Advantages of neurofuzzy logic against conventional experimental design and statistical analysis in studying and developing direct compression formulations

Engineering mannose-functionalized nanostructured lipid carriers by sequential design using hybrid artificial intelligence tools

Nanostructured lipid carriers (NLCs) hold significant promise as drug delivery systems (DDS) owing to their small size and efficient drug-loading capabilities. Surface functionalization of NLCs can facilitate interaction with specific cell receptors, enabling targeted cell delivery. Mannosylation has emerged as a valuable tool for increasing the ability of nanoparticles to be recognized and internalized by macrophages. Nevertheless, the design and development of functionalized NLC is a complex task that entails the optimization of numerous variables and steps, making the process challenging and time-consuming. Moreover, no previous studies have been focused on evaluating the functionalization efficiency. In this work, hybrid Artificial Intelligence technologies are used to help in the design of mannosylated drug loaded NLCs. Artificial neural networks combined with fuzzy logic or genetic algorithms were employed to understand the particle formation processes and optimize the combinations of variables for the different steps in the functionalization process. Mannose was chemically modified to allow, for the first time, functionalization efficiency quantification and optimization. The proposed sequential methodology has enabled the design of a robust procedure for obtaining stable mannosylated NLCs with a uniform particle size distribution, small particle size (< 100 nm), and a substantial positive zeta potential (> 20mV). The incorporation of mannose on the surfaces of these DDS following the established protocols achieved > 85% of functionalization efficiency. This high effectiveness should enhance NLC recognition and internalization by macrophages, thereby facilitating the treatment of chronic inflammatory diseases.

Prediction of potentially toxic elements in water resources using MLP-NN, RBF-NN, and ANFIS: a comprehensive review

Water resources are constantly threatened by pollution of potentially toxic elements (PTEs). In efforts to monitor and mitigate PTEs pollution in water resources, machine learning (ML) algorithms have been utilized to predict them. However, review studies have not paid attention to the suitability of input variables utilized for PTE prediction. Therefore, the present review analyzed studies that employed three ML algorithms: MLP-NN (multilayer perceptron neural network), RBF-NN (radial basis function neural network), and ANFIS (adaptive neuro-fuzzy inference system) to predict PTEs in water. A total of 139 models were analyzed to ascertain the input variables utilized, the suitability of the input variables, the trends of the ML model applications, and the comparison of their performances. The present study identified seven groups of input variables commonly used to predict PTEs in water. Group 1 comprised of physical parameters (P), chemical parameters (C), and metals (M). Group 2 contains only P and C; Group 3 contains only P and M; Group 4 contains only C and M; Group 5 contains only P; Group 6 contains only C; and Group 7 contains only M. Studies that employed the three algorithms proved that Groups 1, 2, 3, 5, and 7 parameters are suitable input variables for forecasting PTEs in water. The parameters of Groups 4 and 6 also proved to be suitable for the MLP-NN algorithm. However, their suitability with respect to the RBF-NN and ANFIS algorithms could not be ascertained. The most commonly predicted PTEs using the MLP-NN algorithm were Fe, Zn, and As. For the RBF-NN algorithm, they were NO3, Zn, and Pb, and for the ANFIS, they were NO3, Fe, and Mn. Based on correlation and determination coefficients (R, R2), the overall order of performance of the three ML algorithms was ANFIS > RBF-NN > MLP-NN, even though MLP-NN was the most commonly used algorithm.

History, Phylogeny, Biodiversity, and New Computer-Based Tools for Efficient Micropropagation and Conservation of Pistachio (Pistacia spp.) Germplasm

The word "pstk" [pistag], used in the ancient Persian language, is the linguistic root from which the current name "pistachio", used worldwide, derives. The word pistachio is generally used to designate the plants and fruits of a single species: Pistacia vera L. Both the plant and its fruits have been used by mankind for thousands of years, specifically the consumption of its fruits by Neanderthals has been dated to about 300,000 years ago. Native to southern Central Asia (including northern Afghanistan and northeastern Iran), its domestication and cultivation occurred about 3000 years ago in this region, spreading to the rest of the Mediterranean basin during the Middle Ages and finally being exported to America and Australia at the end of the 19th century. The edible pistachio is an excellent source of unsaturated fatty acids, carbohydrates, proteins, dietary fiber, vitamins, minerals and bioactive phenolic compounds that help promote human health through their antioxidant capacity and biological activities. The distribution and genetic diversity of wild and domesticated pistachios have been declining due to increasing population pressure and climatic changes, which have destroyed natural pistachio habitats, and the monoculture of selected cultivars. As a result, the current world pistachio industry relies mainly on a very small number of commercial cultivars and rootstocks. In this review we discuss and summarize the current status of: etymology, origin, domestication, taxonomy and phylogeny by molecular analysis (RAPID, RFLP, AFLP, SSR, ISSR, IRAP, eSSR), main characteristics and world production, germplasm biodiversity, main cultivars and rootstocks, current conservation strategies of both conventional propagation (seeds, cutting, and grafting), and non-conventional propagation methods (cryopreservation, slow growth storage, synthetic seed techniques and micropropagation) and the application of computational tools (Design of Experiments (DoE) and Machine Learning: Artificial Neural Networks, Fuzzy logic and Genetic Algorithms) to design efficient micropropagation protocols for the genus Pistacia.

