Artificial neural networks in contemporary toxicology research

Artificial neural networks (ANNs) have a huge potential in toxicology research. They may be used to predict toxicity of various chemical compounds or classify the compounds based on their toxic effects. Today, numerous ANN models have been developed, some of which may be used to detect and possibly explain complex chemico-biological interactions. Fully connected multilayer perceptrons may in some circumstances have high classification accuracy and discriminatory power in separating damaged from intact cells after exposure to a toxic substance. Regularized and not fully connected convolutional neural networks can detect and identify discrete changes in patterns of two-dimensional data associated with toxicity. Bayesian neural networks with weight marginalization sometimes may have better prediction performance when compared to traditional approaches. With the further development of artificial intelligence, it is expected that ANNs will in the future become important parts of various accurate and affordable biosensors for detection of various toxic substances and evaluation of their biochemical properties. In this concise review article, we discuss the recent research focused on the scientific value of ANNs in evaluation and prediction of toxicity of chemical compounds.

Artificial intelligence approaches to the biochemistry of oxidative stress: Current state of the art

Artificial intelligence (AI) and machine learning models are today frequently used for classification and prediction of various biochemical processes and phenomena. In recent years, numerous research efforts have been focused on developing such models for assessment, categorization, and prediction of oxidative stress. Supervised machine learning can successfully automate the process of evaluation and quantification of oxidative damage in biological samples, as well as extract useful data from the abundance of experimental results. In this concise review, we cover the possible applications of neural networks, decision trees and regression analysis as three common strategies in machine learning. We also review recent works on the various weaknesses and limitations of artificial intelligence in biochemistry and related scientific areas. Finally, we discuss future innovative approaches on the ways how AI can contribute to the automation of oxidative stress measurement and diagnosis of diseases associated with oxidative damage.

Assessment and Establishment of Correlation between Reactive Oxidation Species, Citric Acid, and Fructose Level in Infertile Male Individuals: A Machine-Learning Approach

Background:

Biochemical complexity of seminal plasma and obesity has an important role in male infertility (MI); so far, it has not been possible to provide evidence of clinical significance for all of them.

Aims:

Our goal here is to evaluate the correlation between biochemical markers with semen parameters, which might play a role in MI.

Study Setting and Design:

We enlisted 100 infertile men as patients and 50 fertile men as controls to evaluate the sperm parameters and biochemical markers in ascertaining MI.

Materials and Methods:

Semen analyses, seminal fructose, citric acid, and reactive oxidation species (ROS) were measured in 100 patients and 50 controls.

Statistical Analysis:

Descriptive statistics, an independent t-test, Pearson correlation, and machine-learning approaches were used to integrate the various biochemical and seminal parameters measured to quantify the inter-relatedness between these measurements.

Results:

Pearson correlation results showed a significant positive correlation between body mass index (BMI) and fructose levels. Citric acid had a positive correlation with sperm count, morphology, motility, and volume but displayed a negative correlation with BMI and basal metabolic rate (BMR). However, BMI and BMR had a positive correlation with ROS. Sperm count, morphology, and motility were negative correlations with ROS. The machine-learning approach detected that pH was the most critical parameter with an inverse effect on citric acid, and BMI and motility were the most critical parameter for ROS.

Conclusion:

We recommend that evaluation of biochemical markers of seminal fluid may benefit in understanding the etiology of MI based on the functionality of accessory glands and ROS levels.

Interplay between oxidative damage, the redox status, and metabolic biomarkers during long-term fasting

Obesity and its related metabolic disorders, as well as infectious diseases like covid-19, are important health risks nowadays. It was recently documented that long-term fasting improves metabolic health and enhanced the total antioxidant capacity. The present study investigated the influence of a 10-day fasting on markers of the redox status in 109 subjects. Reducing power, 2,2’-Azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) diammonium salt radical cation(ABTS) radical scavenging capacity, and hydroxyl radical scavenging capacity increased significantly, and indicated an increase of circulating antioxidant levels. No differences were detected in superoxide scavenging capacity, protein carbonyls, and superoxide dismutase when measured at baseline and after 10 days of fasting. These findings were concomitant to a decrease in blood glucose, insulin, glycated hemoglobin (HbA1c), total cholesterol, low-density lipoprotein (LDL) and triglycerides as well as an increase in total cholesterol/high-density lipoprotein (HDL) ratio. In addition, the well-being index as well as the subjective energy levels increased, documenting a good tolerability. There was an interplay between redox and metabolic parameters since lipid peroxidation baseline levels (thiobarbituric acid reactive substances [TBARS]) affected the ability of long-term fasting to normalize lipid levels. A machine learning model showed that a combination of antioxidant parameters measured at baseline predicted the efficiency of the fasting regimen to decrease LDL levels. In conclusion, it was demonstrated that long-term fasting enhanced the endogenous production of antioxidant molecules, that act protectively against free radicals, and in parallel improved the metabolic health status. Our results suggest that the outcome of long-term fasting strategies could be depending on the baseline values of the antioxidative and metabolic status of subjects.

