AI can empower agriculture for global food security: challenges and prospects in developing nations.

Food and nutrition are a steadfast essential to all living organisms. With specific reference to humans, the sufficient and efficient supply of food is a challenge as the world population continues to grow. Artificial Intelligence (AI) could be identified as a plausible technology in this 5th industrial revolution in bringing us closer to achieving zero hunger by 2030-Goal 2 of the United Nations Sustainable Development Goals (UNSDG). This goal cannot be achieved unless the digital divide among developed and underdeveloped countries is addressed. Nevertheless, developing and underdeveloped regions fall behind in economic resources; however, they harbor untapped potential to effectively address the impending demands posed by the soaring world population. Therefore, this study explores the in-depth potential of AI in the agriculture sector for developing and under-developed countries. Similarly, it aims to emphasize the proven efficiency and spin-off applications of AI in the advancement of agriculture. Currently, AI is being utilized in various spheres of agriculture, including but not limited to crop surveillance, irrigation management, disease identification, fertilization practices, task automation, image manipulation, data processing, yield forecasting, supply chain optimization, implementation of decision support system (DSS), weed control, and the enhancement of resource utilization. Whereas AI supports food safety and security by ensuring higher crop yields that are acquired by harnessing the potential of multi-temporal remote sensing (RS) techniques to accurately discern diverse crop phenotypes, monitor land cover dynamics, assess variations in soil organic matter, predict soil moisture levels, conduct plant biomass modeling, and enable comprehensive crop monitoring. The present study identifies various challenges, including financial, infrastructure, experts, data availability, customization, regulatory framework, cultural norms and attitudes, access to market, and interdisciplinary collaboration, in the adoption of AI for developing nations with their subsequent remedies. The identification of challenges and opportunities in the implementation of AI could ignite further research and actions in these regions; thereby supporting sustainable development.

VirtuousPocketome: a computational tool for screening protein-ligand complexes to identify similar binding sites.

Protein residues within binding pockets play a critical role in determining the range of ligands that can interact with a protein, influencing its structure and function. Identifying structural similarities in proteins offers valuable insights into their function and activation mechanisms, aiding in predicting protein-ligand interactions, anticipating off-target effects, and facilitating the development of therapeutic agents. Numerous computational methods assessing global or local similarity in protein cavities have emerged, but their utilization is impeded by complexity, impractical automation for amino acid pattern searches, and an inability to evaluate the dynamics of scrutinized protein-ligand systems. Here, we present a general, automatic and unbiased computational pipeline, named VirtuousPocketome, aimed at screening huge databases of proteins for similar binding pockets starting from an interested protein-ligand complex. We demonstrate the pipeline's potential by exploring a recently-solved human bitter taste receptor, i.e. the TAS2R46, complexed with strychnine. We pinpointed 145 proteins sharing similar binding sites compared to the analysed bitter taste receptor and the enrichment analysis highlighted the related biological processes, molecular functions and cellular components. This work represents the foundation for future studies aimed at understanding the effective role of tastants outside the gustatory system: this could pave the way towards the rationalization of the diet as a supplement to standard pharmacological treatments and the design of novel tastants-inspired compounds to target other proteins involved in specific diseases or disorders. The proposed pipeline is publicly accessible, can be applied to any protein-ligand complex, and could be expanded to screen any database of protein structures.

Informed classification of sweeteners/bitterants compounds via explainable machine learning.

Perception of taste is an emergent phenomenon arising from complex molecular interactions between chemical compounds and specific taste receptors. Among all the taste perceptions, the dichotomy of sweet and bitter tastes has been the subject of several machine learning studies for classification purposes. While previous studies have provided accurate sweeteners/bitterants classifiers, there is ample scope to enhance these models by enriching the understanding of the molecular basis of bitter-sweet tastes. Towards these goals, our study focuses on the development and testing of several machine learning strategies coupled with the novel SHapley Additive exPlanations (SHAP) for a rational sweetness/bitterness classification. This allows the identification of the chemical descriptors of interest by allowing a more informed approach toward the rational design and screening of sweeteners/bitterants. To support future research in this field, we make all datasets and machine learning models publicly available and present an easy-to-use code for bitter-sweet taste prediction.

A survey on computational taste predictors.