Neurofuzzy logic predicts a fine-tuning metabolic reprogramming on elicited Bryophyllum PCSCs guided by salicylic acid

Novel approaches to the characterization of medicinal plants as biofactories have lately increased in the field of biotechnology. In this work, a multifaceted approach based on plant tissue culture, metabolomics, and machine learning was applied to decipher and further characterize the biosynthesis of phenolic compounds by eliciting cell suspension cultures from medicinal plants belonging to the Bryophyllum subgenus. The application of untargeted metabolomics provided a total of 460 phenolic compounds. The biosynthesis of 164 of them was significantly modulated by elicitation. The application of neurofuzzy logic as a machine learning tool allowed for deciphering the critical factors involved in the response to elicitation, predicting their influence and interactions on plant cell growth and the biosynthesis of several polyphenols subfamilies. The results indicate that salicylic acid plays a definitive genotype-dependent role in the elicitation of Bryophyllum cell cultures, while methyl jasmonate was revealed as a secondary factor. The knowledge provided by this approach opens a wide perspective on the research of medicinal plants and facilitates their biotechnological exploitation as biofactories in the food, cosmetic and pharmaceutical fields.

Artificial Neural Networks Elucidated the Essential Role of Mineral Nutrients versus Vitamins and Plant Growth Regulators in Achieving Healthy Micropropagated Plants

The design of an adequate culture medium is an essential step in the micropropagation process of plant species. Adjustment and balance of medium components involve the interaction of several factors, such as mineral nutrients, vitamins, and plant growth regulators (PGRs). This work aimed to shed light on the role of these three components on the plant growth and quality of micropropagated woody plants, using Actinidia arguta as a plant model. Two experiments using a five-dimensional experimental design space were defined using the Design of Experiments (DoE) method, to study the effect of five mineral factors (NH₄NO₃, KNO₃, Mesos, Micros, and Iron) and five vitamins (Myo-inositol, thiamine, nicotinic acid, pyridoxine, and vitamin E). A third experiment, using 20 combinations of two PGRs: BAP (6-benzylaminopurine) and GA₃ (gibberellic acid) was performed. Artificial Neural Networks (ANNs) algorithms were used to build models with the whole database to determine the effect of those components on several growth and quality parameters. Neurofuzzy logic allowed us to decipher and generate new knowledge on the hierarchy of some minerals as essential components of the culture media over vitamins and PRGs, suggesting rules about how MS basal media formulation could be modified to assess the quality of micropropagated woody plants.

The Combination of Untargeted Metabolomics and Machine Learning Predicts the Biosynthesis of Phenolic Compounds in Bryophyllum Medicinal Plants (Genus Kalanchoe)

Phenolic compounds constitute an important family of natural bioactive compounds responsible for the medicinal properties attributed to Bryophyllum plants (genus Kalanchoe, Crassulaceae), but their production by these medicinal plants has not been characterized to date. In this work, a combinatorial approach including plant tissue culture, untargeted metabolomics, and machine learning is proposed to unravel the critical factors behind the biosynthesis of phenolic compounds in these species. The untargeted metabolomics revealed 485 annotated compounds that were produced by three Bryophyllum species cultured in vitro in a genotype and organ-dependent manner. Neurofuzzy logic (NFL) predictive models assessed the significant influence of genotypes and organs and identified the key nutrients from culture media formulations involved in phenolic compound biosynthesis. Sulfate played a critical role in tyrosol and lignan biosynthesis, copper in phenolic acid biosynthesis, calcium in stilbene biosynthesis, and magnesium in flavanol biosynthesis. Flavonol and anthocyanin biosynthesis was not significantly affected by mineral components. As a result, a predictive biosynthetic model for all the Bryophyllum genotypes was proposed. The combination of untargeted metabolomics with machine learning provided a robust approach to achieve the phytochemical characterization of the previously unexplored species belonging to the Bryophyllum subgenus, facilitating their biotechnological exploitation as a promising source of bioactive compounds.

