Development of an expert system for the classification of myalgic encephalomyelitis/chronic fatigue syndrome.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a severe condition with an uncertain origin and a dismal prognosis. There is presently no precise diagnostic test for ME/CFS, and the diagnosis is determined primarily by the presence of certain symptoms. The current study presents an explainable artificial intelligence (XAI) integrated machine learning (ML) framework that identifies and classifies potential metabolic biomarkers of ME/CFS. Metabolomic data from blood samples from 19 controls and 32 ME/CFS patients, all female, who were between age and body mass index (BMI) frequency-matched groups, were used to develop the XAI-based model. The dataset contained 832 metabolites, and after feature selection, the model was developed using only 50 metabolites, meaning less medical knowledge is required, thus reducing diagnostic costs and improving prognostic time. The computational method was developed using six different ML algorithms before and after feature selection. The final classification model was explained using the XAI approach, SHAP. The best-performing classification model (XGBoost) achieved an area under the receiver operating characteristic curve (AUCROC) value of 98.85%. SHAP results showed that decreased levels of alpha-CEHC sulfate, hypoxanthine, and phenylacetylglutamine, as well as increased levels of N-delta-acetylornithine and oleoyl-linoloyl-glycerol (18:1/18:2)[2], increased the risk of ME/CFS. Besides the robustness of the methodology used, the results showed that the combination of ML and XAI could explain the biomarker prediction of ME/CFS and provided a first step toward establishing prognostic models for ME/CFS.

Diagnosis of Parkinson's disease based on voice signals using SHAP and hard voting ensemble method.

Parkinson's disease (PD) is the second most common progressive neurological condition after Alzheimer's. The significant number of individuals afflicted with this illness makes it essential to develop a method to diagnose the conditions in their early phases. PD is typically identified from motor symptoms or via other Neuroimaging techniques. Expensive, time-consuming, and unavailable to the general public, these methods are not very accurate. Another issue to be addressed is the black-box nature of machine learning methods that needs interpretation. These issues encourage us to develop a novel technique using Shapley additive explanations (SHAP) and Hard Voting Ensemble Method based on voice signals to diagnose PD more accurately. Another purpose of this study is to interpret the output of the model and determine the most important features in diagnosing PD. The present article uses Pearson Correlation Coefficients to understand the relationship between input features and the output. Input features with high correlation are selected and then classified by the Extreme Gradient Boosting, Light Gradient Boosting Machine, Gradient Boosting, and Bagging. Moreover, the weights in Hard Voting Ensemble Method are determined based on the performance of the mentioned classifiers. At the final stage, it uses SHAP to determine the most important features in PD diagnosis. The effectiveness of the proposed method is validated using 'Parkinson Dataset with Replicated Acoustic Features' from the UCI machine learning repository. It has achieved an accuracy of 85.42%. The findings demonstrate that the proposed method outperformed state-of-the-art approaches and can assist physicians in diagnosing Parkinson's cases.

Explainable Artificial Intelligence to Investigate the Contribution of Design Variables to the Static Characteristics of Bistable Composite Laminates.

Material properties, geometrical dimensions, and environmental conditions can greatly influence the characteristics of bistable composite laminates. In the current work, to understand how each input feature contributes to the curvatures of the stable equilibrium shapes of bistable laminates and the snap-through force to change these configurations, the correlation between these inputs and outputs is studied using a novel explainable artificial intelligence (XAI) approach called SHapley Additive exPlanations (SHAP). SHAP is employed to explain the contribution and importance of the features influencing the curvatures and the snap-through force since XAI models change the data into a form that is more convenient for users to understand and interpret. The principle of minimum energy and the Rayleigh-Ritz method is applied to obtain the responses of the bistable laminates used as the input datasets in SHAP. SHAP effectively evaluates the importance of the input variables to the parameters. The results show that the transverse thermal expansion coefficient and moisture variation have the most impact on the model's output for the transverse curvatures and snap-through force. The eXtreme Gradient Boosting (XGBoost) and Finite Element (FM) methods are also employed to identify the feature importance and validate the theoretical approach, respectively.

Detection of Monkeypox Cases Based on Symptoms Using XGBoost and Shapley Additive Explanations Methods.