Taste is a sensory modality crucial for nutrition and survival, since it allows the discrimination between healthy foods and toxic substances thanks to five tastes, i.e., sweet, bitter, umami, salty, and sour, associated with distinct nutritional or physiological needs. Today, taste prediction plays a key role in several fields, e.g., medical, industrial, or pharmaceutical, but the complexity of the taste perception process, its multidisciplinary nature, and the high number of potentially relevant players and features at the basis of the taste sensation make taste prediction a very complex task. In this context, the emerging capabilities of machine learning have provided fruitful insights in this field of research, allowing to consider and integrate a very large number of variables and identifying hidden correlations underlying the perception of a particular taste. This review aims at summarizing the latest advances in taste prediction, analyzing available food-related databases and taste prediction tools developed in recent years. Supplementary Information: The online version contains supplementary material available at 10.1007/s00217-022-04044-5.

Cardiovascular Risk Prediction in Ankylosing Spondylitis: From Traditional Scores to Machine Learning Assessment.

INTRODUCTION: The performance of seven cardiovascular (CV) risk algorithms is evaluated in a multicentric cohort of ankylosing spondylitis (AS) patients. Performance and calibration of traditional CV predictors have been compared with the novel paradigm of machine learning (ML). METHODS: A retrospective analysis of prospectively collected data from an AS cohort has been performed. The primary outcome was the first CV event. The discriminatory ability of the algorithms was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), which is like the concordance-statistic (c-statistic). Three ML techniques were considered to calculate the CV risk: support vector machine (SVM), random forest (RF), and k-nearest neighbor (KNN). RESULTS: Of 133 AS patients enrolled, 18 had a CV event. c-statistic scores of 0.71, 0.61, 0.66, 0.68, 0.66, 0.72, and 0.67 were found, respectively, for SCORE, CUORE, FRS, QRISK2, QRISK3, RRS, and ASSIGN. AUC values for the ML algorithms were: 0.70 for SVM, 0.73 for RF, and 0.64 for KNN. Feature analysis showed that C-reactive protein (CRP) has the highest importance, while SBP and hypertension treatment have lower importance. CONCLUSIONS: All of the evaluated CV risk algorithms exhibit a poor discriminative ability, except for RRS and SCORE, which showed a fair performance. For the first time, we demonstrated that AS patients do not show the traditional ones used by CV scores and that the most important variable is CRP. The present study contributes to a deeper understanding of CV risk in AS, allowing the development of innovative CV risk patient-specific models.

Predicting the metabolic condition after gestational diabetes mellitus from oral glucose tolerance test curves shape.

The objective of this feasibility study is to predict the metabolic condition in women with a history of gestational diabetes mellitus (GDM) from the shape of oral glucose tolerance test (OGTT) data. The rationale for this approach is that the evolution to a metabolic condition could be traceable in the shape of OGTT curves. 3-h OGTT data of 136 women with follow up, for a total of 401 OGTTs were analyzed. Subjects were classified as having normal (NGT) or non-normal glucose tolerance (NON-NGT), according to the American Diabetes Association criteria. The measured glucose, insulin, C-peptide data and combination of them were used to build up NGT and NON-NGT reference curves. Similarity between reference and individual OGTT-based curves was calculated using the Kullback-Leibler divergence. Our findings suggest that the shape of OGTT curves (1) contains information on the evolution to disease and (2) could be a reliable indicator to predict with high sensitivity (75%) and high specificity (69%) the metabolic condition of women with a history of GDM. In the future, the proposed shape-based prediction could be easily translated to the clinical practice, because it does not require the intervention of an operator specifically trained, thus facilitating its application in a clinical setting and ultimately empowering risk estimation, by improving/complementing the information which is currently adopted for risk stratification after pregnancy with GDM.

A 4-h hyperglycaemic excursion induces rapid and slow changes in major electrolytes in blood in healthy human subjects.

