of L. edodes.

Machine learning-mediated Passiflora caerulea callogenesis optimization

Callogenesis is one of the most powerful biotechnological approaches for in vitro secondary metabolite production and indirect organogenesis in Passiflora caerulea. Comprehensive knowledge of callogenesis and optimized protocol can be obtained by the application of a combination of machine learning (ML) and optimization algorithms. In the present investigation, the callogenesis responses (i.e., callogenesis rate and callus fresh weight) of P. caerulea were predicted based on different types and concentrations of plant growth regulators (PGRs) (i.e., 2,4-dichlorophenoxyacetic acid (2,4-D), 6-benzylaminopurine (BAP), 1-naphthaleneacetic acid (NAA), and indole-3-Butyric Acid (IBA)) as well as explant types (i.e., leaf, node, and internode) using multilayer perceptron (MLP). Moreover, the developed models were integrated into the genetic algorithm (GA) to optimize the concentration of PGRs and explant types for maximizing callogenesis responses. Furthermore, sensitivity analysis was conducted to assess the importance of each input variable on the callogenesis responses. The results showed that MLP had high predictive accuracy (R2 > 0.81) in both training and testing sets for modeling all studied parameters. Based on the results of the optimization process, the highest callogenesis rate (100%) would be obtained from the leaf explant cultured in the medium supplemented with 0.52 mg/L IBA plus 0.43 mg/L NAA plus 1.4 mg/L 2,4-D plus 0.2 mg/L BAP. The results of the sensitivity analysis showed the explant-dependent impact of the exogenous application of PGRs on callogenesis. Generally, the results showed that a combination of MLP and GA can display a forward-thinking aid to optimize and predict in vitro culture systems and consequentially cope with several challenges faced currently in Passiflora tissue culture.

Enhancing petunia tissue culture efficiency with machine learning: A pathway to improved callogenesis

The important feature of petunia in tissue culture is its unpredictable and genotype-dependent callogenesis, posing challenges for efficient regeneration and biotechnology applications. To address this issue, machine learning (ML) can be considered a powerful tool to analyze callogenesis data, extract key parameters, and predict optimal conditions for petunia callogenesis, facilitating more controlled and productive tissue culture processes. The study aimed to develop a predictive model for callogenesis in petunia using ML algorithms and to optimize the concentrations of phytohormones to enhance callus formation rate (CFR) and callus fresh weight (CFW). The inputs for the model were BAP, KIN, IBA, and NAA, while the outputs were CFR and CFW. Three ML algorithms, namely MLP, RBF, and GRNN, were compared, and the results revealed that GRNN (R2≥83) outperformed MLP and RBF in terms of accuracy. Furthermore, a sensitivity analysis was conducted to determine the relative importance of the four phytohormones. IBA exhibited the highest importance, followed by NAA, BAP, and KIN. Leveraging the superior performance of the GRNN model, a genetic algorithm (GA) was integrated to optimize the concentration of phytohormones for maximizing CFR and CFW. The genetic algorithm identified an optimized combination of phytohormones consisting of 1.31 mg/L BAP, 1.02 mg/L KIN, 1.44 mg/L NAA, and 1.70 mg/L IBA, resulting in 95.83% CFR. To validate the reliability of the predicted results, optimized combinations of phytohormones were tested in a laboratory experiment. The results of the validation experiment indicated no significant difference between the experimental and optimized results obtained through the GA. This study presents a novel approach combining ML, sensitivity analysis, and GA for modeling and predicting callogenesis in petunia. The findings offer valuable insights into the optimization of phytohormone concentrations, facilitating improved callus formation and potential applications in plant tissue culture and genetic engineering.

Prediction and optimization of indirect shoot regeneration of Passiflora caerulea using machine learning and optimization algorithms

BACKGROUND

Optimization of indirect shoot regeneration protocols is one of the key prerequisites for the development of Agrobacterium-mediated genetic transformation and/or genome editing in Passiflora caerulea. Comprehensive knowledge of indirect shoot regeneration and optimized protocol can be obtained by the application of a combination of machine learning (ML) and optimization algorithms.