The monkeypox virus poses a novel public health risk that might quickly escalate into a worldwide epidemic. Machine learning (ML) has recently shown much promise in diagnosing diseases like cancer, finding tumor cells, and finding COVID-19 patients. In this study, we have created a dataset based on the data both collected and published by Global Health and used by the World Health Organization (WHO). Being entirely textual, this dataset shows the relationship between the symptoms and the monkeypox disease. The data have been analyzed, using gradient boosting methods such as Extreme Gradient Boosting (XGBoost), CatBoost, and LightGBM along with other standard machine learning methods such as Support Vector Machine (SVM) and Random Forest. All these methods have been compared. The research aims to provide an ML model based on symptoms for the diagnosis of monkeypox. Previous studies have only examined disease diagnosis using images. The best performance has belonged to XGBoost, with an accuracy of 1.0 in reviews. To check the model's flexibility, k-fold cross-validation is used, reaching an average accuracy of 0.9 in 5 different splits of the test set. In addition, Shapley Additive Explanations (SHAP) helps in examining and explaining the output of the XGBoost model.

Exploring ND-011992, a quinazoline-type inhibitor targeting quinone reductases and quinol oxidases.

Bacterial energy metabolism has become a promising target for next-generation tuberculosis chemotherapy. One strategy to hamper ATP production is to inhibit the respiratory oxidases. The respiratory chain of Mycobacterium tuberculosis comprises a cytochrome bcc:aa3 and a cytochrome bd ubiquinol oxidase that require a combined approach to block their activity. A quinazoline-type compound called ND-011992 has previously been reported to ineffectively inhibit bd oxidases, but to act bactericidal in combination with inhibitors of cytochrome bcc:aa3 oxidase. Due to the structural similarity of ND-011992 to quinazoline-type inhibitors of respiratory complex I, we suspected that this compound is also capable of blocking other respiratory chain complexes. Here, we synthesized ND-011992 and a bromine derivative to study their effect on the respiratory chain complexes of Escherichia coli. And indeed, ND-011992 was found to inhibit respiratory complex I and bo3 oxidase in addition to bd-I and bd-II oxidases. The IC50 values are all in the low micromolar range, with inhibition of complex I providing the lowest value with an IC50 of 0.12 µM. Thus, ND-011992 acts on both, quinone reductases and quinol oxidases and could be very well suited to regulate the activity of the entire respiratory chain.

Chemical Genetics Screen of EVP4593 Sensitivity in Budding Yeast Identifies Effects on Mitochondrial Structure and Function.

Mitochondria are essential eukaryotic organelles. Mitochondrial dysfunction can lead to mitochondrial myopathies and may contribute to neurodegenerative diseases, cancer, and diabetes. EVP4593, a 6-aminoquinazoline derivative with therapeutic potential, has been shown to inhibit NADH-ubiquinone oxidoreductase (Complex I) of the mitochondrial electron transport chain, causing the release of reactive oxygen species (ROS) and a reduction in ATP synthesis. In isolated mitochondria, EVP4593 inhibits respiration in the nanomolar range (IC 50 = 14-25 nM). However, other EVP4593-specific effects on biological processes have also been described. Consistent with an effect on mitochondrial function in budding yeast, we find that EVP4593 [>25µM] induces a pronounced growth defect when wildtype cells are grown on a non-fermentable carbon source. This sensitivity to EVP4593 is exacerbated by deletion of PDR5 , an ABC transporter that confers multidrug resistance. To better understand the cellular pathways and processes affected by EVP4593, we conducted a genome-wide chemical genetics screen of the yeast knockout collection. The objective was to identify yeast gene deletion strains that exhibit growth defects when subjected to a sublethal concentration of EVP4593 [15µM]. Our screen identified 21 yeast genes that are required for resistance to 15µM EVP4593 in glycerol-containing media. The genes identified in our screen are functionally involved in several distinct categories including mitochondrial structure and function, translational regulation and nutritional sensing, cellular stress response and detoxification. Additionally, we identified cellular phenotypes associated with the exposure to EVP4593, including changes in mitochondrial structure. In conclusion, our study represents the first genome-wide screen in yeast to identify the genetic pathways and cell-protective mechanisms involved in EVP4593 resistance and reveals that this small molecule inhibitor affects both mitochondrial structure and function.