•

Long-term fasting increases the antioxidant capacity and decreases oxidative damage.

•

It improves the metabolic health status.

•

High TBARS levels at baseline limit the LDL reduction during long-term fasting.

•

The antioxidant status is related with the lipid lowering effect of long-term fasting.

Cardiovascular calcification: artificial intelligence and big data accelerate mechanistic discovery

Cardiovascular calcification is a health disorder with increasing prevalence and high morbidity and mortality. The only available therapeutic options for calcific vascular and valvular heart disease are invasive transcatheter procedures or surgeries that do not fully address the wide spectrum of these conditions; therefore, an urgent need exists for medical options. Cardiovascular calcification is an active process, which provides a potential opportunity for effective therapeutic targeting. Numerous biological processes are involved in calcific disease, including matrix remodelling, transcriptional regulation, mitochondrial dysfunction, oxidative stress, calcium and phosphate signalling, endoplasmic reticulum stress, lipid and mineral metabolism, autophagy, inflammation, apoptosis, loss of mineralization inhibition, impaired mineral resorption, cellular senescence and extracellular vesicles that act as precursors of microcalcification. Advances in molecular imaging and big data technology, including in multiomics and network medicine, and the integration of these approaches are helping to provide a more comprehensive map of human disease. In this Review, we discuss ectopic calcification processes in the cardiovascular system, with an emphasis on emerging mechanistic knowledge obtained through patient data and advances in imaging methods, experimental models and multiomics-generated big data. We also highlight the potential and challenges of artificial intelligence, machine learning and deep learning to integrate imaging and mechanistic data for drug discovery.

Classification of drug molecules for oxidative stress signalling pathway

In humans, oxidative stress is involved in the development of diabetes, cancer, hypertension, Alzheimers’ disease, and heart failure. One of the mechanisms in the cellular defence against oxidative stress is the activation of the Nrf2‐antioxidant response element (ARE) signalling pathway. Computation of activity, efficacy, and potency score of ARE signalling pathway and to propose a multi‐level prediction scheme for the same is the main aim of the study as it contributes in a big amount to the improvement of oxidative stress in humans. Applying the process of knowledge discovery from data, required knowledge is gathered and then machine learning techniques are applied to propose a multi‐level scheme. The validation of the proposed scheme is done using the K‐fold cross‐validation method and an accuracy of 90% is achieved for prediction of activity score for ARE molecules which determine their power to refine oxidative stress.

Beneficial Impact and Molecular Mechanism of Bacillus coagulans on Piglets' Intestine

The aim of this research was to investigate the beneficial impact and molecular mechanism of B. coagulans on piglets' intestine. Twenty-four 21 days old weaned piglets were allotted to three treatments: Control group (basal diet), B6 group (basal diet + 2 × 10⁶ CFU/g B. coagulans), and the B7 group (basal diet + 2 × 10⁷ CFU/g B. coagulans). The results showed that, compared with the control group, the B7 group had a reduced cholesterol content and gamma glutamyl transpeptidase (GGT) in plasma (p < 0.05); the B6 and B7 groups had a significantly decreased diarrhea rate and diamine oxidase (DAO) activity in plasma (p < 0.05), increased villus height in ileum and decreased crypt depth in the jejunum (p < 0.05); increased activities of superoxide dismutase (SOD) and catalase (CAT), and decreased the content of malondialdehyde (MDA) and H₂O₂ in the intestine (p < 0.05). These data suggested that supplementing B. coagulans had beneficial impacts on promoting nutrients' metabolism, maintaining intestinal integrity, and alleviating oxidative stress and diarrhea. Further research of molecular mechanisms showed changing expression levels of related proteins and genes, suggesting that these could be involved in the regulation of the impact. The community composition of the gut microbiota was also found to be altered in several operational taxonomic units within the genus, Prevotella (order Bacteroidales), and the order, Clostridiales.