MATERIALS AND METHODS

In the present investigation, the indirect shoot regeneration responses (i.e., de novo shoot regeneration rate, the number of de novo shoots, and length of de novo shoots) of P. caerulea were predicted based on different types and concentrations of PGRs (i.e., TDZ, BAP, PUT, KIN, and IBA) as well as callus types (i.e., callus derived from different explants including leaf, node, and internode) using generalized regression neural network (GRNN) and random forest (RF). Moreover, the developed models were integrated into the genetic algorithm (GA) to optimize the concentration of PGRs and callus types for maximizing indirect shoot regeneration responses. Moreover, sensitivity analysis was conducted to assess the importance of each input variable on the studied parameters.

RESULTS

The results showed that both algorithms (RF and GRNN) had high predictive accuracy (R² > 0.86) in both training and testing sets for modeling all studied parameters. Based on the results of optimization process, the highest de novo shoot regeneration rate (100%) would be obtained from callus derived from nodal segments cultured in the medium supplemented with 0.77 mg/L BAP plus 2.41 mg/L PUT plus 0.06 mg/L IBA. The results of the sensitivity analysis showed the explant-dependent impact of exogenous application of PGRs on indirect de novo shoot regeneration.

CONCLUSIONS

A combination of ML (GRNN and RF) and GA can display a forward-thinking aid to optimize and predict in vitro culture systems and consequentially cope with several challenges faced currently in Passiflora tissue culture.

Riboflavin mediates m6A modification targeted by miR408, promoting early somatic embryogenesis in longan

Plant somatic embryogenesis (SE) is an in vitro biological process wherein bipolar structures are induced to form somatic cells and regenerate into whole plants. MicroRNA (miRNA) is an essential player in plant SE. However, the mechanism of microRNA408 (miR408) in SE remains elusive. Here, we used stable transgenic technology in longan (Dimocarpus longan) embryogenic calli to verify the mechanism by which miR408 promotes cell division and differentiation of longan early SE. dlo-miR408-3p regulated riboflavin biosynthesis by targeting nudix hydrolase 23 (DlNUDT23), a previously unidentified gene mediating N6-methyladenosine (m6A) modification and influencing RNA homeostasis and cell cycle gene expression during longan early SE. We showed that DlMIR408 overexpression (DlMIR408-OE) promoted 21-nt miRNA biosynthesis. In DlMIR408-OE cell lines, dlo-miR408-3p targeted and downregulated DlNUDT23, promoted riboflavin biosynthesis, decreased flavin mononucleotide (FMN) accumulation, promoted m6A level, and influenced miRNA homeostasis. DNA replication, glycosylphosphatidylinositol (GPI)-anchor biosynthesis, the pentose phosphate pathway, and taurine and hypotaurine metabolism were also closely associated with riboflavin metabolism. In a riboflavin feeding assay, dlo-miR408-3p and pre-miR408 were upregulated and DlNUDT23 was downregulated, increasing the m6A level and cell division and differentiation in longan globular embryos. When riboflavin biosynthesis was inhibited, dlo-miR408-3p was downregulated and DlNUDT23 was upregulated, which decreased m6A modification and inhibited cell division but did not inhibit cell differentiation. FMN artificial demethylated m6A modification affected the homeostasis of precursor miRNA and miRNA. Our results revealed a mechanism underlying dlo-miR408-3p-activated riboflavin biosynthesis in which DlNUDT23 is targeted, m6A modification is dynamically mediated, and cell division is affected, promoting early SE in plants.