NDUFS3 knockout cancer cells and molecular docking reveal specificity and mode of action of anti-cancer respiratory complex I inhibitors.

Inhibition of respiratory complex I (CI) is becoming a promising anti-cancer strategy, encouraging the design and the use of inhibitors, whose mechanism of action, efficacy and specificity remain elusive. As CI is a central player of cellular bioenergetics, a finely tuned dosing of targeting drugs is required to avoid side effects. We compared the specificity and mode of action of CI inhibitors metformin, BAY 87-2243 and EVP 4593 using cancer cell models devoid of CI. Here we show that both BAY 87-2243 and EVP 4593 were selective, while the antiproliferative effects of metformin were considerably independent from CI inhibition. Molecular docking predictions indicated that the high efficiency of BAY 87-2243 and EVP 4593 may derive from the tight network of bonds in the quinone binding pocket, although in different sites. Most of the amino acids involved in such interactions are conserved across species and only rarely found mutated in human. Our data make a case for caution when referring to metformin as a CI-targeting compound, and highlight the need for dosage optimization and careful evaluation of molecular interactions between inhibitors and the holoenzyme.

Modeling of energy consumption factors for an industrial cement vertical roller mill by SHAP-XGBoost: a "conscious lab" approach.

Cement production is one of the most energy-intensive manufacturing industries, and the milling circuit of cement plants consumes around 4% of a year's global electrical energy production. It is well understood that modeling and digitalizing industrial-scale processes would help control production circuits better, improve efficiency, enhance personal training systems, and decrease plants' energy consumption. This tactical approach could be integrated using conscious lab (CL) as an innovative concept in the internet age. Surprisingly, no CL has been reported for the milling circuit of a cement plant. A robust CL interconnect datasets originated from monitoring operational variables in the plants and translating them to human basis information using explainable artificial intelligence (EAI) models. By initiating a CL for an industrial cement vertical roller mill (VRM), this study conducted a novel strategy to explore relationships between VRM monitored operational variables and their representative energy consumption factors (output temperature and motor power). Using SHapley Additive exPlanations (SHAP) as one of the most recent EAI models accurately helped fill the lack of information about correlations within VRM variables. SHAP analyses highlighted that working pressure and input gas rate with positive relationships are the key factors influencing energy consumption. eXtreme Gradient Boosting (XGBoost) as a powerful predictive tool could accurately model energy representative factors by R-square ever 0.80 in the testing phase. Comparison assessments indicated that SHAP-XGBoost could provide higher accuracy for VRM-CL structure than conventional modeling tools (Pearson correlation, Random Forest, and Support vector regression.

COV-ADSX: An Automated Detection System using X-ray Images, Deep Learning, and XGBoost for COVID-19.

Following the COVID-19 pandemic, scientists have been looking for different ways to diagnose COVID-19, and these efforts have led to a variety of solutions. One of the common methods of detecting infected people is chest radiography. In this paper, an Automated Detection System using X-ray images (COV-ADSX) is proposed, which employs a deep neural network and XGBoost to detect COVID-19. COV-ADSX was implemented using the Django web framework, which allows the user to upload an X-ray image and view the results of the COVID-19 detection and image's heatmap, which helps the expert to evaluate the chest area more accurately.

A Novel Framework Based on Deep Learning and ANOVA Feature Selection Method for Diagnosis of COVID-19 Cases from Chest X-Ray Images.

