Cross-validated Values Research Articles

3D-QSAR studies on Pyrido[2,3-d]pyrimidine Derivatives as Fibroblast Growth Factor Receptor 1 Inhibitors: Application of Molecular Field Analysis (MFA)

Three-dimensional quantitative structure–activity relationship (3D-QSAR) models were developed for 77 pyrido[2,3-d]pyrimidines derivatives, inhibiting fibroblast growth factor receptor 1 (FGFR1). The QSAR model was developed using 56 compounds and its predictive ability was assessed using a test set of 21 compounds. The predictive 3D-QSAR models have conventional r2 values of 0.920 for MFA and the cross-validated coefficient r2cv values of 0.884 for MFA. The results of 3D-QSAR methodologies provide a powerful tool directed to the design of potent and selective pyrido[2,3-d]pyrimidines inhibitors.

Rapid and nondestructive detection of oil and fatty acid content of soybean using hyperspectral imaging

Soybean (Glycine max (L.) Merrill) is an important oil crop with significant economic value worldwide, the breeding of soybean varieties requires not only high oil content, but also the appropriate ratio of fatty acids. In this study, a rapid and nondestructive detection method for oil and fatty acid content of soybean was developed using hyperspectral imaging (HSI). Five wavelength selection methods, including competitive adaptive re-weighted sampling, random frogs, iteratively retaining informative variables, uninformative variable elimination, and genetic algorithm, were used to select the important variables, and partial least squares (PLS) was used to build the prediction models. Among five methods, uninformative variable elimination provided with satisfactory results for the prediction of oil content and fatty acid content of soybean. The validation results showed that oil content and linolenic acid had good performance with correlation coefficient for cross-validation (R2cv) values of 0.90 and 0.92, and correlation coefficient predictive (R2p) values of 0.93 and 0.93, respectively. The absolute errors between the predicted and actual values of oil and linolenic acid content ranged from -1.39% to 0.97% and from -0.86% to 1.07%, respectively. In addition, oleic acid had better results with R2cv, RPDcv, and R2p values of 0.84, 2.45, and 0.85, respectively. Furthermore, Compared the models developed using near infrared (NIR), the the average relative errors of the established HSI models for oil content, oleic acid, linoleic acid and linolenic acid in soybean decreased by 48.94%, 21.85%, 37.98% and 39.31%, respectively. Therefore, HSI has great potential to detect oil content and major fatty acids in soybeans.

Medical diagnosis based on artificial intelligence and decision support system in the management of health development.

Medical diagnosis plays a critical role in our daily lives. Every day, over 10 billion cases of both mental and physical health disorders are diagnosed and reported worldwide. To diagnose these disorders, medical practitioners and health professionals employ various assessment tools. However, these tools often face scrutiny due to their complexity, prompting researchers to increase their experimental parameters to provide accurate justifications. Additionally, it is essential for professionals to properly justify, interpret, and analyse the results from these prediction tools. This research paper explores the use of artificial intelligence and advanced analytics in developing Clinical Decision Support Systems (CDSS). These systems are capable of diagnosing and detecting patterns of various medical disorders. Various machine learning algorithms contribute to building these assessment tools, with the Network Pattern Recognition (NEPAR) algorithm being the first to aid in developing CDSS. Over time, researchers have recognised the value of machine learning-based prediction models in successfully justifying medical diagnoses. The proposed CDSS models have demonstrated the ability to diagnose mental disorders with an accuracy of up to 89% using only 28 questions, without requiring human input. For physical health issues, additional parameters are used to enhance the accuracy of CDSS models. Consequently, medical professionals are increasingly relying on these machine learning-based CDSS models, utilising these tools to improve medical diagnosis and assist in decision-making. The different cross-validation values are considered to remove the data biasness.