Machine Learning-Assisted Approaches in Modernized Plant Breeding Programs

In the face of a growing global population, plant breeding is being used as a sustainable tool for increasing food security. A wide range of high-throughput omics technologies have been developed and used in plant breeding to accelerate crop improvement and develop new varieties with higher yield performance and greater resilience to climate changes, pests, and diseases. With the use of these new advanced technologies, large amounts of data have been generated on the genetic architecture of plants, which can be exploited for manipulating the key characteristics of plants that are important for crop improvement. Therefore, plant breeders have relied on high-performance computing, bioinformatics tools, and artificial intelligence (AI), such as machine-learning (ML) methods, to efficiently analyze this vast amount of complex data. The use of bigdata coupled with ML in plant breeding has the potential to revolutionize the field and increase food security. In this review, some of the challenges of this method along with some of the opportunities it can create will be discussed. In particular, we provide information about the basis of bigdata, AI, ML, and their related sub-groups. In addition, the bases and functions of some learning algorithms that are commonly used in plant breeding, three common data integration strategies for the better integration of different breeding datasets using appropriate learning algorithms, and future prospects for the application of novel algorithms in plant breeding will be discussed. The use of ML algorithms in plant breeding will equip breeders with efficient and effective tools to accelerate the development of new plant varieties and improve the efficiency of the breeding process, which are important for tackling some of the challenges facing agriculture in the era of climate change.

Artificial neural network modeling for deciphering the in vitro induced salt stress tolerance in chickpea (Cicer arietinum L)

Salt stress is one of the most critical abiotic stresses having significant contribution in global agriculture production. Chickpea is sensitive to salt stress at various growth stages and a better knowledge of salt tolerance in chickpea would enable breeding of salt tolerant varieties. During present investigation, in vitro screening of desi chickpea by continuous exposure of seeds to NaCl-containing medium was performed. NaCl was applied in the MS medium at the rate of 6.25, 12.50, 25, 50, 75, 100, and 125 mM. Different germination indices and growth indices of roots and shoots were recorded. Mean germination (%) of roots and shoots ranged from 52.08 to 100%, and 41.67-100%, respectively. The mean germination time (MGT) of roots and shoots ranged from 2.40 to 4.78 d and 3.23-7.05 d. The coefficient of variation of the germination time (CVt) was recorded as 20.91-53.43% for roots, and 14.53-44.17% for shoots. The mean germination rate (MR) of roots was better than shoots. The uncertainty (U) values were tabulated as 0.43-1.59 (roots) and 0.92-2.33 (shoots). The synchronization index (Z) reflected the negative impact of elevated salinity levels on both root and shoot emergence. Application of NaCl exerted a negative impact on all growth indices compared to control and decreased gradually with elevated NaCl concentration. Results on salt tolerance index (STI) also revealed the reduced STI with elevated NaCl concentration and STI of roots was less than shoot. Elemental analysis revealed more Na and Cl accumulation with respective elevated NaCl concentrations. The In vitro growth parameters and STI values validated and predicted by multilayer perceptron (MLP) model revealed the relatively high R 2 values of all growth indices and STI. Findings of this study will be helpful to broaden the understanding about the salinity tolerance level of desi chickpea seeds under in vitro conditions using various germination indices and seedling growth indices.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12298-023-01282-z.

Comparative analysis of different artificial neural networks for predicting and optimizing in vitro seed germination and sterilization of petunia

The process of optimizing in vitro seed sterilization and germination is a complicated task since this process is influenced by interactions of many factors (e.g., genotype, disinfectants, pH of the media, temperature, light, immersion time). This study investigated the role of various types and concentrations of disinfectants (i.e., NaOCl, Ca(ClO)2, HgCl2, H2O2, NWCN-Fe, MWCNT) as well as immersion time in successful in vitro seed sterilization and germination of petunia. Also, the utility of three artificial neural networks (ANNs) (e.g., multilayer perceptron (MLP), radial basis function (RBF), and generalized regression neural network (GRNN)) as modeling tools were evaluated to analyze the effect of disinfectants and immersion time on in vitro seed sterilization and germination. Moreover, non‑dominated sorting genetic algorithm‑II (NSGA‑II) was employed for optimizing the selected prediction model. The GRNN algorithm displayed superior predictive accuracy in comparison to MLP and RBF models. Also, the results showed that NSGA‑II can be considered as a reliable multi-objective optimization algorithm for finding the optimal level of disinfectants and immersion time to simultaneously minimize contamination rate and maximize germination percentage. Generally, GRNN-NSGA-II as an up-to-date and reliable computational tool can be applied in future plant in vitro culture studies.

