Artificial Intelligence Technologies for COVID-19 De Novo Drug Design

The recent covid crisis has provided important lessons for academia and industry regarding digital reorganization. Among the fascinating lessons from these times is the huge potential of data analytics and artificial intelligence. The crisis exponentially accelerated the adoption of analytics and artificial intelligence, and this momentum is predicted to continue into the 2020s and beyond. Drug development is a costly and time-consuming business, and only a minority of approved drugs generate returns exceeding the research and development costs. As a result, there is a huge drive to make drug discovery cheaper and faster. With modern algorithms and hardware, it is not too surprising that the new technologies of artificial intelligence and other computational simulation tools can help drug developers. In only two years of covid research, many novel molecules have been designed/identified using artificial intelligence methods with astonishing results in terms of time and effectiveness. This paper reviews the most significant research on artificial intelligence in de novo drug design for COVID-19 pharmaceutical research.     

Cancer-Related Cachexia: The Vicious Circle between Inflammatory Cytokines,Skeletal Muscle,Lipid Metabolism and the Possible Role of Physical Training

Cachexia is a multifactorial and multi-organ syndrome that is a major cause of morbidity and mortality in late-stage chronic diseases. The main clinical features of cancer-related cachexia are chronic inflammation, wasting of skeletal muscle and adipose tissue, insulin resistance, anorexia, and impaired myogenesis. A multimodal treatment has been suggested to approach the multifactorial genesis of cachexia. In this context, physical exercise has been found to have a general effect on maintaining homeostasis in a healthy life, involving multiple organs and their metabolism. The purpose of this review is to present the evidence for the relationship between inflammatory cytokines, skeletal muscle, and fat metabolism and the potential role of exercise training in breaking the vicious circle of this impaired tissue cross-talk. Due to the wide-ranging effects of exercise training, from the body to the behavior and cognition of the individual, it seems to be able to improve the quality of life in this syndrome. Therefore, studying the molecular effects of physical exercise could provide important information about the interactions between organs and the systemic mediators involved in the overall homeostasis of the body.     

Peptide Human Neutrophil Elastase Inhibitors from Natural Sources: An Overview

Elastases are a broad group of enzymes involved in the lysis of elastin, the main component of elastic fibres. They are produced and released in the human body, mainly by neutrophils and the pancreas. The imbalance between elastase activity and its endogenous inhibitors can cause different illnesses due to their excessive activity. The main aim of this review is to provide an overview of the latest advancements on the identification, structures and mechanisms of action of peptide human neutrophil elastase inhibitors isolated from natural sources, such as plants, animals, fungi, bacteria and sponges. The discovery of new elastase inhibitors could have a great impact on the pharmaceutical development of novel drugs through the optimization of the natural lead compounds. Bacteria produce mainly cyclic peptides, while animals provide for long and linear amino acid sequences. Despite their diverse natural sources, these elastase inhibitors show remarkable IC₅₀ values in a range from nM to μM values, thus representing an interesting starting point for the further development of potent bioactive compounds on human elastase enzymes.     

Machine learning methods for short‐term bid forecasting in the renewable energy market: A case study in Italy

In liberalized markets, there usually exists a day‐ahead session where energy is sold and acquired for the following production day. Owing to the high uncertainty of its production, renewable energy (wind in particular) can significantly influence the network imbalance of the following day. In this work, we consider the problem of predicting the sum of the bid volumes for wind energy of all the producers inside the day‐ahead energy market. This is a valuable tool to be used by an energy provider in order to determine the imbalance of a market zone and, thus, properly size its bids. In particular, we focus on the estimation of the possible relationship between the meteorological forecasts and the wind power offered on the market by the companies for a market zone. We propose a machine learning model which is used to compute a 1‐day‐ahead forecast. The input‐output mapping is obtained by support vector regression. The input feature vector is defined by a suitable feature extraction technique since the meteorological forecasts are given on a lattice of thousands of geographical points. The computational experiments are performed considering the Italian market as a case study (years 2012‐2016). The results show that the proposed feature extraction technique, selecting only some geographical zones, manages to reduce the error attained using all the features. Moreover, classical statistical methods are shown to be outperformed by machine learning models. The analysis reveals also some weaknesses of the model, which may be due to other nonmeteorological factors at play.     

Energy storage and control optimization for an electric vehicle

Two big issues involving electric vehicles are energy supply and power management control. To deal with the energy supply problem, this paper proposes the application of a hybrid energy source system, composed of battery pack and ultracapacitor bank. The power management control between the energy supplies was defined by a fuzzy logic with inference rules optimized through genetic algorithm. The genetic algorithm optimizes lower and upper limits of membership functions aiming to reduce the hybrid energy source system total mass while maximizing the electric vehicle drive range and performance. Through the Pareto frontier, we found the best trade‐off solution.     

Assessment of intradialysis calcium mass balance by a single pool variable‐volume calcium kinetic model

Introduction: A reliable method of intradialysis calcium mass balance quantification is far from been established. We herein investigated the use of a single‐pool variable‐volume Calcium kinetic model to assess calcium mass balance in chronic and stable dialysis patients. Methods: Thirty‐four patients on thrice‐weekly HD were studied during 240 dialysis sessions. All patients were dialyzed with a nominal total calcium concentration of 1.50 mmol/L. The main assumption of the model is that the calcium distribution volume is equal to the extracellular volume during dialysis. This hypothesis is assumed valid if measured and predicted end dialysis plasma water ionized calcium concentrations are equal. A difference between predicted and measured end‐dialysis ionized plasma water calcium concentration is a deviation on our main hypothesis, meaning that a substantial amount of calcium is exchanged between the extracellular volume and a nonmodeled compartment. Findings: The difference between predicted and measured values was 0.02 mmol/L (range ?0.08:0.16 mmol/L). With a mean ionized dialysate calcium concentration of 1.25 mmol/L, calcium mass balance was on average negative (mean ± SD ?0.84 ± 1.33 mmol, range ?5.42:2.75). Predialysis ionized plasma water concentration and total ultrafiltrate were the most important predictors of calcium mass balance. A significant mobilization of calcium from the extracellular pool to a nonmodeled pool was calculated in a group of patients. Discussion: The proposed single pool variable‐volume Calcium kinetic model is adequate for prediction and quantification of intradialysis calcium mass balance, it can evaluate the eventual calcium transfer outside the extracellular pool in clinical practice.     

Electron beam modification and functionalization of MWNT for covalent dispersion into polymeric systems

The development of nanotube-based polymer composites with improved mechanical properties and electrical conductivity requires the covalent dispersion of carbon nanotubes to utilize their stress transfer capabilities. Covalent dispersion of nanotubes therefore requires the functionalization of their surface to interact with solvents or monomers. In this work, we have developed a novel method of nanotube surface modification in which dry MWNT are irradiated with a high-energy electron beam (EB) in ambient air environment. Raman spectroscopy was performed to characterize the influence of EB irradiation on nanotubes, namely, variance of the disorder, or D band (∼1360 cm⁻¹) with respect to the graphitic, or G, band (∼1580 cm⁻¹). Raman spectra show increased deformation to the graphitic structure, as well as increased strain on the carbon-carbon bonds, weakening the nanotube. Transmission electron microscopy (TEM) confirms that nanotubes remain intact despite high EB dose. In addition, minimal surface deformation and length reduction occurred on irradiated MWNT.