Application of machine learning algorithms to screen potential biomarkers under cadmium exposure based on human urine metabolic profiles

Exposure to environmental cadmium increases the health risk of residents. Early urine metabolic detection using high-resolution mass spectrometry and machine learning algorithms would be advantageous to predict the adverse health effects. Here, we conducted machine learning approaches to screen potential biomarkers under cadmium exposure in 403 urine samples. In positive and negative ionization mode, 4207 and 3558 features were extracted, respectively. We compared seven machine learning algorithms and found that the extreme gradient boosting (XGBoost) and random forest (RF) classifiers showed better accuracy and predictive performance than others. Following 5-fold cross-validation, the value of area under curve (AUC) was both 0.93 for positive and negative ionization modes in XGBoost classifier. In the RF classifier, AUC were 0.80 and 0.84 for positive and negative ionization modes, respectively. We then identified a biomarker panel based on XGBoost and RF classifiers. The incorporation of machine learning models into urine analysis using high-resolution mass spectrometry could allow a convenient assessment of cadmium exposure.     

Brain tumor diagnostic model and dietary effect based on extracellular vesicle microbiome data in serum

The human microbiome has been recently associated with human health and disease. Brain tumors (BTs) are a particularly difficult condition to directly link to the microbiome, as microorganisms cannot generally cross the blood–brain barrier (BBB). However, some nanosized extracellular vesicles (EVs) released from microorganisms can cross the BBB and enter the brain. Therefore, we conducted metagenomic analysis of microbial EVs in both serum (152 BT patients and 198 healthy controls (HC)) and brain tissue (5 BT patients and 5 HC) samples based on the V3–V4 regions of 16S rDNA. We then developed diagnostic models through logistic regression and machine learning algorithms using serum EV metagenomic data to assess the ability of various dietary supplements to reduce BT risk in vivo. Models incorporating the stepwise method and the linear discriminant analysis effect size (LEfSe) method yielded 12 and 29 significant genera as potential biomarkers, respectively. Models using the selected biomarkers yielded areas under the curves (AUCs) >0.93, and the model using machine learning resulted in an AUC of 0.99. In addition, Dialister and [Eubacterium] rectale were significantly lower in both blood and tissue samples of BT patients than in those of HCs. In vivo tests showed that BT risk was decreased through the addition of sorghum, brown rice oil, and garlic but conversely increased by the addition of bellflower and pear. In conclusion, serum EV metagenomics shows promise as a rich data source for highly accurate detection of BT risk, and several foods have potential for mitigating BT risk.Subject terms: Diagnostic markers, Machine learning     

The Influence of Smoking Status on Exhaled Breath Profiles in Asthma and COPD Patients

Breath analysis using eNose technology can be used to discriminate between asthma and COPD patients, but it remains unclear whether results are influenced by smoking status. We aim to study whether eNose can discriminate between ever- vs. never-smokers and smoking <24 vs. >24 h before the exhaled breath, and if smoking can be considered a confounder that influences eNose results. We performed a cross-sectional analysis in adults with asthma or chronic obstructive pulmonary disease (COPD), and healthy controls. Ever-smokers were defined as patients with current or past smoking habits. eNose measurements were performed by using the SpiroNose. The principal component (PC) described the eNose signals, and linear discriminant analysis determined if PCs classified ever-smokers vs. never-smokers and smoking <24 vs. >24 h. The area under the receiver–operator characteristic curve (AUC) assessed the accuracy of the models. We selected 593 ever-smokers (167 smoked <24 h before measurement) and 303 never-smokers and measured the exhaled breath profiles of discriminated ever- and never-smokers (AUC: 0.74; 95% CI: 0.66–0.81), and no cigarette consumption <24h (AUC 0.54, 95% CI: 0.43–0.65). In healthy controls, the eNose did not discriminate between ever or never-smokers (AUC 0.54; 95% CI: 0.49–0.60) and recent cigarette consumption (AUC 0.60; 95% CI: 0.50–0.69). The eNose could distinguish between ever and never-smokers in asthma and COPD patients, but not recent smokers. Recent smoking is not a confounding factor of eNose breath profiles.     