Computer-Based Tools Unmask Critical Mineral Nutrient Interactions in Hoagland Solution for Healthy Kiwiberry Plant Acclimatization

The aim of this study was to better understand the response of ex vitro acclimatized plants grown to a set of mineral nutrient combinations based on Hoagland solution. To reach that, two computer-based tools were used: the design of experiments (DOE) and a hybrid artificial intelligence technology that combines artificial neural networks with fuzzy logic. DOE was employed to create a five-dimensional IV-design space by categorizing all macroelements and one microelement (copper) of Hoagland mineral solution, reducing the experimental design space from 243 (35) to 19 treatments. Typical growth parameters included hardening efficiency (Hard), newly formed shoot length (SL), total leaf number (TLN), leaf chlorophyll content (LCC), and leaf area (LA). Moreover, three physiological disorders, namely, leaf necrosis (LN), leaf spot (LS), and curled leaf (CL), were evaluated for each treatment (mineral formulation). All the growth parameters plus LN were successfully modeled using neuro-fuzzy logic with a high train set R 2 between experimental and predicted values (72.67 < R 2 < 98.79). The model deciphered new insights using different sets of "IF-THEN" rules, pinpointing the positive role of Mg2+ and Ca2+ to improve Hard, SL, TLN, and LA and alleviate LN but with opposite influences on LCC. On the contrary, TLN and LCC were negatively affected by the addition of NO3 - into the media, while NH4 + in complex interaction with Cu2+ or Mg2+ positively enhanced SL, TLN, LCC, and LA. In our opinion, the approach and results achieved in this work are extremely fruitful to understand the effect of Hoagland mineral nutrients on the healthy growth of ex vitro acclimatized plants, through identifying key factors, which favor growth and limit physiological abnormalities.

Screening of critical variables in fabricating polycaprolactone nanoparticles using Neuro Fuzzy Logic

In this work, we used the artificial intelligence tool known as neurofuzzy logic (NFL) for fabricating uniform nanoparticles of polycaprolactone by the nanoprecipitation method with a focus on stabilizer selection. The adaptability of NFL assisted the decision-making on different manufacturing and formulation conditions. The nanoprecipitation method can be summarized as mixing a poorly water-soluble polymer solution with water and its consequent precipitation. Although nanoprecipitation seems simple, the process is highly variable to even slight modifications, leading to polydispersity and nanoparticle aggregation. Here, the NFL model established relationships between mixing conditions, different stabilizers and solvents, among other parameters. Seven parameters measured by dynamic light scattering and laser doppler electrophoresis were modelized with high predictability using NFL tool, as a function of the raw materials and operation conditions. The model allowed the principal component analysis to be carried out, showing that the selection of a stabilizer is the most critical parameter for avoiding nanoparticle aggregation. Then, inputs related to fluid dynamics were relevant to tune the characteristics of the stabilized nanoparticles even further. NFL model showed great potential to support pharmaceutical research by finding subtle relationships between several variables, even from incomplete or fragmented data, which is common in pharmaceutical development.

Combining Medicinal Plant In Vitro Culture with Machine Learning Technologies for Maximizing the Production of Phenolic Compounds

We combined machine learning and plant in vitro culture methodologies as a novel approach for unraveling the phytochemical potential of unexploited medicinal plants. In order to induce phenolic compound biosynthesis, the in vitro culture of three different species of Bryophyllum under nutritional stress was established. To optimize phenolic extraction, four solvents with different MeOH proportions were used, and total phenolic content (TPC), flavonoid content (FC) and radical-scavenging activity (RSA) were determined. All results were subjected to data modeling with the application of artificial neural networks to provide insight into the significant factors that influence such multifactorial processes. Our findings suggest that aerial parts accumulate a higher proportion of phenolic compounds and flavonoids in comparison to roots. TPC was increased under ammonium concentrations below 15 mM, and their extraction was maximum when using solvents with intermediate methanol proportions (55–85%). The same behavior was reported for RSA, and, conversely, FC was independent of culture media composition, and their extraction was enhanced using solvents with high methanol proportions (>85%). These findings confer a wide perspective about the relationship between abiotic stress and secondary metabolism and could serve as the starting point for the optimization of bioactive compound production at a biotechnological scale.

Machine Learning Unmasked Nutritional Imbalances on the Medicinal Plant Bryophyllum sp. Cultured in vitro

Plant nutrition is a crucial factor that is usually underestimated when designing plant in vitro culture protocols of unexploited plants. As a complex multifactorial process, the study of nutritional imbalances requires the use of time-consuming experimental designs and appropriate statistical and multiple regression analysis for the determination of critical parameters, whose results may be difficult to interpret when the number of variables is large. The use of machine learning (ML) supposes a cutting-edge approach to investigate multifactorial processes, with the aim of detecting non-linear relationships and critical factors affecting a determined response and their concealed interactions. Thus, in this work we applied artificial neural networks coupled to fuzzy logic, known as neurofuzzy logic, to determine the critical factors affecting the mineral nutrition of medicinal plants belonging to Bryophyllum subgenus cultured in vitro. The application of neurofuzzy logic algorithms facilitate the interpretation of the results, as the technology is able to generate useful and understandable "IF-THEN" rules, that provide information about the factor(s) involved in a certain response. In this sense, ammonium, sulfate, molybdenum, copper and sodium were the most important nutrients that explain the variation in the in vitro culture establishment of the medicinal plants in a species-dependent manner. Thus, our results indicate that Bryophyllum spp. display a fine-tuning regulation of mineral nutrition, that was reported for the first time under in vitro conditions. Overall, neurofuzzy model was able to predict and identify masked interactions among such factors, providing a source of knowledge (helpful information) from the experimental data (non-informative per se), in order to make the exploitation and valorization of medicinal plants with high phytochemical potential easier.