Bioinformatic analysis of neuropeptide related genes in patients diagnosed with invasive breast carcinoma

PurposeNeuropeptide receptors are expressed in many malignancies. Effectors involved in the action mechanisms of HCRTR1, HCRTR2, NPY4R (PPYR1) may be related to breast cancer (BC). Genes encoding these receptors and PPY and PTPN11 genes were aimed to examine via bioinformatics tools in the BRCA cohort. To our knowledge, this is the first study in which these receptor genes and PP, which have not found much research in BC, are examined together with PTPN11 and analyzed comprehensively in large patient cohorts from public databases. MethodscBioPortal was used for gene alteration analyses, GeneMania for association analyses with other genes, Kaplan-Meier Plotter for Overall Survival (OS) and Relapse Free Survival (RFS) analyses, UALCAN for methylation analyses, TIMER2.0 for expression analyses, The Human Protein Atlas database for expression validations, TIMER for immune infiltration analyses, WEKA 3.8.6 for diagnostic classification performances of the genes based on Random Forest Classifier and Enrichr-KG for Gene Ontology (GO) Biological Process (BP) and KEGG analysis. Results19 (1.9 %) nucleotide changes were found in 996 cases. Missense mutation is most common. Decreased expression levels of the HCRTR1 gene were associated with shorter OS and RFS, but decreased expression levels of the PTPN11 gene were associated with longer OS and RFS. Decreased expression levels NPY4R (PPYR1) gene were associated with shorter RFS. Increased expression levels of HCRTR2 and PPY genes were associated with longer RFS. HCRTR1 and NPY4R (PPYR1) genes were statistically hypermethylated; conversely HCRTR2 and PPY genes were hypomethylated. There was no significant change in PTPN11 gene promoter methylation level. HCRTR1, NPY4R (PPYR1) and PTPN11 gene expressions were downregulated; conversely, HCRTR2 and PPY gene expressions upregulated. Weak correlations were observed between NPY4R (PPYR1) gene expression and CD4+ T Cell, Neutrophil, Dendritic Cell and between PTPN11 gene expression and CD8+ T Cell, Macrophage, Neutrophil, Dendritic Cell infiltrations. Area under the receiver operating characteristics curve values of the 10-fold cross-validation and by splitting the dataset in a ratio of 80:20 models were 0.930 and 0.963 respectively. HCRTR2 and HCRTR1 belong to regulation of cytosolic calcium ion concentration, cellular calcium ion homeostasis GO BPs. ConclusionIn BC patients, increases in HCRTR2 and PPY gene expressions could be considered as positive prognostic factors. Decreases in HCRTR1 and NPY4R (PPYR1) gene expressions could be considered as negative prognostic factors. Decreased expression of PTPN11 gene may have a positive prognostic factor. Changes in existing genes are likely to be both a biomarker and therapeutic target for BC. However, experimental and clinical studies are needed to elucidate the mechanisms underlying these neuropeptide receptors in terms of breast carcinogenesis.

Electronic Nose Analysis of Exhaled Breath Volatile Organic Compound Profiles during Normoxia, Hypoxia, and Hyperoxia.

This study investigates volatile organic compound (VOC) profiles in the exhaled breath of normal subjects under different oxygenation conditions-normoxia (FiO2 21%), hypoxia (FiO2 11%), and hyperoxia (FiO2 35%)-using an electronic nose (e-nose). We aim to identify significant differences in VOC profiles among the three conditions utilizing principal component analysis (PCA) and canonical discriminant analysis (CDA). Our results indicate distinct VOC patterns corresponding to each oxygenation state, demonstrating the potential of e-nose technology in detecting physiological changes in breath composition (cross-validated accuracy values: FiO2 21% vs. FiO2 11% = 63%, FiO2 11% vs. FiO2 35% = 65%, FiO2 21% vs. FiO2 35% = 71%, and p < 0.05 for all). This research underscores the viability of breathomics in the non-invasive monitoring and diagnostics of various respiratory and systemic conditions.

Comparative chemometric modeling of fresh and dry cannabis inflorescences using FT-NIR spectroscopy: Quantification and classification insights.