Background and Objective. The new coronavirus disease (known as COVID-19) was first identified in Wuhan and quickly spread worldwide, wreaking havoc on the economy and people's everyday lives. As the number of COVID-19 cases is rapidly increasing, a reliable detection technique is needed to identify affected individuals and care for them in the early stages of COVID-19 and reduce the virus's transmission. The most accessible method for COVID-19 identification is Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR); however, it is time-consuming and has false-negative results. These limitations encouraged us to propose a novel framework based on deep learning that can aid radiologists in diagnosing COVID-19 cases from chest X-ray images. Methods. In this paper, a pretrained network, DenseNet169, was employed to extract features from X-ray images. Features were chosen by a feature selection method, i.e., analysis of variance (ANOVA), to reduce computations and time complexity while overcoming the curse of dimensionality to improve accuracy. Finally, selected features were classified by the eXtreme Gradient Boosting (XGBoost). The ChestX-ray8 dataset was employed to train and evaluate the proposed method. Results and Conclusion. The proposed method reached 98.72% accuracy for two-class classification (COVID-19, No-findings) and 92% accuracy for multiclass classification (COVID-19, No-findings, and Pneumonia). The proposed method's precision, recall, and specificity rates on two-class classification were 99.21%, 93.33%, and 100%, respectively. Also, the proposed method achieved 94.07% precision, 88.46% recall, and 100% specificity for multiclass classification. The experimental results show that the proposed framework outperforms other methods and can be helpful for radiologists in the diagnosis of COVID-19 cases.

Short-chain aurachin D derivatives are selective inhibitors of E. coli cytochrome bd-I and bd-II oxidases.

Cytochrome bd-type oxidases play a crucial role for survival of pathogenic bacteria during infection and proliferation. This role and the fact that there are no homologues in the mitochondrial respiratory chain qualify cytochrome bd as a potential antimicrobial target. However, few bd oxidase selective inhibitors have been described so far. In this report, inhibitory effects of Aurachin C (AurC-type) and new Aurachin D (AurD-type) derivatives on oxygen reductase activity of isolated terminal bd-I, bd-II and bo3 oxidases from Escherichia coli were potentiometrically measured using a Clark-type electrode. We synthesized long- (C10, decyl or longer) and short-chain (C4, butyl to C8, octyl) AurD-type compounds and tested this set of molecules towards their selectivity and potency. We confirmed strong inhibition of all three terminal oxidases for AurC-type compounds, whereas the 4(1H)-quinolone scaffold of AurD-type compounds mainly inhibits bd-type oxidases. We assessed a direct effect of chain length on inhibition activity with highest potency and selectivity observed for heptyl AurD-type derivatives. While Aurachin C and Aurachin D are widely considered as selective inhibitors for terminal oxidases, their structure-activity relationship is incompletely understood. This work fills this gap and illustrates how structural differences of Aurachin derivatives determine inhibitory potency and selectivity for bd-type oxidases of E. coli.

Identification of novel anti-cancer agents by the synthesis and cellular screening of a noscapine-based library.

Noscapine is a natural product first isolated from the opium poppy (Papaver somniferum L.) with anticancer properties. In this work, we report the synthesis and cellular screening of a noscapine-based library. A library of novel noscapine derivatives was synthesized with modifications in the isoquinoline and phthalide scaffolds. The so generated library, consisting of fifty-seven derivatives of the natural product noscapine, was tested against MDA-MB-231 breast cancer cells in a cellular proliferation assay (with a Z' > 0.7). The screening resulted in the identification of two novel noscapine derivatives as inhibitors of MDA cell growth with IC50 values of 5 µM and 1.5 µM, respectively. Both hit molecules have a five-fold and seventeen-fold higher potency, compared with that of lead compound noscapine (IC50 26 µM). The identified active derivatives retain the tubulin-binding ability of noscapine. Further testing of both hit molecules, alongside the natural product against additional cancer cell lines (HepG2, HeLa and PC3 cells) confirmed our initial findings. Both molecules have improved anti-proliferative properties when compared to the initial natural product, noscapine.

Synthesis and in Vitro Evaluation of Novel 5-Nitroindole Derivatives as c-Myc G-Quadruplex Binders with Anticancer Activity.

Lead-optimization strategies for compounds targeting c-Myc G-quadruplex (G4) DNA are being pursued to develop anticancer drugs. Here, we investigate the structure-activity- relationship (SAR) of a newly synthesized series of molecules based on the pyrrolidine-substituted 5-nitro indole scaffold to target G4 DNA. Our synthesized series allows modulation of flexible elements with a structurally preserved scaffold. Biological and biophysical analyses illustrate that substituted 5-nitroindole scaffolds bind to the c-Myc promoter G-quadruplex. These compounds downregulate c-Myc expression and induce cell-cycle arrest in the sub-G1/G1 phase in cancer cells. They further increase the concentration of intracellular reactive oxygen species. NMR spectra show that three of the newly synthesized compounds interact with the terminal G-quartets (5'- and 3'-ends) in a 2 : 1 stoichiometry.