Modeling and Optimizing Culture Medium Mineral Composition for in vitro Propagation of Actinidia arguta

The design of plant tissue culture media remains a complicated task due to the interactions of many factors. The use of computer-based tools is still very scarce, although they have demonstrated great advantages when used in large dataset analysis. In this study, design of experiments (DOE) and three machine learning (ML) algorithms, artificial neural networks (ANNs), fuzzy logic, and genetic algorithms (GA), were combined to decipher the key minerals and predict the optimal combination of salts for hardy kiwi (Actinidia arguta) in vitro micropropagation. A five-factor experimental design of 33 salt treatments was defined using DOE. Later, the effect of the ionic variations generated by these five factors on three morpho-physiological growth responses - shoot number (SN), shoot length (SL), and leaves area (LA) - and on three quality responses - shoots quality (SQ), basal callus (BC), and hyperhydricity (H) - were modeled and analyzed simultaneously. Neurofuzzy logic models demonstrated that just 11 ions (five macronutrients (N, K, P, Mg, and S) and six micronutrients (Cl, Fe, B, Mo, Na, and I)) out of the 18 tested explained the results obtained. The rules "IF - THEN" allow for easy deduction of the concentration range of each ion that causes a positive effect on growth responses and guarantees healthy shoots. Secondly, using a combination of ANNs-GA, a new optimized medium was designed and the desired values for each response parameter were accurately predicted. Finally, the experimental validation of the model showed that the optimized medium significantly promotes SQ and reduces BC and H compared to standard media generally used in plant tissue culture. This study demonstrated the suitability of computer-based tools for improving plant in vitro micropropagation: (i) DOE to design more efficient experiments, saving time and cost; (ii) ANNs combined with fuzzy logic to understand the cause-effect of several factors on the response parameters; and (iii) ANNs-GA to predict new mineral media formulation, which improve growth response, avoiding morpho-physiological abnormalities. The lack of predictability on some response parameters can be due to other key media components, such as vitamins, PGRs, or organic compounds, particularly glycine, which could modulate the effect of the ions and needs further research for confirmation.

Machine learning approaches and their current application in plant molecular biology: A systematic review

Machine learning (ML) is a field of artificial intelligence that has rapidly emerged in molecular biology, thus allowing the exploitation of Big Data concepts in plant genomics. In this context, the main challenges are given in terms of how to analyze massive datasets and extract new knowledge in all levels of cellular systems research. In summary, ML techniques allow complex interactions to be inferred in several biological systems. Despite its potential, ML has been underused due to complex computational algorithms and definition terms. Therefore, a systematic review to disentangle ML approaches is relevant for plant scientists and has been considered in this study. We presented the main steps for ML development (from data selection to evaluation of classification/prediction models) with a respective discussion approaching functional genomics mainly in terms of pathogen effector genes in plant immunity. Additionally, we also considered how to access public source databases under an ML framework towards advancing plant molecular biology and introduced novel powerful tools, such as deep learning.

Finding key nanoprecipitation variables for achieving uniform polymeric nanoparticles using neurofuzzy logic technology

Nanoprecipitation is a simple and fast method to produce polymeric nanoparticles (Np); however, most applications require filtration or another separation technique to isolate the nanosuspension from aggregates or polydisperse particle production. In order to avoid variability introduced by these additional steps, we report here a systematic study of the process to yield monomodal and uniform Np production with the nanoprecipitation method. To further identify key variables and their interactions, we used artificial neural networks (ANN) to investigate the multiple variables which influence the process. In this work, a polymethacrylate derivative was used for Np (NpERS) and a database with several formulations and conditions was developed for the ANN model. The resulting ANN model had a high predictability (> 70%) for NpERS characteristics measured (mean size, PDI, zeta potential, and number of particle populations). Moreover, the model identified production variables leading to polymer supersaturation, such as mixing time and turbulence, as key in achieving monomodal and uniform NpERS in one production step. Polymer concentration and type of solvent, modifiers of polymer diffusion and supersaturation, were also shown to control NpERS characteristics. The ANN study allowed the identification of key variables and their interactions and resulted in a predictive model to study the NpERS production by nanoprecipitation. In turn, we have achieved an optimized method to yield uniform NpERS which could pave way for polymeric nanoparticle production methods with potential in biological and drug delivery applications.