Cannabis sativa L. inflorescences are rich in cannabinoids and terpenes. Traditional chemical analysis methods for cannabinoids and terpenes, such as liquid and gas chromatography (using UV or MS detectors), are expensive and time-consuming. This study explores the use of Fourier transform near-infrared (FT-NIR) spectroscopy combined with chemometric approaches for classifying cannabis chemovars and predicting cannabinoid and terpene concentrations for the first time in freshly harvested (wet) cannabis inflorescence. The study also compares the performance of FT-NIR spectroscopy on wet versus dry cannabis inflorescences. Spectral data from 187 samples across seven cannabis chemovars were analyzed using partial least squares-discriminant analysis (PLS-DA) and partial least squares-regression (PLS-R) models. The PLS-DA models effectively classified chemovars and major classes using only two latent variables (LVs) with minimal overfitting risk, with sensitivity, specificity, and accuracy values approaching 1. Despite the high water content in wet cannabis inflorescence, the PLS-R models demonstrated good to excellent predictive capabilities for nine cannabinoids and eight terpenes using FT-NIR spectra for the first time, achieving cross-validation and prediction R-squared values greater than 0.7, ratio of performance to interquartile range (RPIQ) exceeding 2, and a RMSECV/RMSEC ratio below 1.24. However, the low-cannabidiolic acid submodel and (-)-Δ9-trans-tetrahydrocannabinol model showed poor predictive performance. Some cannabinoid and terpene prediction models in wet cannabis inflorescence exhibited lower predictive capabilities compared with previously published models for dry cannabis inflorescence. These findings suggest that FT-NIR spectroscopy can be a viable rapid on-site analytical tool for growers during the inflorescence flowering stage.

K-Nearest Neighbor Method for Early Detection of Diabetes Patients Based on Symptoms and Clinical Data

Diabetes is a chronic disease rarely detected and develops quickly. Diabetes can trigger other chronic diseases such as kidney failure and heart disease. Early detection is necessary to help patients treat diabetes before the disease becomes more severe. Various health examination methods to detect diabetes, but these examinations require medical expert action and cannot be carried out by anyone. In addition, examination costs are often unaffordable. This research aims to apply data mining methods, especially k-Nearest Neighbor (KNN), for early detection of diabetes patients based on disease symptoms and patient clinical data. KNN is used to classify patient symptoms and clinical data into two classes, diabetes and non-diabetes, calculating the distance between test data and training data using Euclidean Distance. The research results show that a lower k-value provides a higher accuracy value. However, accuracy at low k-values ​​is insufficient to conclude the performance of KNN for early diabetes detection. High accuracy at low k-values ​​has the potential for overfitting, and the model is not generalizing well. Apart from that, if you use a low k-value, the model only sees patterns from 1 or a few neighbors, which results in the pattern of the data not being captured by the KNN model using a k-value that is too high also risks the model becoming underfitting. The model is too general, which makes the model unreliable. This research made use of the k-fold cross-validation technique to circumvent these issues. It is possible to avoid overfitting in the constructed KNN model by employing this method. The researchers are employing k-fold=10 and k-fold=20 in their investigation. KNN This research carried out this analysis by looking at the accuracy of each iteration of the k and k-fold values. The higher the k-fold value, the more accuracy the KNN produces. Inversely proportional to the k-fold cross-validation value, the higher the k-value in KNN, the decreases the accuracy. The KNN method applied in this research provides an accuracy of 98.2692% with higher precision than recall. These findings suggest that KNN can be an effective and efficient tool for early diabetes detection.

Evaluating the sustainability of groundwater abstraction in small watersheds using time series analysis

Groundwater is crucial in meeting the water needs of communities, industries, and ecosystems. The effective management of this resource is essential for maintaining the long-term stability of both the environmental and socio-economic conditions. This work focuses on assessing the sustainability of groundwater abstraction in Charlottetown, Prince Edward Island, specifically from well fields situated within the small-scale watersheds of Winter River and North River. The advanced time series analysis techniques, including Vector Error Correction Models (VECM), Impulse Response Functions (IRFs), and Forecast Error Variance Decomposition (FEVD) are employed to investigate the relationships among precipitation, temperature, groundwater abstraction, and stream flows. The analysis of IRFs reveals dynamic responses of streams to various shocks, including the variation of temperature, precipitation and well discharges, which showcase related immediate impacts, short-term responses, and long-term relationships. Temperature fluctuations exhibit complex responses, with short-term response decreases followed by sustained increases. Precipitation emerges as a dominant factor, showing sustained positive impacts on streamflow. Well operations significantly influence stream ecosystems, emphasizing the importance of optimized well operation strategies. The FEVD revealed that the first forecast horizon for all stream flows is primarily influenced by past shocks in precipitation with 16–55% in addition to other factors. The walk forward cross-validated forecast values for the next 24 months align with seasonal trends, reflecting declining discharge in summer, variable but generally decreasing discharge in fall, and increased discharge in winter and spring. The study findings provide recommendations for sustainable groundwater abstraction practices, including optimizing well operation strategies, community and stakeholder engagement, and ecosystem preservation.