Comparison of Targeted and Untargeted Approaches in Breath Analysis for the Discrimination of Lung Cancer from Benign Pulmonary Diseases and Healthy Persons

The aim of the present study was to compare the efficiency of targeted and untargeted breath analysis in the discrimination of lung cancer (Ca+) patients from healthy people (HC) and patients with benign pulmonary diseases (Ca−). Exhaled breath samples from 49 Ca+ patients, 36 Ca− patients and 52 healthy controls (HC) were analyzed by an SPME–GC–MS method. Untargeted treatment of the acquired data was performed with the use of the web-based platform XCMS Online combined with manual reprocessing of raw chromatographic data. Machine learning methods were applied to estimate the efficiency of breath analysis in the classification of the participants. Results: Untargeted analysis revealed 29 informative VOCs, from which 17 were identified by mass spectra and retention time/retention index evaluation. The untargeted analysis yielded slightly better results in discriminating Ca+ patients from HC (accuracy: 91.0%, AUC: 0.96 and accuracy 89.1%, AUC: 0.97 for untargeted and targeted analysis, respectively) but significantly improved the efficiency of discrimination between Ca+ and Ca− patients, increasing the accuracy of the classification from 52.9 to 75.3% and the AUC from 0.55 to 0.82. Conclusions: The untargeted breath analysis through the inclusion and utilization of newly identified compounds that were not considered in targeted analysis allowed the discrimination of the Ca+ from Ca− patients, which was not achieved by the targeted approach.     

Exploratory Study Using Urinary Volatile Organic Compounds for the Detection of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) biomarkers are lacking in clinical practice. We therefore explored the pattern and composition of urinary volatile organic compounds (VOCs) in HCC patients. This was done in order to assess the feasibility of a potential non-invasive test for HCC, and to enhance our understanding of the disease. This pilot study recruited 58 participants, of whom 20 were HCC cases and 38 were non-HCC cases. The non-HCC cases included healthy individuals and patients with various stages of non-alcoholic fatty liver disease (NAFLD), including those with and without fibrosis. Urine was analysed using gas chromatography–ion mobility spectrometry (GC–IMS) and gas chromatography–time-of-flight mass spectrometry (GC–TOF-MS). GC–IMS was able to separate HCC from fibrotic cases with an area under the curve (AUC) of 0.97 (0.91–1.00), and from non-fibrotic cases with an AUC of 0.62 (0.48–0.76). For GC-TOF-MS, a subset of samples was analysed in which seven chemicals were identified and tentatively linked with HCC. These include 4-methyl-2,4-bis(p-hydroxyphenyl)pent-1-ene (2TMS derivative), 2-butanone, 2-hexanone, benzene, 1-ethyl-2-methyl-, 3-butene-1,2-diol, 1-(2-furanyl)-, bicyclo(4.1.0)heptane, 3,7,7-trimethyl-, [1S-(1a,3β,6a)]-, and sulpiride. Urinary VOC analysis using both GC–IMS and GC-TOF-MS proved to be a feasible method of identifying HCC cases, and was also able to enhance our understanding of HCC pathogenesis.     

Development and Validation of a Chiral Liquid Chromatographic Assay for Enantiomeric Separation and Quantification of Verapamil in Rat Plasma: Stereoselective Pharmacokinetic Application