Deciphering the virulence of Mycobacterium avium subsp. paratuberculosis isolates in animal macrophages using mathematical models

Understanding why pathogenic Mycobacterium avium subsp. paratuberculosis (Map) isolates cause disparate disease outcomes with differing magnitudes of severity is important in designing and implementing new control strategies. We applied a suite of mathematical models: i) general linear, ii) and neurofuzzy logic, to explain how the host of origin of several Map isolates, Map genotype, host, macrophage-based in vitro model and time post-infection contributed to the infection. A logistic growth ordinary differential equation (ODE) model was applied to estimate within macrophage growth rates for the different Map isolates. The models revealed different susceptibilities of bovine and ovine macrophages to Map infection and confirmed distinct virulence profiles for the isolates, judged by their ability to grow within macrophages. Ovine macrophages were able to internalize Map isolates more efficiently than bovine macrophages. While bovine macrophages were able to internalize Map isolates from cattle with more efficiency, ovine macrophages were more efficient in internalizing ovine isolates. Overall, Map isolates from goat and sheep grew minimally within macrophages or did not grow but were able to persist by maintaining its initial population. In contrast, the ability of the bovine isolates and the non-domesticated animal isolates to grow to higher CFU numbers within macrophages suggests that these isolates are more virulent than the sheep and goat isolates, or that these isolates are better adapted to infect domestic ruminants. Overall, our study confirms the different virulence levels for the Map isolates and susceptibility profiles of host macrophages, which is crucial in increasing our understanding of Map infection.

Delimiting the knowledge space and the design space of nanostructured lipid carriers through Artificial Intelligence tools

Nanostructured lipid carriers (NLC) are biocompatible and biodegradable nanoscale systems with extensive application for controlled drug release. However, the development of optimal nanosystems along with a reproducible manufacturing process is still challenging. In this study, a two-step experimental design was performed and databases were successfully modelled using Artificial Intelligence techniques as an innovative method to get optimal, reproducible and stable NLC. The initial approach, including a wide range of values for the different variables, was followed by a second set of experiments with variable values in a narrower range, more suited to the characteristics of the system. NLC loaded with rifabutin, a hydrophobic drug model, were produced by hot homogenization and fully characterized in terms of particle size, size distribution, zeta potential, encapsulation efficiency and drug loading. The use of Artificial Intelligence tools has allowed to elucidate the key parameters that modulate each formulation property. Stable nanoparticles with low sizes and polydispersions, negative zeta potentials and high drug loadings were obtained when the proportion of lipid components, drug, surfactants and stirring speed were optimized by FormRules^® and INForm^®. The successful application of Artificial Intelligence tools on NLC formulation optimization constitutes a pioneer approach in the field of lipid nanoparticles.

Mycobacterium avium subsp. paratuberculosis (Map) Fatty Acids Profile Is Strain-Dependent and Changes Upon Host Macrophages Infection

Johne's disease is a chronic granulomatous enteritis of ruminants caused by the intracellular bacterium Mycobacterium avium subsp. paratuberculosis (Map). We previously demonstrated that Map isolates from sheep persisted within host macrophages in lower CFUs than cattle isolates after 7 days of infection. In the current study, we hypothesize that these phenotypic differences between Map isolates may be driven be the fatty acids (FAs) present on the phosphadidyl-1-myo-inositol mannosides of the Map cell wall that mediate recognition by the mannose receptors of host macrophages. FAs modifications may influence Map's envelope fluidity ultimately affecting pathogenicity. To test this hypothesis, we investigated the responses of two Map isolates from cattle (K10 isolate) and sheep (2349/06-1) to the bovine and ovine macrophage environment by measuring the FAs content of extracellular and intracellular bacteria. For this purpose, macrophages cell lines of bovine (BOMAC) and ovine (MOCL-4) origin were infected with the two isolates of Map for 4 days at 37°C. The relative FAs composition of the two isolates recovered from infected BOMAC and MOCL-4 cells was determined by gas chromatography and compared with that of extracellular bacteria and that of bacteria grown in Middlebrook 7H9 medium. Using this approach, we demonstrated that the FAs composition of extracellular and 7H9-grown bacteria was highly conserved within each Map isolate, and statistically different from that of intracellular bacteria. Analysis of FAs composition from extracellular bacteria enabled the distinction of the two Map strains based on the presence of the tuberculostearic acid (18:0 10Me) exclusively in the K10 strain of Map. In addition, significant differences in the content of Palmitic acid and cis-7 Palmitoleic acid between both isolates harvested from the extracellular environment were observed. Once the infection established itself in BOMAC and MOCL-4 cells, the FAs profiles of both Map isolates appeared conserved. Our results suggest that the FAs composition of Map might influence its recognition by macrophages and influence the survival of the bacillus within host macrophages.

