Machine learning-based protein signatures for differentiating hypertensive disorders of pregnancy.

Hypertensive disorders of pregnancy (HDP) result in major maternal and fetal complications. Our study aimed to find a panel of protein markers to identify HDP by applying machine-learning models. The study was conducted on a total of 133 samples, divided into four groups, healthy pregnancy (HP, n = 42), gestational hypertension (GH, n = 67), preeclampsia (PE, n = 9), and ante-partum eclampsia (APE, n = 15). Thirty circulatory protein markers were measured using Luminex multiplex immunoassay and ELISA. Significant markers were screened for potential predictive markers by both statistical and machine-learning approaches. Statistical analysis found seven markers such as sFlt-1, PlGF, endothelin-1(ET-1), basic-FGF, IL-4, eotaxin and RANTES to be altered significantly in disease groups compared to healthy pregnant. Support vector machine (SVM) learning model classified GH and HP with 11 markers (eotaxin, GM-CSF, IL-4, IL-6, IL-13, MCP-1, MIP-1α, MIP-1ß, RANTES, ET-1, sFlt-1) and HDP with 13 markers (eotaxin, G-CSF, GM-CSF, IFN-gamma, IL-4, IL-5, IL-6, IL-13, MCP-1, MIP-1ß, RANTES, ET-1, sFlt-1). While logistic regression (LR) model classified PE with 13 markers (basic FGF, IL-1ß, IL-1ra, IL-7, IL-9, MIP-1ß, RANTES, TNF-alpha, nitric oxide, superoxide dismutase, ET-1, PlGF, sFlt-1) and APE by 12 markers (eotaxin, basic-FGF, G-CSF, GM-CSF, IL-1ß, IL-5, IL-8, IL-13, IL-17, PDGF-BB, RANTES, PlGF). These markers may be used to diagnose the progression of healthy pregnant to a hypertensive state. Future longitudinal studies with large number of samples are needed to validate these findings.

Integrated metabolomics and machine learning approach to predict hypertensive disorders of pregnancy.

BACKGROUND: Hypertensive disorders of pregnancy account for 3% to 10% of maternal-fetal morbidity and mortality worldwide. This condition has been considered one of the leading causes of maternal deaths in developing countries, such as India. OBJECTIVE: This study aimed to discover hypertensive disorders of pregnancy-specific candidate urine metabolites as markers for hypertensive disorders of pregnancy by applying integrated metabolomics and machine learning approaches. STUDY DESIGN: The targeted urinary metabolomics study was conducted in 70 healthy pregnant controls and 133 pregnant patients having hypertension as cases. Hypertensive disorders of pregnancy-specific metabolites for disease prediction were further extracted using univariate and multivariate statistical analyses. For machine learning analysis, 80% of the data were used for training (79 for hypertensive disorders of pregnancy and 42 for healthy pregnancy) and validation (27 for hypertensive disorders of pregnancy and 14 for healthy pregnancy), and 20% of the data were used for test sets (27 for hypertensive disorders of pregnancy and 14 for healthy pregnancy). RESULTS: The statistical analysis using an unpaired t test revealed 44 differential metabolites. Pathway analysis showed mainly that purine and thiamine metabolism were altered in the group with hypertensive disorders of pregnancy compared with the healthy pregnancy group. The area under the receiver operating characteristic curves of the 5 most predominant metabolites were 0.98 (adenosine), 0.92 (adenosine monophosphate), 0.89 (deoxyadenosine), 0.81 (thiamine), and 0.81 (thiamine monophosphate). The best prediction accuracies were obtained using 2 machine learning models (95% for the gradient boost model and 98% for the decision tree) among the 5 used models. The machine learning models showed higher predictive performance for 3 metabolites (ie, thiamine monophosphate, adenosine monophosphate, and thiamine) among 5 metabolites. The combined accuracies of adenosine from all models were 98.6 in the training set and 95.6 in the test set. Moreover, the predictive performance of adenosine was higher than other metabolites. The relative feature importance of adenosine was also observed in the decision tree and the gradient boost model. CONCLUSION: Among other metabolites, adenosine and thiamine metabolites were found to differentiate participants with hypertensive disorders of pregnancy from participants with healthy pregnancies; hence, these metabolites can serve as a promising noninvasive marker for the detection of hypertensive disorders of pregnancy.

Rate coefficients for the OH + HC(O)C(O)H (glyoxal) reaction between 210 and 390 K.

Rate coefficients, k1(T), over the temperature range of 210-390 K are reported for the gas-phase reaction OH + HC(O)C(O)H (glyoxal) --> products at pressures between 45 and 300 Torr (He, N2). Rate coefficients were determined under pseudo-first-order conditions in OH using pulsed laser photolysis production of OH radicals coupled with OH detection by laser-induced fluorescence. The rate coefficients obtained were independent of pressure and bath gas. The room-temperature rate coefficient, k1(296 K), was determined to be (9.15 +/- 0.8) x 10-12 cm3 molecule-1 s-1. k1(T) shows a negative temperature dependence with a slight deviation from Arrhenius behavior that is reproduced over the temperature range included in this study by k1(T) = [(6.6 +/- 0.6) x 10-18]T2[exp([820 +/- 30]/T)] cm3 molecule-1 s-1. For atmospheric modeling purposes, a fit to an Arrhenius expression over the temperature range included in this study that is most relevant to the atmosphere, 210-296 K, yields k1(T) = (2.8 +/- 0.7) x 10-12 exp[(340 +/- 50)/T] cm3 molecule-1 s-1 and reproduces the rate coefficient data very well. The quoted uncertainties in k1(T) are at the 95% confidence level (2sigma) and include estimated systematic errors. Comparison of the present results with the single previous determination of k1(296 K) and a discussion of the reaction mechanism and non-Arrhenius temperature dependence are presented.

Kinetics of the OH Reaction with Methyl Chloroform and Its Atmospheric Implications.

The rate coefficients for the reaction of hydroxyl (OH) radicals with methyl chloroform (CH(3)CCI(3)) were measured between 243 and 379 kelvin with the pulsed photolysis-laserinduced fluorescence method. The measured rate coefficients at 298 and 277 kelvin were approximately 20 and approximately 15%, respectively, lower than earlier values. These results will increase the tropospheric OH concentrations derived from the CH(3)CCI(3) budget analysis by approximately 15%. The predicted atmospheric lifetimes of species whose main loss process is the reaction with OH in the troposphere will be lowered by 15% with consequent changes in their budgets, global warming potentials, and ozone depletion potentials.