Machine learning: its challenges and opportunities in plant system biology.

Sequencing technologies are evolving at a rapid pace, enabling the generation of massive amounts of data in multiple dimensions (e.g., genomics, epigenomics, transcriptomic, metabolomics, proteomics, and single-cell omics) in plants. To provide comprehensive insights into the complexity of plant biological systems, it is important to integrate different omics datasets. Although recent advances in computational analytical pipelines have enabled efficient and high-quality exploration and exploitation of single omics data, the integration of multidimensional, heterogenous, and large datasets (i.e., multi-omics) remains a challenge. In this regard, machine learning (ML) offers promising approaches to integrate large datasets and to recognize fine-grained patterns and relationships. Nevertheless, they require rigorous optimizations to process multi-omics-derived datasets. In this review, we discuss the main concepts of machine learning as well as the key challenges and solutions related to the big data derived from plant system biology. We also provide in-depth insight into the principles of data integration using ML, as well as challenges and opportunities in different contexts including multi-omics, single-cell omics, protein function, and protein-protein interaction. KEY POINTS: • The key challenges and solutions related to the big data derived from plant system biology have been highlighted. • Different methods of data integration have been discussed. • Challenges and opportunities of the application of machine learning in plant system biology have been highlighted and discussed.

The transcriptional co-repressor SEED DORMANCY 4-LIKE (AtSDR4L) promotes the embryonic-to-vegetative transition in Arabidopsis thaliana.

Repression of embryonic traits during the seed-to-seedling phase transition requires the inactivation of master transcription factors associated with embryogenesis. How the timing of such inactivation is controlled is unclear. Here, we report on a novel transcriptional co-repressor, Arabidopsis thaliana SDR4L, that forms a feedback inhibition loop with the master transcription factors LEC1 and ABI3 to repress embryonic traits post-imbibition. LEC1 and ABI3 regulate their own expression by inducing AtSDR4L during mid to late embryogenesis. AtSDR4L binds to sites upstream of LEC1 and ABI4, and these transcripts are upregulated in Atsdr4l seedlings. Atsdr4l seedlings phenocopy a LEC1 overexpressor. The embryonic traits of Atsdr4l can be partially rescued by impairing LEC1 or ABI3. The penetrance and expressivity of the Atsdr4l phenotypes depend on both developmental and external cues, demonstrating the importance of AtSDR4L in seedling establishment under suboptimal conditions.

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.

Influence of functional groups in chemical reactivity and optoelectronic properties of novel glycidyl nitrate copolymers (GNCOP): a DFT study.

INTRODUCTION: Nowadays, propulsion materials are receiving increased attention as an important component in electric motors. So, awareness of their chemical reactivity and geometric and electronic structures can help to make materials with higher quality and efficiency. In this study, we have proposed novel glycidyl nitrate copolymers (GNCOPs) and meta-substituted derivatives as propulsion materials. METHOD: Based on density functional theory (DFT) method, chemical reactivity indices have been calculated for predicting their behavior in burning process. RESULT AND DISSCUSSION: Adding functional groups changes reactivity of the GNCOP compound, especially, in the -CN functional group, chemical potential, chemical hardness, and electrophilicity change -0.374, +0.007, and +1.342eV, respectively. In addition, these compounds have dual properties in interaction with oxygen molecule. Optoelectronic study in time-dependent DFT framework shows that there are three peaks with significant excitations. CONCLUSION: In conclusion, adding functional group into the GNCOPs can introduce new materials with high energetic properties.

Team effort: Combinatorial control of seed maturation by transcription factors.

Seed development is under tight spatiotemporal regulation. Here, we summarize how transcriptional regulation helps shape the major traits during seed maturation, which include storage reserve accumulation, dormancy, desiccation tolerance, and longevity. The regulation is rarely a solo task by an individual transcription factor (TF). Rather, it often involves coordinated recruitment or replacement of multiple TFs to achieve combinatorial regulation. We highlight recent progress on the transcriptional integration of activation and repression of seed maturation genes, and discuss potential research directions to further understand the TF networks of seed maturation.

A novel zero delay low pass filter: Application to precision positioning systems.

In this paper, a nonlinear low-pass filter is presented, which produces significantly less phase lag than linear and some nonlinear filters. The proposed filter employs a saturation function to enhance the linear filter's performance. The gain and phase responses of the filter are derived analytically using a modified describing function, and the efficiency of the proposed method is examined through numerical examples. Based on the required cut-off frequency and noise to signal ratio, a rule of thumb is given to set the filter's parameters. In the frequency domain, simulation results show that the filter's gain response is near 0dB in the pass-band, and the noise attenuation rate is -40dB∕dec, while the phase lag is three times lesser compared to 2nd order Butterworth low-pass filter. Moreover, comparing with Jin et al.'s parabolic sliding mode filter and feed-forwarded parabolic sliding mode filter the gain and phase of the proposed filter are closer to zero in the pass-band and before cut-off frequency. Furthermore, the filter's performance is also evaluated in case of different noise color and concluded that the proposed filter is superior to linear and nonlinear filters in case of white, blue, or purple noise Finally, the filter's effectiveness and the tuning guideline are validated by simulating a precision motion control system in the discrete-time domain.

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

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.

Effect of plant growth regulators on indirect shoot organogenesis of Ficus religiosa through seedling derived petiole segments.

Ficus religiosa is known as a long-lived multipurpose forest tree. The tree plays an important role for religious, medicinal, and ornamental purposes. However, the propagation rate of Ficus religiosa is low in natural habitat so the plant tissue culture techniques are an applicable method for multiplication of this valuable medicinal plants. Thus, the aim of this study is to understand the effect of different auxin/cytokinin ratios on indirect shoot organogenesis of this plant. According to our results, the maximum callus induction frequency (100%) was obtained on Murashige and Skoog (MS) medium supplemented with 0.5 mg/l 2,4-dichlorophenoxyacetic acid (2,4-D) plus 0.05 mg/l 6-benzylaminopurine (BAP) from petiole segments. For shoot induction purpose, the yellow-brownish, friable, organogenic calli were inoculated on shoot induction medium. On MS medium supplemented with 1.5 mg/l BAP and 0.15 mg/l Indole-3-butyric acid (IBA), 96.66% of the petiole-derived calli responded with an average number of 3.56 shoots per culture. The highest root formation frequency (96.66%), root number (5.5), and root length (4.83 cm) were achieved on MS medium containing 2.0 mg/l IBA plus 0.1 mg/l Naphthaleneacetic acid (NAA). The rooted shoots were successfully transferred to field condition and the substrate with the mixture of cocopeat and perlite (1:1) had the highest survival rate (96.66%). This is the first report of an effective in vitro organogenesis protocol for F. religiosa by indirect shoot organogenesis through axenic seedling derived petiole explants, which can be efficiently employed for conservation of this important medicinal plant species as well as the utilization of active biomolecules.