Selection of optimal knot point and best geographic weighted on geographically weighted spline nonparametric regression model

This study proposes the development of a nonparametric regression model combined with geographically weighted regression. The regression model considers geographical factors and has a data pattern that does not follow a parametric form to overcome the problem of spatial heterogeneity and unknown regression functions. This study aims to model provincial food security index data in Indonesia with the GWSNR model, so finding the optimal knot point and the best geographic weighting is necessary. We propose the selection of optimal knot points using the Cross Validation (CV) and Generalized Cross Validation (GCV) methods. The optimal knot point will control the accuracy of the regression curve as we also consider the MSE value in showing the ability of the model. In addition, we determine the best geographic weighting and test the significance of the model parameters. We demonstrate the GWSNR model on food security index data. The best GWSNR model uses the Gaussian kernel weighting function and selects the optimal knot point as one-knot point based on the lowest CV and GCV values. Simultaneous and partial parameter test results show that there are 10 area classifications with different effects on each group of classification results. Some of the highlights of the proposed approach are:•The method is the development of a nonparametric regression model with geographic weighting, which combines nonparametric and spatial regression in modeling the national food security index.•There are three-knot points tested in nonparametric truncated spline regression and three geographic weightings in spatial regression. Then the optimal knot point and best bandwidth are determined using Cross Validation and Generalized Cross Validation.•This article will determine regional groupings in Indonesia in 2022 based on significant predictors in modeling the national food security index numbers.

Simple Method for Calcium Determination in Crude Oil Emulsion Using Digital Image Colorimetry

A portable device for digital image colorimetry (DIC) is reported for the determination of Ca in crude oil emulsions. ASTM D4807 was used for sample preparation for the isolation of saline species containing Ca. DIC was evaluated based on the complexation reactions with Ca using calcein, murexide, and calcon. Partial least squares (PLS) provided the best determination coefficients (higher than 0.990) for all complexing reagents. Significant interference of Mg was observed for the determination of Ca using calcein. PLS models with the lowest root mean square error of cross validation (RMSECV) values were obtained for murexide and calcon for a concentration of 0.250 mmol L−1 at pH of 13. The best conditions for camera focal length were 11 and 2 mm for murexide and calcon. For light intensity, the optimized conditions for murexide and calcon was 180 lux. Stabilities of color complexes over the time were 30 and 15 min for murexide and calcon, respectively. DIC/murexide provided the lowest root mean square error of prediction (RMSEP) and a linear response was observed from 0.5 to 10 mg L−1 Ca and the relative standard deviation (RSD) was lower than 10%. Significant differences were not observed between the results obtained by DIC/murexide and those obtained by microwave-assisted wet digestion (MAWD) with determination by inductively coupled plasma-optical emission spectrometry (ICP-OES). A limit of quantification of 0.50 mg kg−1 Ca were obtained using DIC/murexide. This approach is an alternative and useful method for the determination of Ca in crude oil samples, with advantages of miniaturization, low cost, and ease of operation.

Global and regional final point-of-drinking water prevalence of Vibrio pathogens: a systematic analysis with socioeconomic, global health security, and WASH indices-guided meta-regressions

