Deep convolution neural network for screening carotid calcification in dental panoramic radiographs.

Ischemic stroke, a leading global cause of death and disability, is commonly caused by carotid arteries atherosclerosis. Carotid artery calcification (CAC) is a well-known marker of atherosclerosis. Such calcifications are classically detected by ultrasound screening. In recent years it was shown that these calcifications can also be inferred from routine panoramic dental radiographs. In this work, we focused on panoramic dental radiographs taken from 500 patients, manually labelling each of the patients' sides (each radiograph was treated as two sides), which were used to develop an artificial intelligence (AI)-based algorithm to automatically detect carotid calcifications. The algorithm uses deep learning convolutional neural networks (CNN), with transfer learning (TL) approach that achieved true labels for each corner, and reached a sensitivity (recall) of 0.82 and a specificity of 0.97 for individual arteries, and a recall of 0.87 and specificity of 0.97 for individual patients. Applying and integrating the algorithm in healthcare units and dental clinics has the potential of reducing stroke events and their mortality and morbidity consequences.

Reply to van der Pluijm et al. Comment on "Weitzman et al. Resistance to Antimalarial Monotherapy Is Cyclic. J. Clin. Med. 2022, 11, 781".

Thank you for the opportunity to respond to comments gracefully raised by van der Pluijm et al. [...].

Resistance to Antimalarial Monotherapy Is Cyclic.

Malaria is a prevalent parasitic disease that is estimated to kill between one and two million people-mostly children-every year. Here, we query PubMed for malaria drug resistance and plot the yearly citations of 14 common antimalarials. Remarkably, most antimalarial drugs display cyclic resistance patterns, rising and falling over four decades. The antimalarial drugs that exhibit cyclic resistance are quinine, chloroquine, mefloquine, amodiaquine, artesunate, artemether, sulfadoxine, doxycycline, halofantrine, piperaquine, pyrimethamine, atovaquone, artemisinin, and dihydroartemisinin. Exceptionally, the resistance of the two latter drugs can also correlate with a linear rise. Our predicted antimalarial drug resistance is consistent with clinical data reported by the Worldwide Antimalarial Resistance Network (WWARN) and validates our methodology. Notably, the cyclical resistance suggests that most antimalarial drugs are sustainable in the end. Furthermore, cyclic resistance is clinically relevant and discourages routine monotherapy, in particular, while resistance is on the rise. Finally, cyclic resistance encourages the combination of antimalarial drugs at distinct phases of resistance.

Machine learning vs. classic statistics for the prediction of IVF outcomes.

PURPOSE: To assess whether machine learning methods provide advantage over classic statistical modeling for the prediction of IVF outcomes. METHODS: The study population consisted of 136 women undergoing a fresh IVF cycle from January 2014 to August 2016 at a tertiary, university-affiliated medical center. We tested the ability of two machine learning algorithms, support vector machine (SVM) and artificial neural network (NN), vs. classic statistics (logistic regression) to predict IVF outcomes (number of oocytes retrieved, mature oocytes, top-quality embryos, positive beta-hCG, clinical pregnancies, and live births) based on age and BMI, with or without clinical data. RESULTS: Machine learning algorithms (SVM and NN) based on age, BMI, and clinical features yielded better performances in predicting number of oocytes retrieved, mature oocytes, fertilized oocytes, top-quality embryos, positive beta-hCG, clinical pregnancies, and live births, compared with logistic regression models. While accuracies were 0.69 to 0.9 and 0.45 to 0.77 for NN and SVM, respectively, they were 0.34 to 0.74 using logistic regression models. CONCLUSIONS: Our findings suggest that machine learning algorithms based on age, BMI, and clinical data have an advantage over logistic regression for the prediction of IVF outcomes and therefore can assist fertility specialists' counselling and their patients in adjusting the appropriate treatment strategy.

A hybrid model for evaluating exposure of the general population in Israel to air pollutants.