A novel, fast and sensitive enantioselective HPLC assay with a new core–shell isopropyl carbamate cyclofructan 6 (superficially porous particle, SPP) chiral column (LarihcShell-P, LSP) was developed and validated for the enantiomeric separation and quantification of verapamil (VER) in rat plasma. The polar organic mobile phase composed of acetonitrile/methanol/trifluoroacetic acid/triethylamine (98:2:0.05: 0.025, v/v/v/v) and a flow rate of 0.5 mL/min was applied. Fluorescence detection set at excitation/emission wavelengths 280/313 nm was used and the whole analysis process was within 3.5 min, which is 10-fold lower than the previous reported HPLC methods in the literature. Propranolol was selected as the internal standard. The S-(−)- and R-(+)-VER enantiomers with the IS were extracted from rat plasma by utilizing Waters Oasis HLB C18 solid phase extraction cartridges without interference from endogenous compounds. The developed assay was validated following the US-FDA guidelines over the concentration range of 1–450 ng/mL (r² ≥ 0.997) for each enantiomer (plasma) and the lower limit of quantification was 1 ng/mL for both isomers. The intra- and inter-day precisions were not more than 11.6% and the recoveries of S-(−)- and R-(+)-VER at all quality control levels ranged from 92.3% to 98.2%. The developed approach was successfully applied to the stereoselective pharmacokinetic study of VER enantiomers after oral administration of 10 mg/kg racemic VER to Wistar rats. It was found that S-(−)-VER established higher C_max and area under the concentration-time curve (AUC) values than the R-(+)-enantiomer. The newly developed approach is the first chiral HPLC for the enantiomeric separation and quantification of verapamil utilizing a core–shell isopropyl carbamate cyclofructan 6 chiral column in rat plasma within 3.5 min after solid phase extraction (SPE).     

Synthesis of sialyl Lewis X-polysaccharide conjugates

Sialyl Lewis X (SLeX) is well known as a ligand of the cell adhesion molecule E-selectin which is specifically expressed at inflammatory lesion sites. We have synthesized several SLeX-polysaccharide conjugates and examined their potential for drug delivery to inflammatory lesions. The AUC (area under the blood concentration-time curve) 0-24 h of SLeX-CMCht (1), SLeX-CMPul (2) and SLeX-DSH (3) at the inflammatory lesion was about 60-, 300-, and 30-fold higher than that of the monovalent SLeX (7), respectively. Moreover, 1 showed 2-fold higher accumulation in the inflammatory lesion than SLN-CMCht (4), and 2 showed 2.5-fold higher accumulation than SLN-CMPul (5).     

Feature selection for OPLS discriminant analysis of cancer tissue lipidomics data

The mass spectrometry‐based molecular profiling can be used for better differentiation between normal and cancer tissues and for the detection of neoplastic transformation, which is of great importance for diagnostics of a pathology, prognosis of its evolution trend, and development of a treatment strategy. The aim of the present study is the evaluation of tissue classification approaches based on various data sets derived from the molecular profile of the organic solvent extracts of a tissue. A set of possibilities are considered for the orthogonal projections to latent structures discriminant analysis: all mass spectrometric peaks over 300 counts threshold, subset of peaks selected by ranking with support vector machine algorithm, peaks selected by random forest algorithm, peaks with the statistically significant difference of the intensity determined by the Mann‐Whitney U test, peaks identified as lipids, and both identified and significantly different peaks. The best predictive potential is obtained for OPLS‐DA model built on nonpolar glycerolipids (Q² = 0.64, area under curve [AUC] = 0.95); the second one is OPLS‐DA model with lipid peaks selected by random forest algorithm (Q² = 0.58, AUC = 0.87). Moreover, models based on particular molecular classes are more preferable from biological point of view, resulting in new explanatory mechanisms of pathophysiology and providing a pathway analysis. Another promising features for OPLS‐DA modeling are phosphatidylethanolamines (Q² = 0.48, AUC = 0.86).     

Irradiation preservation of Hangzhou White Chrysanthemum Dendranthema morifolium (Ramat. Tzvel)

A study on the irradiation preservation of Hangzhou White Chrysanthemum (HWC for short) was carried out to keep the quality of HWC and prolong its shelf life. The results showed that: 1). γ-irradiation with proper dosage was one of the key steps to prolong the shelf-life of HWC. After γ - treatment at the dose level of 3–5kGy, the laminated plastic film packed HWC could be stored in ambient temperature for over 300 days, remaining its original colour, aroma and taste. 2). Different dose rate had no effect on the treatment results. 3). The main quality indexes of HWC treated with 10.0 kGy γ - rays were not changed, moreover, it had the higher hygienic qualities.     