Concise Synthesis of 1,4-Benzoquinone-Based Natural Products as Mitochondrial Complex I Substrates and Substrate-Based Inhibitors.

A short, efficient one-step synthesis of 2-methyl-5-(3-methyl-2-butenyl)-1,4-benzoquinone, a natural product from Pyrola media is described. The synthesis is based on a direct late C-H functionalization of the quinone scaffold. The formation of the natural product was confirmed by means of 2D-NMR spectroscopy. Additional derivatives were synthesized and tested alongside the natural product as potential substrate and substrate-based inhibitors of mitochondrial complex I (MCI). The structure-activity relationship study led to the discovery of 3-methylbuteneoxide-1,4-anthraquinone (1 i), an inhibitor with an IC50 of 5 µM against MCI. The identified molecule showed high selectivity for MCI when tested against other quinone-converting enzymes, including succinate dehydrogenase, and the Na (+)-translocating NADH:quinone oxidoreductase. Moreover, the identified inhibitor was also active in cell-based proliferation assays. Therefore, 1 i can be considered as a novel chemical probe for MCI.

Synthesis and Biological Screening of New Lawson Derivatives as Selective Substrate-Based Inhibitors of Cytochrome bo3 Ubiquinol Oxidase from Escherichia coli.

The respiratory chain of Escherichia coli contains two different types of terminal oxidase that are differentially regulated as a response to changing environmental conditions. These oxidoreductases catalyze the reduction of molecular oxygen to water and contribute to the proton motive force. The cytochrome bo3 oxidase (cyt bo3 ) acts as the primary terminal oxidase under atmospheric oxygen levels, whereas the bd-type oxidase is most abundant under microaerobic conditions. In E. coli, both types of respiratory terminal oxidase (HCO and bd-type) use ubiquinol-8 as electron donor. Here, we assess the inhibitory potential of newly designed and synthesized 3-alkylated Lawson derivatives through L-proline-catalyzed three-component reductive alkylation (TCRA). The inhibitory effects of these Lawson derivatives on the terminal oxidases of E. coli (cyt bo3 and cyt bd-I) were tested potentiometrically. Four compounds were able to reduce the oxidoreductase activity of cyt bo3 by more than 50 % without affecting the cyt bd-I activity. Moreover, two inhibitors for both cyt bo3 and cyt bd-I oxidase could be identified. Based on molecular-docking simulations, we propose binding modes of the new Lawson inhibitors. The molecular fragment benzyl enhances the inhibitory potential and selectivity for cyt bo3 , whereas heterocycles reduce this effect. This work extends the library of 3-alkylated Lawson derivatives as selective inhibitors for respiratory oxidases and provides molecular probes for detailed investigations of the mechanisms of respiratory-chain enzymes of E. coli.

Polymerase assays for lead discovery: An overall review of methodologies and approaches.

Polymerases represent an attractive molecular target for antibacterial drug development, antiviral intervention and cancer therapy. Over the past decade, academic groups and scientists from pharmaceutical industry have developed a large plethora of different functional assays to monitor the enzymatic reaction catalyzed by polymerases. These assays were used to enable high-throughput screening (HTS) for lead discovery purposes, as well as hit-to-lead (H2L) drug profiling activities. In both cases the choice of the assay technology is critical and to the best of our knowledge, there is no review available to help scientists to choose the most suitable assay. This review summarizes the most common functional assays developed to monitor the enzymatic activity of polymerases and discusses the advantages and disadvantages of each assay. Assays are presented and evaluated in term of cost, ease of use, high-throughput screening compatibility and liability towards delivering false positives and false negatives.

The Effects of Mental Health Training Program on Stress, Anxiety, and Depression during Pregnancy.