The final point-of-drinking water (FPODW) exposure to Vibrio and waterborne pathogens remains a misaim surveillance target. Therefore, the current study purposed to estimate the global and regional prevalence of Vibrio pathogens in FPODW. Vibrio-FPODW data derived from integrated databases per PRISMA protocol were fitted to a random-intercept-logistic mixed-effects and meta-regression models. The global FPODW Vibrio prevalence was 5.13% (95%CI: 2.24–11.30) with 7.76% (6.84–8.78) cross-validated value. Vibrio prevalence in different FPODW varied with the highest in unclassified (13.98%, 3.98–38.95), household stored (6.42%, 1.16–28.69), municipal (4.39%, 1.54–11.90), and bottled (1.06%, 0.00–98.57) FPODW. Regionally, FPODW Vibrio prevalence varied significantly with highest in Africa (6.31%, 0.49–47.88), then Asia (4.83%, 2.01–11.18). Similarly, it varied significantly among income classification with the highest from low-income (8.77%, 0.91–50.05), then lower-middle-income (6.16%, 2.75–13.20), upper-middle-income (0.23%, 0.00–82.04), and 0.94% (0.19–2.72) in high-income economies. Among the WHO region, it varied significantly from 1.41% (0.17–10.45) in Eastern Mediterranean, 6.31% (0.49–47.88) in Africa to 8.86% (3.85–19.06) in South-East Asia and declining among SDI-quintiles from 11.64% (3.29–33.83) in Low-SDI, 10.59% (4.58–22.61) in High-middle-SDI to 0.26% (0.01–9.09) in Middle-SDI. FPODW Vibrio prevalence was 7.31% (2.94–17.03) in the low-GHSIG, followed by 4.55% (0.00–100.00) in the upper-GHSIG, and 2.21% (0.31–14.24) in middle-GHSIG; rural (4.18%, 0.06–76.17) and urban (5.28%, 2.35–11.44) settings. Also, sample size, SDI, SDI-quintiles, and nation significantly explained 14.12%, 10.91%, 30.35%, and 87.65% variance in FPODW Vibrio prevalence, respectively as a univariate influence. Additionally, 11.90% variance in FPODW Vibrio prevalence explained mortality rate attributed to unsafe WASH services. In conclusion, the study revealed a substantial high FPODW prevalence of Vibrio calling for initiative-taking and intentional surveillances of waterborne pathogens at the neglected stage across nations in order to achieve sustainably the SDG 3.

APPLICATION OF NONPARAMETRIC REGRESSION SPLINE TRUNCATED FOR MODELING THE HEIGHT OF YEOP CHAGI KICKS OF TAEKWONDO ATHLETES IN SAMARINDA CITY

Nonparametric regression is a model approach method that is used when the shape of the regression curve between the response variable and the predictor variable is assumed to have an unknown shape or pattern. One of the estimators in the nonparametric regression approach is the truncated spline which has the ability to handle data whose behavior changes at certain sub intervals. The purpose of this study was to obtain the estimated value of the parameters of the nonparametric regression model with a truncated spline approach at one knot point, two knot points, and three knot points for kick height data of yeop chagi taekwondo athletes in Samarinda City. The results showed that the truncated spline nonparametric regression model was the best in modeling high kick height data for yeop chagi taekwondo athletes in Samarinda City with three knot points. This model has the minimum Generalized Cross Validation (GCV) value of 7.94 with an R2 value of 94.72% and a Mean Square Error (MSE) value of 2.62. Based on the results of the model parameter significance test, it was concluded that the factors that influence the kick height of the yeop chagi taekwondo athlete in Samarinda City are flexibility, leg power, leg length, and waist circumference.

Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression.

Identifying predictors of treatment response to repetitive transcranial magnetic stimulation (rTMS) remain elusive in treatment-resistant depression (TRD). Leveraging electronic medical records (EMR), this retrospective cohort study applied supervised machine learning (ML) to sociodemographic, clinical, and treatment-related data to predict depressive symptom response (>50% reduction on PHQ-9) and remission (PHQ-9 < 5) following rTMS in 232 patients with TRD (mean age: 54.5, 63.4% women) treated at the University of California, San Diego Interventional Psychiatry Program between 2017 and 2023. ML models were internally validated using nested cross-validation and Shapley values were calculated to quantify contributions of each feature to response prediction. The best-fit models proved reasonably accurate at discriminating treatment responders (Area under the curve (AUC): 0.689 [0.638, 0.740], p < 0.01) and remitters (AUC 0.745 [0.692, 0.797], p < 0.01), though only the response model was well-calibrated. Both models were associated with significant net benefits, indicating their potential utility for clinical decision-making. Shapley values revealed that patients with comorbid anxiety, obesity, concurrent psychiatric medication use, and more chronic TRD were less likely to respond or remit following rTMS. Patients with trauma and former tobacco users were more likely to respond. Furthermore, delivery of intermittent theta burst stimulation and more rTMS sessions were associated with superior outcomes. These findings highlight the potential of ML-guided techniques to guide clinical decision-making for rTMS treatment in patients with TRD to optimize therapeutic outcomes.