Oxidative stress and fertility: incorrect assumptions and ineffective solutions?

One of the most important concerns in assisted reproduction (ART), and in particular ICSI, is the quality of sperm DNA. Oxidative stress is one of the major causes of damage to DNA and attempting to reduce generation of DNA damage related to reactive oxygen species (ROS) through consumption of antioxidants is often tempting. However, current antioxidant treatments, given irrespectively of clinically quantified deficiencies, are poorly efficient, potentially detrimental and over-exposure is risky. Here we discuss new treatments in relation to present day concepts on oxidative stress. This discussion includes stimulation of endogenous anti-ROS defense i.e. glutathione synthesis and recycling of homocysteine, the epicentre of multiple ROS-linked pathologies.

Chemopreventive efficacy of geraniol against 7,12-dimethylbenz[a]anthracene-induced hamster buccal pouch carcinogenesis

The status of lipid peroxidation, antioxidants, and detoxification enzymes were used as biochemical end points to assess the chemopreventive potential of geraniol, a monoterpene, in 7,12-dimethylbenz[a]anthracene (DMBA)-induced hamster buccal pouch carcinogenesis. Topical application of 0.5% DMBA in liquid paraffin, three times a week, for 14 weeks developed well-differentiated squamous cell carcinoma in the buccal pouch of golden Syrian hamsters. Although 100% tumor formation was noticed in hamsters treated with DMBA alone, intragastric administration of geraniol, at a dose of 250 mg/kg body weight (b.w.) to DMBA-treated hamster completely prevented the formation of oral tumors. Furthermore, geraniol significantly reduced lipid peroxidation by-products and improved the status of enzymatic and non-enzymatic antioxidants as well as modulated the status of phase I and phase II detoxification enzymes, favoring the excretion of carcinogenic metabolite, during DMBA-induced oral carcinogenesis. The present study concludes that the chemopreventive potential of geraniol relies on its anti-lipid peroxidative and antioxidant function as well as modulatory effects on phase I and II detoxification enzymes to excrete the carcinogenic metabolite, during DMBA-induced hamster buccal pouch carcinogenesis.

Macrophage autophagy and oxidative stress: an ultrastructural and immunoelectron microscopical study

The word autophagy broadly refers to the cellular catabolic processes that lead to the removal of damaged cytosolic proteins or cell organelles through lysosomes. Although autophagy is often observed during programmed cell death, it may also serve as a cell survival mechanism. Accumulation of reactive oxygen species within tissues and cells induces various defense mechanisms or programmed cell death. It has been shown that, besides inducing apoptosis, oxidative stress can also induce autophagy. To date, however, the regulation of autophagy in response to oxidative stress remains largely elusive and poorly understood. Therefore, the present study was designed to examine the ratio between oxidative stress and autophagy in macrophages after oxidant exposure (AAPH) and to investigate the ultrastructural localization of beclin-1, a protein essential for autophagy, under basal and stressful conditions. Our data provide evidence that oxidative stress induces autophagy in macrophages. We demonstrate, for the first time by immunoelectron microscopy, the subcellular localization of beclin-1 in autophagic cells.

Lifestyle Behaviours and Plasma Vitamin C and β-Carotene Levels from the ELAN Population (Liège, Belgium)

Several factors, including fruit and vegetables intakes, have been shown to significantly influence the plasma concentrations of the two antioxidants vitamin C and β-carotene. Deficiency levels of 6 mg/L (34.2 μM) for vitamin C and of 0.22 mg/L (0.4 μM) for β-carotene have been suggested below which cardiovascular risk might be increased. The present study performed on 897 presumably healthy subjects aged 40–60 years aimed to examine how modifiable lifestyle factors may be related to vitamin C and/or β-carotene deficiency. Gender, smoking, lack of regular physical activity and of daily fruit consumption (≥2/day), and social status (in particular, unemployment) were found to be significant risk factors for vitamin C deficiency. For β-carotene deficiency, the same factors were identified except social status; moreover, overweight and OC use in women were also found to have a deleterious effect. For non exposed subjects, the probability of developing vitamin C deficiency was 4% in men and 2.4% in women. This probability increased to 66.3% for men and to 44.3% for women (and even to 50.4% under OC use), when all risk factors were present. For β-carotene deficiency, the corresponding probabilities were equal to 29.7% in men and 13.7% in women (no risk factor present), and to 86.1% for men and 69.9% (91.6% for OC use) for women (all factors present), respectively.