BACKGROUND: The process of becoming a mother is considered as an enjoyable and evolutionary event of women's life. However, due to physical and mental changes, it can be associated with some degree of stress and anxiety that may lead to mental health problems. This study aimed to compare the effects of mental health training during pregnancy on stress, anxiety, and depression between two groups of couples and pregnant women. MATERIALS AND METHODS: This randomized clinical trial was conducted on 120 pregnant women referring to health centers in Isfahan, Iran, from September to February 2016. The participants were randomly divided into three groups: couples (with the partner present), pregnant women (without the partner present), and control group (routine care). After completing the pretest, the intervention groups received four sessions of pregnancy mental health training. Data were collected using the Depression, Anxiety, and Stress Scales (DASS-42) and a demographic characteristics form. The collected data were analyzed using Statistical Package for the Social Sciences software. RESULTS: Before the intervention, no statistical difference was observed among the three groups in the mean scores of stress, anxiety, and depression. The mean score of depression, anxiety, and stress decreased significantly in the intervention groups 2 weeks after the intervention respectively (F=5.84, p=0.004), (F=14.76, p < 0.001) and (F=11.98, p < 0.001). No significant difference was observed between the couples and pregnant women groups in terms of depression (p = 0.140). CONCLUSIONS: The results of this study showed that mental health training for pregnant women, especially with the presence of the partner, is a useful intervention in preventing stress, anxiety, and depression.

A miniaturized assay for kinetic characterization of the Na+-translocating NADH:ubiquinone oxidoreductase from Vibrio cholerae.

We demonstrate the miniaturization of an enzymatic assay for the determination of NADH oxidation and quinone reduction by the Na+ -translocating NADH quinone oxidoreductase (NQR) in the 96-well plate format. The assay is based on the spectrophotometric detection of NADH consumption and quinol formation. We validated the new method with known inhibitors of the NQR and optimized conditions for high-throughput screening as demonstrated by excellent Z-factors well above the accepted threshold (≥0.5). Overall, the method allows the screening and identification of potential inhibitors of the NQR, and rapid characterization of NQR variants obtained by site-specific mutagenesis.

Identification of 4-N-[2-(4-phenoxyphenyl)ethyl]quinazoline-4,6-diamine as a novel, highly potent and specific inhibitor of mitochondrial complex I.

By probing the quinone substrate binding site of mitochondrial complex I with a focused set of quinazoline-based compounds, we identified substitution patterns as being critical for the observed inhibition. The structure activity relationship study also resulted in the discovery of the quinazoline 4-N-[2-(4-phenoxyphenyl)ethyl]quinazoline-4,6-diamine (EVP4593) as a highly potent inhibitor of the multisubunit membrane protein. EVP4593 specifically and effectively reduces the mitochondrial complex I-dependent respiration with no effect on the respiratory chain complexes II-IV. Similar to established Q-site inhibitors, EVP4593 elicits the release of reactive oxygen species at the flavin site of mitochondrial complex I. Recently, EVP4593 was nominated as a lead compound for the treatment of Huntingtons disease. Our results challenge the postulated primary mode-of-action of EVP4593 as an inhibitor of NF-κB pathway activation and/or store-operated calcium influx.

PAIN-less identification and evaluation of small molecule inhibitors against protein tyrosine phosphatase 1B.

A highly miniaturized biochemical assay was set up to test a focused set of natural products against the enzymatic activity of protein tyrosine phosphatase 1B (PTP1B). The screen resulted in the identification of the natural product alkaloids, berberine and palmatine as well as α-tocopheryl succinate (α-TOS) as potential inhibitors of PTP1B. In a second step, several read-out and counter assays were applied to confirm the observed inhibitory activity of the identified hits and to remove false positives which target the enzymatic activity of PTP1B by a non-specific mechanism, also known as PAINS (pan-assay interference compounds). Both, berberine and palmatine were identified as false positives which interfered with the assay read-out. Using NMR spectroscopy, self-association via stacking interactions was detected for berberine in aqueous media, which may also contribute to the non-specific inhibition of PTP1B. α-TOS was confirmed as a novel reversible and competitive inhibitor of PTP1B. A concise structure-activity relationship study identified the carboxyl group and the saturated phytyl-side chain as being critical for PTP1B inhibition.