Hyperglycaemia is well known to cause reductions in plasma Na(+) levels or even hyponatraemia due to an osmotically induced dilution of the interstitium and blood. It is, however, unclear whether this dilution is significantly counteracted by ion regulatory homeostatic mechanism(s) or not. Furthermore, the effects of moderate hyperglycaemia on other major ions are less well known. To further clarify these questions, we measured the changes in blood osmolarity and concentrations of Na(+), K(+), Cl(-), Mg(2+) and Ca(2+) during a 4-h-long experimental hyperglycaemia in healthy subjects rendered temporarily insulin deficient using the hyperglycaemic clamp. Hyperglycaemia, 16.8 mM, was rapidly imposed from a baseline of 4.4 mM by intravenous somatostatin and glucose infusions in 19 healthy subjects (10 m, 9 f; age 36 ± 5 years (mean ± SD); BMI 22.7 ± 2.9 kg/m(2)). Subsequently, glycaemia was returned to basal and measurements continued until all dynamic changes had stopped (at ~8 h). Osmolarity increased from 281.8 ± 0.7 to 287.9 ± 0.7, while Na(+) decreased from 143.9 ± 0.3 to 138.7 ± 0.2, Cl(-) from 101.7 ± 0.2 to 99.5 ± 0.1, Ca(2+) from 1.98 ± 0.04 to 1.89 ± 0.02 and Mg(2+) from 0.84 ± 0.01 to 0.80 ± 0.00 mM. All these changes were rapidly reaching stable levels. K(+) increased from 4.02 ± 0.02 to 4.59 ± 0.02 mM (P < 0.0001) also reaching stable levels but with some delay. Na(+), Cl(-), Mg(2+) and Ca(2+) are essentially determined by blood dilution, and their values will remain diminished as long as the hyperglycaemia lasts. Partial suppression of insulin-stimulated Na(+)/K(+) pumping lead to increased K(+) levels. The combination of elevated K(+) and decreased Mg(2+) and Ca(2+) levels may lead to an altered excitability, which is particularly relevant for diabetic patients with heart disease.

Identification of a model of non-esterified fatty acids dynamics through genetic algorithms: the case of women with a history of gestational diabetes.

Elevation in non-esterified fatty acids (NEFA) has been shown to modulate insulin secretion and it is considered as a risk factor for the development of type 2 diabetes. Here we present a method that complements a mathematical model of NEFA kinetics with genetic algorithms for model identification. The complemented strategy allowed to assess parameters of NEFA kinetics and to get insight into their relationship with insulin during oral glucose tolerance tests in women with former gestational diabetes: (i) providing a reliable estimation of the model parameters, (ii) assuring the usability of the model, and (iii) promoting and facilitating its application in a clinical context.

Biomechanics of actin filaments: a computational multi-level study.

The actin microfilament (F-actin) is a structural and functional component of the cell cytoskeleton. Notwithstanding the primary role it plays for the mechanics of the cell, the mechanical behaviour of F-actin is still not totally explored. In particular, the relationship between the mechanics of F-actin and its molecular architecture is not completely understood. In this study, the mechanical properties of F-actin were related to the molecular topology of its building monomers (G-actin) by employing a computational multi-level approach. F-actins with lengths up to 500 nm were modelled and characterized, using a combination of equilibrium molecular dynamics (MD) simulations and normal mode analysis (NMA). MD simulations were performed to analyze the molecular rearrangements of G-actin in physiological conditions; NMA was applied to compute the macroscopic properties of F-actin from its vibrational modes of motion. Results from this multi-level approach showed that bending stiffness, bending modulus and persistence length are independent from the length of F-actin. On the contrary, the orientations and motions of selected groups of residues of G-actin play a primary role in determining the filament flexibility. In conclusion, this study (i) demonstrated that a combined computational approach of MD and NMA allows to investigate the biomechanics of F-actin taking into account the molecular topology of the filament (i.e., the molecular conformations of G-actin) and (ii) that this can be done using only crystallographic G-actin, without the need of introducing experimental parameters nor of reducing the number of residues.

A self-organizing map based morphological analysis of oral glucose tolerance test curves in women with gestational diabetes mellitus.

Gestational diabetes mellitus (GDM) makes women at risk of type 2 diabetes during their life. In order to predict this later abnormal glucose intolerance, several antepartum and postpartum predictors have been identified. In this study we conjecture that future evolution is predictable from morphology of the oral glucose tolerance test (OGTT) curves at baseline. To test our hypothesis, as a first step we evaluated the association between the curve morphologies of normal and diabetic patient condition at baseline. In particular, we analysed glucose and insulin curves of a group of women with a history of GDM. A Self-organizing map (SOM) was proposed to evaluate shape differences among control, normal, impaired glucose tolerance and diabetic curves shape. We compared our results with the currently applied clinical classification. We found that morphology contains information about the current status of the patient, because the SOM analysis clearly allows to discriminate subjects belonging to healthy or diabetic group. Moreover, SOMs highlighted additional information that could be used for prognostic purposes.