Computational intelligence models to predict porosity of tablets using minimum features

The effects of different formulations and manufacturing process conditions on the physical properties of a solid dosage form are of importance to the pharmaceutical industry. It is vital to have in-depth understanding of the material properties and governing parameters of its processes in response to different formulations. Understanding the mentioned aspects will allow tighter control of the process, leading to implementation of quality-by-design (QbD) practices. Computational intelligence (CI) offers an opportunity to create empirical models that can be used to describe the system and predict future outcomes in silico. CI models can help explore the behavior of input parameters, unlocking deeper understanding of the system. This research endeavor presents CI models to predict the porosity of tablets created by roll-compacted binary mixtures, which were milled and compacted under systematically varying conditions. CI models were created using tree-based methods, artificial neural networks (ANNs), and symbolic regression trained on an experimental data set and screened using root-mean-square error (RMSE) scores. The experimental data were composed of proportion of microcrystalline cellulose (MCC) (in percentage), granule size fraction (in micrometers), and die compaction force (in kilonewtons) as inputs and porosity as an output. The resulting models show impressive generalization ability, with ANNs (normalized root-mean-square error [NRMSE] =1%) and symbolic regression (NRMSE =4%) as the best-performing methods, also exhibiting reliable predictive behavior when presented with a challenging external validation data set (best achieved symbolic regression: NRMSE =3%). Symbolic regression demonstrates the transition from the black box modeling paradigm to more transparent predictive models. Predictive performance and feature selection behavior of CI models hints at the most important variables within this factor space.

Artificial neural network-based model for the prediction of optimal growth and culture conditions for maximum biomass accumulation in multiple shoot cultures of Centella asiatica

An artificial neural network (ANN)-based modelling approach is used to determine the synergistic effect of five major components of growth medium (Mg, Cu, Zn, nitrate and sucrose) on improved in vitro biomass yield in multiple shoot cultures of Centella asiatica. The back propagation neural network (BPNN) was employed to predict optimal biomass accumulation in terms of growth index over a defined culture duration of 35 days. The four variable concentrations of five media components, i.e. MgSO₄ (0, 0.75, 1.5, 3.0 mM), ZnSO₄ (0, 15, 30, 60 μM), CuSO₄ (0, 0.05, 0.1, 0.2 μM), NO₃ (20, 30, 40, 60 mM) and sucrose (1, 3, 5, 7 %, w/v) were taken as inputs for the ANN model. The designed model was evaluated by performing three different sets of validation experiments that indicated a greater similarity between the target and predicted dataset. The results of the modelling experiment suggested that 1.5 mM Mg, 30 μM Zn, 0.1 μM Cu, 40 mM NO₃ and 6 % (w/v) sucrose were the respective optimal concentrations of the tested medium components for achieving maximum growth index of 1654.46 with high centelloside yield (62.37 mg DW/culture) in the cultured multiple shoots. This study can facilitate the generation of higher biomass of uniform, clean, good quality C. asiatica herb that can efficiently be utilized by pharmaceutical industries.

The Future of Pharmaceutical Manufacturing Sciences

The entire pharmaceutical sector is in an urgent need of both innovative technological solutions and fundamental scientific work, enabling the production of highly engineered drug products. Commercial-scale manufacturing of complex drug delivery systems (DDSs) using the existing technologies is challenging. This review covers important elements of manufacturing sciences, beginning with risk management strategies and design of experiments (DoE) techniques. Experimental techniques should, where possible, be supported by computational approaches. With that regard, state-of-art mechanistic process modeling techniques are described in detail. Implementation of materials science tools paves the way to molecular-based processing of future DDSs. A snapshot of some of the existing tools is presented. Additionally, general engineering principles are discussed covering process measurement and process control solutions. Last part of the review addresses future manufacturing solutions, covering continuous processing and, specifically, hot-melt processing and printing-based technologies. Finally, challenges related to implementing these technologies as a part of future health care systems are discussed.

Artificial Intelligence versus Statistical Modeling and Optimization of Cholesterol Oxidase Production by using Streptomyces Sp

Cholesterol oxidase (COD) is a bi-functional FAD-containing oxidoreductase which catalyzes the oxidation of cholesterol into 4-cholesten-3-one. The wider biological functions and clinical applications of COD have urged the screening, isolation and characterization of newer microbes from diverse habitats as a source of COD and optimization and over-production of COD for various uses. The practicability of statistical/ artificial intelligence techniques, such as response surface methodology (RSM), artificial neural network (ANN) and genetic algorithm (GA) have been tested to optimize the medium composition for the production of COD from novel strain Streptomyces sp. NCIM 5500. All experiments were performed according to the five factor central composite design (CCD) and the generated data was analysed using RSM and ANN. GA was employed to optimize the models generated by RSM and ANN. Based upon the predicted COD concentration, the model developed with ANN was found to be superior to the model developed with RSM. The RSM-GA approach predicted maximum of 6.283 U/mL COD production, whereas the ANN-GA approach predicted a maximum of 9.93 U/mL COD concentration. The optimum concentrations of the medium variables predicted through ANN-GA approach were: 1.431 g/50 mL soybean, 1.389 g/50 mL maltose, 0.029 g/50 mL MgSO₄, 0.45 g/50 mL NaCl and 2.235 ml/50 mL glycerol. The experimental COD concentration was concurrent with the GA predicted yield and led to 9.75 U/mL COD production, which was nearly two times higher than the yield (4.2 U/mL) obtained with the un-optimized medium. This is the very first time we are reporting the statistical versus artificial intelligence based modeling and optimization of COD production by Streptomyces sp. NCIM 5500.