Chrysanthemum: A Comprehensive Review on Recent Developments on In Vitro Regeneration

Chrysanthemum is a flowering plant grown worldwide and is one of the most popular ornamental plants. Chrysanthemums are usually cultivated using root suckers and shoot cuttings. This conventional technique is relatively slow. In addition, as cuttings are gained regularly from mother plants, there is a chance of viral infection and degeneration, which raises the production cost. The hurdles mentioned above have been managed by applying in vitro propagation techniques, which can enhance reproduction rates through in vitro culture and use very small explants, which are impossible with the conventional approach. Usually, it is difficult to get true-to-type plants as the parents with good quality, but clonal propagation of a designated elite species makes it possible. Hence, this review highlights recent studies of the in vitro propagation of Chrysanthemum included; the appropriate explant sources, medium compositions, alternative disinfection of culture media, plant growth regulators (PGRs), different mutagenesis applications, acclimatization efficiency, and alternative light sources to overcome the shortcomings of conventional propagation techniques.

Mathematical modeling and optimizing the in vitro shoot proliferation of wallflower using multilayer perceptron non-dominated sorting genetic algorithm-II (MLP-NSGAII)

Novel computational methods such as artificial neural networks (ANNs) can facilitate modeling and predicting results of tissue culture experiments and thereby decrease the number of experimental treatments and combinations. The objective of the current study is modeling and predicting in vitro shoot proliferation of Erysimum cheiri (L.) Crantz, which is an important bedding flower and medicinal plant. Its micropropagation has not been investigated before and as a case study multilayer perceptron- non-dominated sorting genetic algorithm-II (MLP-NSGAII) can be applied. MLP was used for modeling three outputs including shoots number (SN), shoots length (SL), and callus weight (CW) based on four variables including 6-benzylaminopurine (BAP), kinetin (Kin), 1-naphthalene acetic acid (NAA) and gibberellic acid (GA₃). The R² correlation values of 0.84, 0.99 and 0.93 between experimental and predicted data were obtained for SN, SL, and CW, respectively. These results proved the high accuracy of MLP model. Afterwards the model connected to Non-dominated Sorting Genetic Algorithm-II (NSGA-II) was used to optimize input variables for obtaining the best predicted outputs. The results of sensitivity analysis indicated that SN and CW were more sensitive to BA, followed by Kin, NAA and GA. For SL, more sensitivity was obtained for GA₃ than NAA. The validation experiment indicated that the difference between the validation data and MLP-NSGAII predicted data were negligible. Generally, MLP-NSGAII can be considered as a powerful method for modeling and optimizing in vitro studies.

Innovation in the Breeding of Common Bean Through a Combined Approach of in vitro Regeneration and Machine Learning Algorithms