Estimation curve of multivariate adaptive biresponse fuzzy clustering means regression splines approach to stunting and wasting cases in Southeast Sulawesi

This article offers a new method of clustering data. This method is constructed by combining the multivariate adaptive regression spline biresponse continuous model (MARSBC) with the fuzzy clustering means (FCM) approach, called the multivariate adaptive biresponse fuzzy clustering means regression splines (MABFCMRS) model. This method uses patterns obtained from the MARSBC model to separate data into specific groups. Observing unobserved heterogeneity that has not been obtained from previous models. Unlike the classic fuzzy clustering methods that use euclid distances to determine the weight of the object, this method uses the total square of the massed residual distance generated by the MARSBC model. Theoretical studies were conducted to obtain predictions for the MABFCMRS model parameters. Furthermore, this method was applied to stunting and wasting cases in southeastern Sulawesi province. The results of the research show that in the case of stunting modeling and wasting in southeast Sulawesi province, the best clusters were obtained based on the criteria of partition coefficient (PC) and modification of PC (MPC). This research is able to show that the clustering process using the MABFCMRS model has been able to improve generalized cross-validation (GCV) values and determination coefficients.•This paper presents a new, effective method for clustering data based on unobserved heterogeneity.•This is applicable to sizable samples with 3 to 20 predictors.

Catalytic Activity of 2-Imino-1,10-phenthrolyl Fe/Co Complexes via Linear Machine Learning.

In anticipation of the correlations between catalyst structures and their properties, the catalytic activities of 2-imino-1,10-phenanthrolyl iron and cobalt metal complexes are quantitatively investigated via linear machine learning (ML) algorithms. Comparatively, the Ridge Regression (RR) model has captured more robust predictive performance compared with other linear algorithms, with a correlation coefficient value of R2= 0.952 and a cross-validation value of Q2= 0.871. It shows that different algorithms select distinct types of descriptors, depending on the importance of descriptors. Through the interpretation of the RR model, the catalytic activity is potentially related to the steric effect of substituents and negative charged groups. This study refines descriptor selection for accurate modeling, providing insights into the variation principle of catalytic activity.

Prediction models for postoperative recurrence of non-lactating mastitis based on machine learning

ObjectivesThis study aims to build a machine learning (ML) model to predict the recurrence probability for postoperative non-lactating mastitis (NLM) by Random Forest (RF) and XGBoost algorithms. It can provide the ability to identify the risk of NLM recurrence and guidance in clinical treatment plan.MethodsThis study was conducted on inpatients who were admitted to the Mammary Department of Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine between July 2019 to December 2021. Inpatient data follow-up has been completed until December 2022. Ten features were selected in this study to build the ML model: age, body mass index (BMI), number of abortions, presence of inverted nipples, extent of breast mass, white blood cell count (WBC), neutrophil to lymphocyte ratio (NLR), albumin-globulin ratio (AGR) and triglyceride (TG) and presence of intraoperative discharge. We used two ML approaches (RF and XGBoost) to build models and predict the NLM recurrence risk of female patients. Totally 258 patients were randomly divided into a training set and a test set according to a 75%-25% proportion. The model performance was evaluated based on Accuracy, Precision, Recall, F1-score and AUC. The Shapley Additive Explanations (SHAP) method was used to interpret the model.ResultsThere were 48 (18.6%) NLM patients who experienced recurrence during the follow-up period. Ten features were selected in this study to build the ML model. For the RF model, BMI is the most important influence factor and for the XGBoost model is intraoperative discharge. The results of tenfold cross-validation suggest that both the RF model and the XGBoost model have good predictive performance, but the XGBoost model has a better performance than the RF model in our study. The trends of SHAP values of all features in our models are consistent with the trends of these features’ clinical presentation. The inclusion of these ten features in the model is necessary to build practical prediction models for recurrence.ConclusionsThe results of tenfold cross-validation and SHAP values suggest that the models have predictive ability. The trend of SHAP value provides auxiliary validation in our models and makes it have more clinical significance.