A (polyvinyl caprolactam-polyvinyl acetate-polyethylene glycol graft copolymer)-dispersed sustained-release tablet for imperialine to simultaneously prolong the drug release and improve the oral bioavailability

Imperialine, extracted from Bulbus Fritillariae Cirrhosae, is an efficient antitussive and expectorant medicine. However, its short half-life and stomach degradation limited imperialine from further clinical use. The current study was conducted to develop a sustained-release tablet for imperialine both to prolong absorption time and to improve the oral bioavailability of the drug. The tablets were prepared by a direct compression method formulated on optimized solid dispersion (SD) for imperialine based on polyvinyl caprolactam-polyvinyl acetate-polyethylene glycol graft copolymer (Soluplus(®)) with imperialine/Soluplus(®) ratio of 1:8 (w/w). In order to obtain the optimized formulation, factors that affected the drug release were investigated by in vitro dissolution studies in the media of pH1.2, 5.8, 7.0 and 7.4. Powder X-ray diffraction and scanning electron microscope confirmed that the imperialine in SD was amorphous instead of crystalline, and still stayed amorphous even after the direct compression. And besides, pharmacokinetic study in Beagle dogs was performed to inspect the in vivo sustained release. Plasma concentration-time curves and pharmacokinetic parameters were gained. As a result, the Cmax of imperialine was one-fold reduced and Tmax was two-fold prolonged, and the mean AUC0-24 was expressed as 89.581±21.243μgh/L, which showed that the oral bioavailability of imperialine was 2.46-fold improved. Moreover, the in vitro-in vivo correlation was recommended to carry out, demonstrating the percentages of drug release in vitro were well-correlated with the absorptive fraction in vivo with the correlation coefficients above 0.9900. By mathematically modeling and moment imaging of the drug release, Peppas equation was selected as the most fitted model for the sustained-release tablets with the diffusional coefficient in the range of 0.59-0.62, indicating the release of imperialine from the sustained-release tablets was an anomalous process involving polymer swelling, drug diffusion and matrix erosion.

Modeling the effects of light and sucrose on in vitro propagated plants: a multiscale system analysis using artificial intelligence technology

BACKGROUND

Plant acclimation is a highly complex process, which cannot be fully understood by analysis at any one specific level (i.e. subcellular, cellular or whole plant scale). Various soft-computing techniques, such as neural networks or fuzzy logic, were designed to analyze complex multivariate data sets and might be used to model large such multiscale data sets in plant biology.

METHODOLOGY AND PRINCIPAL FINDINGS

In this study we assessed the effectiveness of applying neuro-fuzzy logic to modeling the effects of light intensities and sucrose content/concentration in the in vitro culture of kiwifruit on plant acclimation, by modeling multivariate data from 14 parameters at different biological scales of organization. The model provides insights through application of 14 sets of straightforward rules and indicates that plants with lower stomatal aperture areas and higher photoinhibition and photoprotective status score best for acclimation. The model suggests the best condition for obtaining higher quality acclimatized plantlets is the combination of 2.3% sucrose and photonflux of 122-130 µmol m(-2) s(-1).

CONCLUSIONS

Our results demonstrate that artificial intelligence models are not only successful in identifying complex non-linear interactions among variables, by integrating large-scale data sets from different levels of biological organization in a holistic plant systems-biology approach, but can also be used successfully for inferring new results without further experimental work.

Tablet formulation of an active pharmaceutical ingredient with a sticking and filming problem: direct compression and dry granulation evaluations

OBJECTIVE

To develop a tablet formulation for an active pharmaceutical ingredient for which sticking and filming problems occurred during tablet punching.

METHODS

Direct compression and dry granulation tableting techniques were evaluated using factorial experimental design. The effects of chrome-coated punch tips, filler types and active percent in the tablet formulation by direct compression were evaluated. Similarly, for dry granulation using the roller compaction technique, three formulation factors - roller compaction pressure, intragranular filler percent and filler type - were studied. Tablets prepared by both techniques were characterized in regard to their compressibility index, tablet hardness, disintegration time, friability index and stickiness-filming index (an arbitrary index). Ten formulations were prepared by each technique. Using multiple response optimizations and estimated response surface plots, the data were analyzed to identify optimum levels for the formulation factors.

RESULTS

Compressibility index values for all the formulations prepared by direct compression exceeded 25%, unlike the blends prepared by dry granulation. Both tablet hardness and disintegration time for direct compression formulations were significantly lower than for dry granulation formulations. The friability index values were significantly higher for direct compression formulations than for dry granulation formulations. All the direct compression formulations, unlike the dry granulation formulations, had a high stickiness-filming index.