Improved usability of the minimal model of insulin sensitivity based on an automated approach and genetic algorithms for parameter estimation.

Minimal model analysis of glucose and insulin data from an IVGTT (intravenous glucose tolerance test) is widely used to estimate insulin sensitivity; however, the use of the model often requires intervention by a trained operator and some problems can occur in the estimation of model parameters. In the present study, a new method for minimal model analysis, termed GAMMOD, was developed based on genetic algorithms for the estimation of model parameters. Such an algorithm does not require the fixing of initial values for the parameters (that may lead to unreliable estimates). Our method also implements an automated weighting scheme not requiring manual intervention of the operator, thus improving the usability of the model. We studied a group of 170 women with a history of previous gestational diabetes. Results obtained by GAMMOD were compared with those obtained by MINMOD (a traditional gradient-based algorithm for minimal model analysis). Insulin sensitivity by GAMMOD was (3.86+/-0.19) compared with (4.33+/-0.20) x 10(-4) micro-units.ml(-1) x min(-1) by MINMOD; glucose effectiveness was 0.0236+/-0.0005 compared with 0.0229+/-0.0005 min(-1) respectively. The difference in the estimation by the two methods was within the precision expected for such metabolic parameters and is probably of no clinical relevance. Moreover, both the coefficient of variation of the estimated parameters and the error of fit were generally lower in GAMMOD, despite the fact that it does not require manual intervention. In conclusion, the GAMMOD approach for parameter estimation in the minimal model provides a reliable estimation of the model parameters and improves the usability of the model, thus facilitating its further use and application in a clinical context.

The power-law mathematical model for blood damage prediction: analytical developments and physical inconsistencies.

Blood trauma caused by medical devices is a major concern. Complications following the implantation/application of devices such as prosthetic heart valves, cannulae, blood pumps, tubing, and throttles lead to sublethal and lethal damage to platelets and erythrocytes. This damage is provided by the alterations in fluid dynamics, providing a mechanical load on the blood corpuscle's membrane by means of the shear stress. An appropriate quantification of the shear-induced hemolysis of artificial organs is thought to be useful in the design and development of such devices in order to minimize device-induced blood trauma. To date, a power-law mathematical relationship using the time of exposure of a blood corpuscle to a certain mechanical load and the shear stress itself (derived under the peculiar condition of uniform shear stress) has served as a basic model for the estimation of the damage to blood, investigated by means of numerical and/or experimental fluid dynamical techniques. The aim of the present article is to highlight the effect of a time-varying mechanical loading acting on blood cells based on the usual power-law model; furthermore, the effect of the loading history of a blood particle is discussed, showing how the past history of the shear acting on a blood corpuscle is not taken into account, as researchers have done until now. The need for a reassessment of the power-law model for potential blood trauma assessment is discussed by using a mathematical formulation based on the hypotheses of the existence of damage accumulation for blood with respect to time and with respect to shear stress, to be applied in complex flow fields such as the ones established in the presence of artificial organs.

Evolutive algorithms for beat-by-beat estimation of left ventricular mechanics.

Traditional methods to evaluate the ventricular mechanics need intraventricular pressure and volume recordings for multiple variably loaded beats. To do this, a complex and invasive procedure must be applied, that may decrease the clinical use. To overcome this limitation, a method to estimate the ventricular mechanics beat-by-beat is presented, modeling the ventricular pressure-volume relationship with a time-varying elastance function. The ability of the genetic algorithms (GAs) as identification technique is exploited. Applying GAs on surrogated data simulating variably loading conditions, the parameters of the time-varying elastance function, considered a measure of the contractility of the myocardial fibers are identified. These single-beat estimates are highly correlated with the end systolic pressure-volume relationship slope obtained by conventional multiple-beat analysis. The main advantage in using GAs for single beat analysis may lie, in the perspective of an use for in vivo investigations, both in their stochastic nature, and in the guaranteed better performance with respect to other search techniques on problems involving noisy signals. Future studies will approach the reduction in GAs computational costs, for a real time in vivo application.