Comparative near Infrared (NIR) spectroscopy calibrations performance of dried and undried forage on dry and wet matter bases

The application of Near Infrared (NIR) spectroscopy for analyzing wet feed directly on farms is increasingly recognized for its role in supporting harvest-time decisions and refining the precision of animal feeding practices. This study aims to evaluate the accuracy of NIR spectroscopy calibrations for both undried, unprocessed samples and dried, ground samples. Additionally, it investigates the influence of the bases of reference data (wet vs. dry basis) on the predictive capabilities of the NIR analysis. The study utilized 492 Corn Whole Plant (CWP) and 405 High Moisture Corn (HMC) samples, sourced from various farms across Italy. Spectral data were acquired from both undried, unground and dried, ground samples using laboratory bench NIR instruments, covering a spectral range of 1100 to 2498 nm. The reference chemical composition of these samples was analyzed and presented in two formats: on a wet matter basis and on a dry matter basis.The study revealed that calibrations based on undried samples generally exhibited lower predictive accuracy for most traits, with the exception of Dry Matter (DM). Notably, the decline in predictive performance was more pronounced in highly moist products like CWP, where the average error increased by 60–70%. Conversely, this reduction in accuracy was relatively contained (10–15%) in drier samples such as HMC. The Standard Error of Cross-Validation (SECV) values for DMres, Ash, CP, and EE were notably low, at 0.39, 0.30, 0.29, 0.21% for CWP and 0.49, 0.14, 0.25, 0.14% for HMC, respectively. These results align with previous studies, indicating the reliability of NIR spectroscopy in diverse moisture contexts.The study attributes this variance to the interference caused by water in 'as is' samples, where the spectral features predominantly reflect water content, thereby obscuring the spectral signatures of other nutrients. In terms of calibration development strategies, the study concludes that there is no significant difference in predictive performance between undried calibrations based on either 'dry matter' or 'as is' basis. This finding emphasizes the potential of NIR spectroscopy in diverse moisture contexts, although with varying degrees of accuracy contingent upon the moisture content of the analyzed samples. Overall, this research provides valuable insights into the calibration strategies of NIR spectroscopy and its practical applications in agricultural settings, particularly for on-farm forage analysis.

Machine learning-enhanced drug testing for simultaneous morphine and methadone detection in urinary biofluids

The simultaneous identification of drugs has considerable difficulties due to the intricate interplay of analytes and the interference present in biological matrices. In this study, we introduce an innovative electrochemical sensor that overcomes these hurdles, enabling the precise and simultaneous determination of morphine (MOR), methadone (MET), and uric acid (UA) in urine samples. The sensor harnesses the strategically adapted carbon nanotubes (CNT) modified with graphitic carbon nitride (g-C3N4) nanosheets to ensure exceptional precision and sensitivity for the targeted analytes. Through systematic optimization of pivotal parameters, we attained accurate and quantitative measurements of the analytes within intricate matrices employing the fast Fourier transform (FFT) voltammetry technique. The sensor’s performance was validated using 17 training and 12 test solutions, employing the widely acclaimed machine learning method, partial least squares (PLS), for predictive modeling. The root mean square error of cross-validation (RMSECV) values for morphine, methadone, and uric acid were significantly low, measuring 0.1827 µM, 0.1951 µM, and 0.1584 µM, respectively, with corresponding root mean square error of prediction (RMSEP) values of 0.1925 µM, 0.2035 µM, and 0.1659 µM. These results showcased the robust resiliency and reliability of our predictive model. Our sensor’s efficacy in real urine samples was demonstrated by the narrow range of relative standard deviation (RSD) values, ranging from 3.71 to 5.26%, and recovery percentages from 96 to 106%. This performance underscores the potential of the sensor for practical and clinical applications, offering precise measurements even in complex and variable biological matrices. The successful integration of g-C3N4-CNT nanocomposites and the robust PLS method has driven the evolution of sophisticated electrochemical sensors, initiating a transformative era in drug analysis.