Common bean is considered a recalcitrant crop for in vitro regeneration and needs a repeatable and efficient in vitro regeneration protocol for its improvement through biotechnological approaches. In this study, the establishment of efficient and reproducible in vitro regeneration followed by predicting and optimizing through machine learning (ML) models, such as artificial neural network algorithms, was performed. Mature embryos of common bean were pretreated with 5, 10, and 20 mg/L benzylaminopurine (BAP) for 20 days followed by isolation of plumular apice for in vitro regeneration and cultured on a post-treatment medium containing 0.25, 0.50, 1.0, and 1.50 mg/L BAP for 8 weeks. Plumular apice explants pretreated with 20 mg/L BAP exerted a negative impact and resulted in minimum shoot regeneration frequency and shoot count, but produced longer shoots. All output variables (shoot regeneration frequency, shoot counts, and shoot length) increased significantly with the enhancement of BAP concentration in the post-treatment medium. Interaction of the pretreatment × post-treatment medium revealed the need for a specific combination for inducing a high shoot regeneration frequency. Higher shoot count and shoot length were achieved from the interaction of 5 mg/L BAP × 1.00 mg/L BAP followed by 10 mg/L BAP × 1.50 mg/L BAP and 20 mg/L BAP × 1.50 mg/L BAP. The evaluation of data through ML models revealed that R2 values ranged from 0.32 to 0.58 (regeneration), 0.01 to 0.22 (shoot counts), and 0.18 to 0.48 (shoot length). On the other hand, the mean squared error values ranged from 0.0596 to 0.0965 for shoot regeneration, 0.0327 to 0.0412 for shoot count, and 0.0258 to 0.0404 for shoot length from all ML models. Among the utilized models, the multilayer perceptron model provided a better prediction and optimization for all output variables, compared to other models. The achieved results can be employed for the prediction and optimization of plant tissue culture protocols used for biotechnological approaches in a breeding program of common beans.

Predictive modeling of Persian walnut (Juglans regia L.) in vitro proliferation media using machine learning approaches: a comparative study of ANN, KNN and GEP models

BACKGROUND

Optimizing plant tissue culture media is a complicated process, which is easily influenced by genotype, mineral nutrients, plant growth regulators (PGRs), vitamins and other factors, leading to undesirable and inefficient medium composition. Facing incidence of different physiological disorders such as callusing, shoot tip necrosis (STN) and vitrification (Vit) in walnut proliferation, it is necessary to develop prediction models for identifying the impact of different factors involving in this process. In the present study, three machine learning (ML) approaches including multi-layer perceptron neural network (MLPNN), k-nearest neighbors (KNN) and gene expression programming (GEP) were implemented and compared to multiple linear regression (MLR) to develop models for prediction of in vitro proliferation of Persian walnut (Juglans regia L.). The accuracy of developed models was evaluated using coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). With the aim of optimizing the selected prediction models, multi-objective evolutionary optimization algorithm using particle swarm optimization (PSO) technique was applied.

RESULTS

Our results indicated that all three ML techniques had higher accuracy of prediction than MLR, for example, calculated R² of MLPNN, KNN and GEP vs. MLR was 0.695, 0.672 and 0.802 vs. 0.412 in Chandler and 0.358, 0.377 and 0.428 vs. 0.178 in Rayen, respectively. The GEP models were further selected to be optimized using PSO. The comparison of modeling procedures provides a new insight into in vitro culture medium composition prediction models. Based on the results, hybrid GEP-PSO technique displays good performance for modeling walnut tissue culture media, while MLPNN and KNN have also shown strong estimation capability.

CONCLUSION

Here, besides MLPNN and GEP, KNN also is introduced, for the first time, as a simple technique with high accuracy to be used for developing prediction models in optimizing plant tissue culture media composition studies. Therefore, selection of the modeling technique to study depends on the researcher's desire regarding the simplicity of the procedure, obtaining clear results as entire formula and/or less time to analyze.

AGL15 Promotion of Somatic Embryogenesis: Role and Molecular Mechanism

Plants have amazing regenerative properties with single somatic cells, or groups of cells able to give rise to fully formed plants. One means of regeneration is somatic embryogenesis, by which an embryonic structure is formed that "converts" into a plantlet. Somatic embryogenesis has been used as a model for zygotic processes that are buried within layers of maternal tissues. Understanding mechanisms of somatic embryo induction and development are important as a more accessible model for seed development. We rely on seed development not only for most of our caloric intake, but also as a delivery system for engineered crops to meet agricultural challenges. Regeneration of transformed cells is needed for this applied work as well as basic research to understand gene function. Here we focus on a MADS-domain transcription factor, AGAMOUS-Like15 (AGL15) that shows a positive correlation between accumulation levels and capacity for somatic embryogenesis. We relate AGL15 function to other transcription factors, hormones, and epigenetic modifiers involved in somatic embryo development.