Polymerized Whey Protein Concentrate-Based Glutathione Delivery System: Physicochemical Characterization,Bioavailability and Sub-Chronic Toxicity Evaluation

Glutathione (GSH) is a powerful antioxidant, but its application is limited due to poor storage stability and low bioavailability. A novel nutrient encapsulation and delivery system, consisting of polymerized whey protein concentrate and GSH, was prepared and in vivo bioavailability, antioxidant capacity and toxicity were evaluated. Polymerized whey protein concentrate encapsulated GSH (PWPC-GSH) showed a diameter of roughly 1115 ± 7.07 nm (D₅₀) and zeta potential of 30.37 ± 0.75 mV. Differential scanning calorimetry (DSC) confirmed that GSH was successfully dispersed in PWPC particles. In vivo pharmacokinetics study suggested that PWPC-GSH displayed 2.5-times and 2.6-fold enhancement in maximum concentration (C_max) and area under the concentration–time curve (AUC) as compared to free GSH. Additionally, compared with plasma of mice gavage with free GSH, significantly increased antioxidant capacity of plasma in mice with PWPC-GSH was observed (p < 0.05). Sub-chronic toxicity evaluation indicated that no adverse toxicological reactions related to oral administration of PWPC-GSH were observed on male and female rats with a diet containing PWPC-GSH up to 4% (w/w). Data indicated that PWPC may be an effective carrier for GSH to improve bioavailability and antioxidant capacity.     

Fraxinellone Induces Hepatotoxicity in Zebrafish through Oxidative Stress and the Transporters Pathway

Fraxinellone (FRA), a major active component from Cortex Dictamni, produces hepatotoxicity via the metabolization of furan rings by CYP450. However, the mechanism underlying the hepatotoxicity of FRA remains unclear. Therefore, zebrafish larvae at 72 h post fertilization were used to evaluate the metabolic hepatotoxicity of FRA and to explore the underlying molecular mechanisms. The results showed that FRA (10–30 μM) induced liver injury and obvious alterations in the metabolomics of zebrafish larvae. FRA induces apoptosis by increasing the level of ROS and activating the JNK/P53 pathway. In addition, FRA can induce cholestasis by down-regulating bile acid transporters P-gp, Bsep, and Ntcp. The addition of the CYP3A inhibitor ketoconazole (1 μM) significantly reduced the hepatotoxicity of FRA (30 μM), which indicated that FRA induced hepatotoxicity through CYP3A metabolism. Targeted metabolomics analysis indicates the changes in amino acid levels can be combined with molecular biology to clarify the mechanism of hepatotoxicity induced by FRA, and amino acid metabolism monitoring may provide a new method for the prevention and treatment of DILI from FRA.     

A machine learning approach to computer-aided molecular design

Summary Preliminary results of a machine learning application concerning computer-aided molecular design applied to drug discovery are presented. The artificial intelligence techniques of machine learning use a sample of active and inactive compounds, which is viewed as a set of positive and negative examples, to allow the induction of a molecular model characterizing the interaction between the compounds and a target molecule. The algorithm is based on a twofold phase. In the first one — the specialization step — the program identifies a number of active/inactive pairs of compounds which appear to be the most useful in order to make the learning process as effective as possible and generates a dictionary of molecular fragments, deemed to be responsible for the activity of the compounds. In the second phase — the generalization step — the fragments thus generated are combined and generalized in order to select the most plausible hypothesis with respect to the sample of compounds. A knowledge base concerning physical and chemical properties is utilized during the inductive process.     