CONCLUSION

Statistical analysis helped in identifying the optimum levels of formulation factors, as well as the method for eliminating sticking and filming. Unlike the direct compression technique, dry granulation yielded tablets for which sticking and filming were completely eliminated.

Fuzzy Logic-based expert system for evaluating cake quality of freeze-dried formulations

Freeze-drying of peptide and protein-based pharmaceuticals is an increasingly important field of research. The diverse nature of these compounds, limited understanding of excipient functionality, and difficult-to-analyze quality attributes together with the increasing importance of the biosimilarity concept complicate the development phase of safe and cost-effective drug products. To streamline the development phase and to make high-throughput formulation screening possible, efficient solutions for analyzing critical quality attributes such as cake quality with minimal material consumption are needed. The aim of this study was to develop a fuzzy logic system based on image analysis (IA) for analyzing cake quality. Freeze-dried samples with different visual quality attributes were prepared in well plates. Imaging solutions together with image analytical routines were developed for extracting critical visual features such as the degree of cake collapse, glassiness, and color uniformity. On the basis of the IA outputs, a fuzzy logic system for analysis of these freeze-dried cakes was constructed. After this development phase, the system was tested with a new screening well plate. The developed fuzzy logic-based system was found to give comparable quality scores with visual evaluation, making high-throughput classification of cake quality possible.

Isotretinoin oil-based capsule formulation optimization

The purpose of this study was to develop and optimize an isotretinoin oil-based capsule with specific dissolution pattern. A three-factor-constrained mixture design was used to prepare the systemic model formulations. The independent factors were the components of oil-based capsule including beeswax (X₁), hydrogenated coconut oil (X₂), and soybean oil (X₃). The drug release percentages at 10, 30, 60, and 90 min were selected as responses. The effect of formulation factors including that on responses was inspected by using response surface methodology (RSM). Multiple-response optimization was performed to search for the appropriate formulation with specific release pattern. It was found that the interaction effect of these formulation factors (X₁X₂, X₁X₃, and X₂X₃) showed more potential influence than that of the main factors (X₁, X₂, and X₃). An optimal predicted formulation with Y_10 min, Y_30 min, Y_60 min, and Y_90 min release values of 12.3%, 36.7%, 73.6%, and 92.7% at X₁, X₂, and X₃ of 5.75, 15.37, and 78.88, respectively, was developed. The new formulation was prepared and performed by the dissolution test. The similarity factor f₂ was 54.8, indicating that the dissolution pattern of the new optimized formulation showed equivalence to the predicted profile.

Improving knowledge of plant tissue culture and media formulation by neurofuzzy logic: a practical case of data mining using apricot databases

Plant tissue growth can be regulated and controlled via culture media composition. A number of different laborious and time-consuming approaches have been used to attempt development of optimized media for a wide range of species and applications. However, plant tissue culture is a very complex task, and the identification of the influences of process factors such as mineral nutrients or plant growth regulators on a wide spectrum of growth responses cannot always well comprehended. This study employs a new approach, data mining, to uncover and integrate knowledge hidden in multiple data from plant tissue culture media formulations using apricot micropropagation databases as an example. Neurofuzzy logic technology made it possible to identify relationships among several factors (cultivars, mineral nutrients and plant growth regulators) and growth parameters (shoots number, shoots length and productivity), extracting biologically useful information from each database and combining them to create a model. The IF-THEN rule sets generated by neurofuzzy logic were completely in agreement with previous findings based on statistical analysis, but advantageously generated understandable and reusable knowledge that can be applied in future plant tissue culture media optimization.

Artificial neural networks modeling the in vitro rhizogenesis and acclimatization of Vitis vinifera L

This study employs artificial neural networks (ANNs) to create a model to identify relationships between variables affecting the in vitro rhizogenesis and acclimatization of two cultivars of Vitis vinifera L. Albariño and Mencía. The effects of three factors (inputs), the type of cultivar, concentration and exposure time to indolebutyric acid (IBA), on the success of in vitro rhizogenesis and acclimatization were evaluated. The developed model, using ANNs software, was assessed using a separate set of validation data and was in good agreement with the observed results. Exposure time to IBA was found to have the dominant role in influencing the height of acclimatized plantlets. ANNs can be a useful tool for modeling different complex processes and data sets, in plant tissue cultures or, more generally, in plant biology.

Strengths of artificial neural networks in modeling complex plant processes

Commonly, simple mathematical models can not be used to describe exactly the biological processes due to their higher complexity. In fact, most biological interactions cannot be elucidated by a simple stepwise algorithm or a precise formula, particularly when the data are complex or noisy. ANNs allows an accurate description of those kind of biological processes in plant science, offering new advantages over traditional treatments as the possibility of a model, prediction and optimize results. Different kind of data can be analyzed using a unique and "easy to use" technology. Researchers with a high specialized mathematical background are not required and ANNs offer the possibility of achieving the whole view of the experimental study with a limited number of experiments and costs. Additionally, it is possible to add new inputs and outputs to the database to reach a new understanding.