Development of a novel noninvasive quantitative method to monitor Siraitia grosvenorii cell growth and browning degree using an integrated computer-aided vision technology and machine learning

The rapid, accurate and noninvasive detection of biomass and plant cell browning can provide timely feedback on cell growth in plant cell culture. In this study, Siraitia grosvenorii suspension cells were taken as an example, a phenotype analysis platform was successfully developed to predict the biomass and the degree of cell browning based on the color changes of cells in computer-aided vision technology. First, a self-made laboratory system was established to obtain images. Then, matrices were prepared from digital images by a self-developed high-throughput image processing tool. Finally, classification models were used to judge different cell types, and then a semi-supervised classification to predict different degrees of cell browning. Meanwhile, regression models were developed to predict the plant cell mass. All models were verified with a good agreement by biological experiments. Therefore, this method can be applied for low-cost biomass estimation and browning degree quantification in plant cell culture.

Modeling and optimizing callus growth and development in Cannabis sativa using random forest and support vector machine in combination with a genetic algorithm

Plant callus is generally considered to be a mass of undifferentiated cells and can be used for secondary metabolite production, physiological studies, and plant transformation/regeneration. However, there are several types of callus with different morphological and developmental characteristics and not all are suitable for all applications. Callogenesis is a multivariable developmental process affected by several intrinsic and extrinsic factors, but the most important driver is plant growth regulator (PGRs) levels and type. Since callogenesis is a non-linear process influenced by many different factors, robust computational methods such as machine learning algorithms have great potential to model, predict, and optimize callus growth and development. The current study was conducted to evaluate the effect of PGRs on callus morphology in drug-type Cannabis sativa to maximize callus growth and promote embryogenic callus production. For this aim, random forest (RF) and support vector machine (SVM) were applied in conjunction with image processing to model and predict callus morphological and physical traits. The results showed that SVM was more accurate than RF. In order to find the optimal level of PGRs for optimizing callus growth and development, the SVM was linked to a genetic algorithm (GA). To confirm the reliability of SVM-GA, the optimized-predicted outcomes were tested in a validation experiment that revealed SVM-GA was able to accurately model and optimize the system. Moreover, our results showed that there is a significant correlation between embryogenic callus production and the true density of callus. KEY POINTS: • The effect of PGRs on callus growth and development of cannabis was studied. • The predictive accuracy of SVM and RF was evaluated and compared. • GA was linked to the SVM for optimizing the callus growth and development.

Advances and Perspectives in Tissue Culture and Genetic Engineering of Cannabis

For a long time, Cannabis sativa has been used for therapeutic and industrial purposes. Due to its increasing demand in medicine, recreation, and industry, there is a dire need to apply new biotechnological tools to introduce new genotypes with desirable traits and enhanced secondary metabolite production. Micropropagation, conservation, cell suspension culture, hairy root culture, polyploidy manipulation, and Agrobacterium-mediated gene transformation have been studied and used in cannabis. However, some obstacles such as the low rate of transgenic plant regeneration and low efficiency of secondary metabolite production in hairy root culture and cell suspension culture have restricted the application of these approaches in cannabis. In the current review, in vitro culture and genetic engineering methods in cannabis along with other promising techniques such as morphogenic genes, new computational approaches, clustered regularly interspaced short palindromic repeats (CRISPR), CRISPR/Cas9-equipped Agrobacterium-mediated genome editing, and hairy root culture, that can help improve gene transformation and plant regeneration, as well as enhance secondary metabolite production, have been highlighted and discussed.

Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits

Improving genetic yield potential in major food grade crops such as soybean (Glycine max L.) is the most sustainable way to address the growing global food demand and its security concerns. Yield is a complex trait and reliant on various related variables called yield components. In this study, the five most important yield component traits in soybean were measured using a panel of 250 genotypes grown in four environments. These traits were the number of nodes per plant (NP), number of non-reproductive nodes per plant (NRNP), number of reproductive nodes per plant (RNP), number of pods per plant (PP), and the ratio of number of pods to number of nodes per plant (P/N). These data were used for predicting the total soybean seed yield using the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Random Forest (RF), machine learning (ML) algorithms, individually and collectively through an ensemble method based on bagging strategy (E-B). The RBF algorithm with highest Coefficient of Determination (R2) value of 0.81 and the lowest Mean Absolute Errors (MAE) and Root Mean Square Error (RMSE) values of 148.61 kg.ha-1, and 185.31 kg.ha-1, respectively, was the most accurate algorithm and, therefore, selected as the metaClassifier for the E-B algorithm. Using the E-B algorithm, we were able to increase the prediction accuracy by improving the values of R2, MAE, and RMSE by 0.1, 0.24 kg.ha-1, and 0.96 kg.ha-1, respectively. Furthermore, for the first time in this study, we allied the E-B with the genetic algorithm (GA) to model the optimum values of yield components in an ideotype genotype in which the yield is maximized. The results revealed a better understanding of the relationships between soybean yield and its components, which can be used for selecting parental lines and designing promising crosses for developing cultivars with improved genetic yield potential.

Synergizing Off-Target Predictions for In Silico Insights of CENH3 Knockout in Cannabis through CRISPR/Cas

The clustered regularly interspaced short palindromic repeats (CRISPR)/Cas-mediated genome editing system has recently been used for haploid production in plants. Haploid induction using the CRISPR/Cas system represents an attractive approach in cannabis, an economically important industrial, recreational, and medicinal plant. However, the CRISPR system requires the design of precise (on-target) single-guide RNA (sgRNA). Therefore, it is essential to predict off-target activity of the designed sgRNAs to avoid unexpected outcomes. The current study is aimed to assess the predictive ability of three machine learning (ML) algorithms (radial basis function (RBF), support vector machine (SVM), and random forest (RF)) alongside the ensemble-bagging (E-B) strategy by synergizing MIT and cutting frequency determination (CFD) scores to predict sgRNA off-target activity through in silico targeting a histone H3-like centromeric protein, HTR12, in cannabis. The RF algorithm exhibited the highest precision, recall, and F-measure compared to all the tested individual algorithms with values of 0.61, 0.64, and 0.62, respectively. We then used the RF algorithm as a meta-classifier for the E-B method, which led to an increased precision with an F-measure of 0.62 and 0.66, respectively. The E-B algorithm had the highest area under the precision recall curves (AUC-PRC; 0.74) and area under the receiver operating characteristic (ROC) curves (AUC-ROC; 0.71), displaying the success of using E-B as one of the common ensemble strategies. This study constitutes a foundational resource of utilizing ML models to predict gRNA off-target activities in cannabis.

A hybrid model based on general regression neural network and fruit fly optimization algorithm for forecasting and optimizing paclitaxel biosynthesis in Corylus avellana cell culture

BACKGROUND

Paclitaxel is a well-known chemotherapeutic agent widely applied as a therapy for various types of cancers. In vitro culture of Corylus avellana has been named as a promising and low-cost strategy for paclitaxel production. Fungal elicitors have been reported as an impressive strategy for improving paclitaxel biosynthesis in cell suspension culture (CSC) of C. avellana. The objectives of this research were to forecast and optimize growth and paclitaxel biosynthesis based on four input variables including cell extract (CE) and culture filtrate (CF) concentration levels, elicitor adding day and CSC harvesting time in C. avellana cell culture, as a case study, using general regression neural network-fruit fly optimization algorithm (GRNN-FOA) via data mining approach for the first time.