The Inhibitory Effect of Sulforaphane on Bladder Cancer Cell Depends on GSH Depletion-Induced by Nrf2 Translocation

Sulforaphane (SFN), an isothiocyanate (ITCs) derived from glucosinolate that is found in cruciferous vegetables, has been reported to exert a promising anticancer effect in a substantial amount of scientific research. However, epidemical studies showed inconsistencies between cruciferous vegetable intake and bladder cancer risk. In this study, human bladder cancer T24 cells were used as in vitro model for revealing the inhibitory effect and its potential mechanism of SFN on cell growth. Here, a low dose of SFN (2.5 µM) was shown to promote cell proliferation (5.18–11.84%) and migration in T24 cells, whilst high doses of SFN (>10 µM) inhibited cell growth significantly. The induction effect of SFN on nuclear factor (erythroid-derived 2)-like 2 (Nrf2) expression at both low (2.5 µM) and high dose (10 µM) was characterized by a bell-shaped curve. Nrf2 and glutathione (GSH) might be the underlying mechanism in the effect of SFN on T24 cell growth since Nrf2 siRNA and GSH-depleting agent L-Buthionine-sulfoximine abolished the effect of SFN on cell proliferation. In summary, the inhibitory effect of SFN on bladder cancer cell growth and migration is highly dependent on Nrf2-mediated GSH depletion and following production. These findings suggested that a higher dose of SFN is required for the prevention and treatment of bladder cancer.     

Quantitative Analysis of Daporinad (FK866) and Its In Vitro and In Vivo Metabolite Identification Using Liquid Chromatography-Quadrupole-Time-of-Flight Mass Spectrometry

Daporinad (FK866) is one of the highly specific inhibitors of nicotinamide phosphoribosyl transferase (NAMPT) and known to have its unique mechanism of action that induces the tumor cell apoptosis. In this study, a simple and sensitive liquid chromatography–quadrupole-time-of-flight–mass spectrometric (LC-qTOF-MS) assay has been developed for the evaluation of drug metabolism and pharmacokinetics (DMPK) properties of Daporinad in mice. A simple protein precipitation method using acetonitrile (ACN) was used for the sample preparation and the pre-treated samples were separated by a C18 column. The calibration curve was evaluated in the range of 1.02~2220 ng/mL and the quadratic regression (weighted 1/concentration²) was used for the best fit of the curve with a correlation coefficient ≥ 0.99. The qualification run met the acceptance criteria of ±25% accuracy and precision values for QC samples. The dilution integrity was verified for 5, 10 and 30-fold dilution and the accuracy and precision of the dilution QC samples were also satisfactory within ±25% of the nominal values. The stability results indicated that Daporinad was stable for the following conditions: short-term (4 h), long-term (2 weeks), freeze/thaw (three cycles). This qualified method was successfully applied to intravenous (IV) pharmacokinetic (PK) studies of Daporinad in mice at doses of 5, 10 and 30 mg/kg. As a result, it showed a linear PK tendency in the dose range from 5 to 10 mg/kg, but a non-linear PK tendency in the dose of 30 mg/kg. In addition, in vitro and in vivo metabolite identification (Met ID) studies were conducted to understand the PK properties of Daporinad and the results showed that a total of 25 metabolites were identified as ten different types of metabolism in our experimental conditions. In conclusion, the LC-qTOF-MS assay was successfully developed for the quantification of Daporinad in mouse plasma as well as for its in vitro and in vivo metabolite identification.     