Revisiting methotrexate and phototrexate Zinc15 library-based derivatives using deep learning in-silico drug design approach.

Introduction: Cancer is the second most prevalent cause of mortality in the world, despite the availability of several medications for cancer treatment. Therefore, the cancer research community emphasized on computational techniques to speed up the discovery of novel anticancer drugs. Methods: In the current study, QSAR-based virtual screening was performed on the Zinc15 compound library (271 derivatives of methotrexate (MTX) and phototrexate (PTX)) to predict their inhibitory activity against dihydrofolate reductase (DHFR), a potential anticancer drug target. The deep learning-based ADMET parameters were employed to generate a 2D QSAR model using the multiple linear regression (MPL) methods with Leave-one-out cross-validated (LOO-CV) Q2 and correlation coefficient R2 values as high as 0.77 and 0.81, respectively. Results: From the QSAR model and virtual screening analysis, the top hits (09, 27, 41, 68, 74, 85, 99, 180) exhibited pIC50 ranging from 5.85 to 7.20 with a minimum binding score of -11.6 to -11.0 kcal/mol and were subjected to further investigation. The ADMET attributes using the message-passing neural network (MPNN) model demonstrated the potential of selected hits as an oral medication based on lipophilic profile Log P (0.19-2.69) and bioavailability (76.30% to 78.46%). The clinical toxicity score was 31.24% to 35.30%, with the least toxicity score (8.30%) observed with compound 180. The DFT calculations were carried out to determine the stability, physicochemical parameters and chemical reactivity of selected compounds. The docking results were further validated by 100ns molecular dynamic simulation analysis. Conclusion: The promising lead compounds found endorsed compared to standard reference drugs MTX and PTX that are best for anticancer activity and can lead to novel therapies after experimental validations. Furthermore, it is suggested to unveil the inhibitory potential of identified hits via in-vitro and in-vivo approaches.

Traceability of Microplastic Fragments from Waste Plastic Express Packages Using Near-Infrared Spectroscopy Combined with Chemometrics.

The pollution from waste plastic express packages (WPEPs), especially microplastic (MP) fragments, caused by the blowout development of the express delivery industry has attracted widespread attention. On account of the variety of additives, strong complexity, and high diversity of plastic express packages (PEPs), the multi-class classification of WPEPs is a typical large-class-number classification (LCNC). The traceability and identification of microplastic fragments from WPEPs is very challenging. An effective chemometric method for large-class-number classification would be very beneficial for the comprehensive treatment of WPEP pollution through the recycling and reuse of waste plastic express packages, including microplastic fragments and plastic debris. Rather than using the traditional one-against-one (OAO) and one-against-all (OAA) dichotomies, an exhaustive and parallel half-against-half (EPHAH) decomposition, which overcomes the defects of the OAO's classifier learning limitations and the OAA's data proportion imbalance, is proposed for feature selection. EPHAH analysis, combined with partial least squares discriminant analysis (PLS-DA) for large-class-number classification, was performed on 750 microplastic fragments of polyethylene WPEPs from 10 major courier companies using near-infrared (NIR) spectroscopy. After the removal of abnormal samples through robust principal component analysis (RPCA), the root mean square error of cross-validation (RMSECV) value for the model was reduced to 0.01, which was 21.5% lower than that including the abnormal samples. The best models of PLS-DA were obtained using SNV combined with SG-17 smoothing and 2D (SNV+SG-17+2D); the latent variables (LVs), the error rates of Monte Carlo cross-validation (ERMCCVs), and the final classification accuracies were 6.35, 0.155, and 88.67% for OAO-PLSDA; 5.37, 0.103, and 87.33% for OAA-PLSDA; and 3.12, 0.054, and 96.00% for EPHAH-PLSDA. The results showed that the EPHAH strategy can completely learn the complex LCNC decision boundaries for 10 classes, effectively break the tie problem, and greatly improve the voting resolution, thereby demonstrating significant superiority to both the OAO and OAA strategies in terms of classification accuracy. Meanwhile, PLS-DA further maximized the covariance and data interpretation abilities between the potential variables and categories of microplastic debris, thereby establishing an ideal performance identification model with a recognition rate of 96.00%.