RESULTS

GRNN-FOA models (0.88-0.97) showed the superior prediction performances as compared to regression models (0.57-0.86). Comparative analysis of multilayer perceptron-genetic algorithm (MLP-GA) and GRNN-FOA showed very slight difference between two models for dry weight (DW), intracellular and extracellular paclitaxel in testing subset, the unseen data. However, MLP-GA was slightly more accurate as compared to GRNN-FOA for total paclitaxel and extracellular paclitaxel portion in testing subset. The slight difference was observed in maximum growth and paclitaxel biosynthesis optimized by FOA and GA. The optimization analysis using FOA on developed GRNN-FOA models showed that optimal CE [4.29% (v/v)] and CF [5.38% (v/v)] concentration levels, elicitor adding day (17) and harvesting time (88 h and 19 min) can lead to highest paclitaxel biosynthesis (372.89 µg l^-1).

CONCLUSIONS

Great accordance between the predicted and observed values of DW, intracellular, extracellular and total yield of paclitaxel, and also extracellular paclitaxel portion support excellent performance of developed GRNN-FOA models. Overall, GRNN-FOA as new mathematical tool may pave the way for forecasting and optimizing secondary metabolite production in plant in vitro culture.

The Past, Present and Future of Cannabis sativa Tissue Culture

The recent legalization of Cannabis sativa L. in many regions has revealed a need for effective propagation and biotechnologies for the species. Micropropagation affords researchers and producers methods to rapidly propagate insect-/disease-/virus-free clonal plants and store germplasm and forms the basis for other biotechnologies. Despite this need, research in the area is limited due to the long history of prohibitions and restrictions. Existing literature has multiple limitations: many publications use hemp as a proxy for drug-type Cannabis when it is well established that there is significant genotype specificity; studies using drug-type cultivars are predominantly optimized using a single cultivar; most protocols have not been replicated by independent groups, and some attempts demonstrate a lack of reproducibility across genotypes. Due to culture decline and other problems, the multiplication phase of micropropagation (Stage 2) has not been fully developed in many reports. This review will provide a brief background on the history and botany of Cannabis as well as a comprehensive and critical summary of Cannabis tissue culture. Special attention will be paid to current challenges faced by researchers, the limitations of existing Cannabis micropropagation studies, and recent developments and future directions of Cannabis tissue culture technologies.

Efficient Cryopreservation of Populus tremula by In Vitro-Grown Axillary Buds and Genetic Stability of Recovered Plants

Axillary buds of in vitro microshoots were successfully frozen at -196 °C by the one-step freezing method using the protective vitrification solution 2 (PVS2). Microshoots were taken from 11 transgenic lines and three wild type lines. Influence of different explant pretreatments were analyzed from the point of their influence towards recovery after cryopreservation. It was found out that the use of axillary buds as explants after removal of the apical one increases recovery on average by 8%. The cultivation on growth medium of higher density insignificantly raises the regenerants survival rate. Pretreatment of the osmotic fluid (OF) shows the greatest influence on the survival rate. It leads to the increase in survival rate by 20%. The cryopreservation technology providing regenerants average survival rate of 83% was developed. It was based on the experimental results obtained with explant pretreatment. Incubation time in liquid nitrogen did not affect the explants survival rate after thawing. After six months cryostorage of samples their genetic variability was analyzed. Six variable simple sequence repeat (SSR) loci were used to analyze genotype variability after the freezing-thawing procedure. The microsatellite analysis showed the genetic status identity of plants after cryopreservation and of the original genotypes. The presence of the recombinant gene in the transgenic lines after cryostorage were confirmed so as the interclonal variation in the growth rate under greenhouse conditions. The developed technique is recommended for long-term storage of various breeding and genetically modified lines of aspen plants, as it provides a high percentage of explants survival with no changes in genotype.