Biofilm-i: A Platform for Predicting Biofilm Inhibitors Using Quantitative Structure—Relationship (QSAR) Based Regression Models to Curb Antibiotic Resistance

Antibiotic drug resistance has emerged as a major public health threat globally. One of the leading causes of drug resistance is the colonization of microorganisms in biofilm mode. Hence, there is an urgent need to design novel and highly effective biofilm inhibitors that can work either synergistically with antibiotics or individually. Therefore, we have developed a recursive regression-based platform “Biofilm-i” employing a quantitative structure–activity relationship approach for making generalized predictions, along with group and species-specific predictions of biofilm inhibition efficiency of chemical(s). The platform encompasses eight predictors, three analysis tools, and data visualization modules. The experimentally validated biofilm inhibitors for model development were retrieved from the “aBiofilm” resource and processed using a 10-fold cross-validation approach using the support vector machine and andom forest machine learning techniques. The data was further sub-divided into training/testing and independent validation sets. From training/testing data sets the Pearson’s correlation coefficient of overall chemicals, Gram-positive bacteria, Gram-negative bacteria, fungus, Pseudomonas aeruginosa, Staphylococcus aureus, Candida albicans, and Escherichia coli was 0.60, 0.77, 0.62, 0.77, 0.73, 0.83, 0.70, and 0.71 respectively via Support Vector Machine. Further, all the QSAR models performed equally well on independent validation data sets. Additionally, we also checked the performance of the random forest machine learning technique for the above datasets. The integrated analysis tools can convert the chemical structure into different formats, search for a similar chemical in the aBiofilm database and design the analogs. Moreover, the data visualization modules check the distribution of experimentally validated biofilm inhibitors according to their common scaffolds. The Biofilm-i platform would be of immense help to researchers engaged in designing highly efficacious biofilm inhibitors for tackling the menace of antibiotic drug resistance.     

Comparative Pharmacokinetic Study of Forchlorfenuron in Adult and Juvenile Rats

Forchlorfenuron (CPPU) is a plant growth regulator extensively used in agriculture. However, studies on CPPU pharmacokinetics are lacking. We established and validated a rapid, sensitive, and accurate liquid chromatography–mass spectrometry method for CPPU detection in rat plasma. CPPU pharmacokinetics was evaluated in adult and juvenile rats orally treated with 10, 30, and 90 mg/kg of the compound. The area under the plasma drug concentration–time curve from 0 to 24 h (AUC), at the final time point sampled (AUC_0–t), and the maximum drug concentration of CPPU increased in a dose-dependent manner. The pharmacokinetic parameters AUC_0–t and absolute bioavailability were higher in the juvenile rats than in adult rats. The mean residence time and AUC_0–t of juvenile rats in the gavage groups, except for the 10 mg/kg dose, were significantly higher in comparison to those observed for adult rats (p < 0.001). The plasma clearance of CPPU in juvenile rats was slightly lower than that in the adult rats. Taken together, juvenile rats were more sensitive to CPPU than adult rats, which indicates potential safety risks of CPPU in minors.     

Determination of Toxic Pyrrolizidine Alkaloids in Traditional Chinese Herbal Medicines by UPLC-MS/MS and Accompanying Risk Assessment for Human Health

Pyrrolizidine alkaloids (PAs) are a class of natural toxins with hepatotoxicity, genotoxicity and carcinogenicity. They are endogenous and adulterated toxic components widely found in food and herbal products. In this study, a sensitive and efficient ultra-high performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) method was used to detect the PAs in 386 kinds of Chinese herbal medicines recorded in the Chinese Pharmacopoeia (2020). The estimated daily intake (EDI) of 0.007 μg/kg body weight (bw)/day was adopted as the safety baseline. The margin of exposure (MOE) approach was applied to evaluate the chronic exposure risk for the genotoxic and carcinogenic potential of PAs. Results showed that PAs was detected in 271 out of 386 samples with a content of 0.1–25,567.4 μg/kg, and there were 20 samples with EDI values above the baseline, 0.007 μg/kg bw/day. Beyond that, the MOE values for 10 out of 271 positive samples were below 10,000. Considering the actual situation, Haber’s rule was used to assume two weeks exposure every year during lifetime, and still the MOE values for four out of 271 positive samples were under 10,000, indicating these products may have potential health risk. The developed method was successfully applied to detect the PAs-containing Chinese herbal medicines. This study provides convincing data that can support risk management actions in China and a meaningful reference for the rational and safe use of Chinese herbal medicines.