Exposure to air pollution is associated with a wide range of health effects, including increased respiratory symptoms, cancer, reproductive and birth defects, and premature death. Air quality measurements by standardized measuring equipment, although accurate, can only provide an estimate for part of the population, with decreasing accuracy further away from the monitoring sites. Estimating pollution levels over large geographical domains requires the use of air quality models which ideally incorporate air quality measurements. In order to estimate actual exposure of the population to air pollution (population-weighted concentrations of air pollutants), there is a need to combine data from air quality models with population density data. Here we present the results of exposure estimates for the entire population of Israel using a chemical transport model combined with measurements from the national monitoring network. We evaluated the individual exposure levels for the entire population to several air pollutants based on census tract units. Using this hybrid model, we found that the entire population of Israel is exposed to concentrations of PM10 and PM2.5 that exceed the target values but are below the environmental values according to the Israeli Clean Air Law. In addition, we found and that over 1.5 million residents are exposed to NOx at concentrations higher than the target values. This data may help decision makers develop targeted interventions to reduce the concentrations of specific pollutants, based on population-weighted exposure.

CDB-a database for protein heterodimeric complexes.

Crystallographic structures of protein complexes are essential to develop proteomic and structural biology methods, as prediction of protein-protein interaction (PPI) sites and protein-protein docking. Such structures can aid the development of protein complexation inhibitors. Complex DataBase (CDB), accessible at www.jct-bioinfo.com/cdb/search, is a database web application for heterodimeric protein crystallographic complexes along with the crystallographic structures of each individual unbound protein. Direct access to crystallographic structures of protein complexes, along with provided annotations, can serve as starting point for constructing new experimental protein complexes sets of any type, for protein binding studies, and the development and evaluation of PPIs prediction methods.

Phosphate-binding protein from Polaromonas JS666: purification, characterization, crystallization and sulfur SAD phasing.

Phosphate-binding proteins (PBPs) are key proteins that belong to the bacterial ABC-type phosphate transporters. PBPs are periplasmic (or membrane-anchored) proteins that capture phosphate anions from the environment and release them to the transmembrane transporter. Recent work has suggested that PBPs have evolved for high affinity as well as high selectivity. In particular, a short, unique hydrogen bond between the phosphate anion and an aspartate residue has been shown to be critical for selectivity, yet is not strictly conserved in PBPs. Here, the PBP from Polaromonas JS666 is focused on. Interestingly, this PBP is predicted to harbor different phosphate-binding residues to currently known PBPs. Here, it is shown that the PBP from Polaromonas JS666 is capable of binding phosphate, with a maximal binding activity at pH 8. Its structure is expected to reveal its binding-cleft configuration as well as its phosphate-binding mode. Here, the expression, purification, characterization, crystallization and X-ray diffraction data collection to 1.35 Šresolution of the PBP from Polaromonas JS666 are reported.

Hydrolysis of organophosphate compounds by mutant butyrylcholinesterase: a story of two histidines.

This study is aimed at understanding the hydrolysis mechanism of organophosphate (OP) compounds by G117H-BChE. It is a theoretical study that focuses on the role of the G117H mutation in the dephosphorylation step. Various proposed mechanisms are examined. We show that His117 acts as a general base by activating a water molecule, and thus assisting its nucleophilic attack on the phosphate. The calculated reaction energy profile agrees well with the experimental data. Moreover, analysis of the reaction via its two hypothetical elementary steps, proton transfer and hydroxide attack, supports the role of His117 as a general base. Further support to the proposed mechanism is gained by structural comparison of the active site to RNAse A, which has similar composition of substrate and functional groups. The similarity between these enzymes extends beyond the structure and also becomes evident when comparing functionality of various active sites residues as well as rate-pH dependence obtained in the two cases. Moreover, it is demonstrated that an extended form of Bevilacqua's model (Biochemistry 2003;42:2259-2265) may resolve the apparent contradictions between the proposed mechanism and various experimental observations regarding rate-pH dependence. Finally, that same model is shown to rationalize the hydrolase activity of G117D BChE, an observation which is considered puzzling. It is concluded that G117H-BChE hydrolyzes echothiophate and possibly other OP compounds via a general acid-base mechanism. On the basis of this mechanism, one can now proceed with rational design aimed at improving the enzyme by exploiting both the structural and mechanistic knowledge.

The structure of G117H mutant of butyrylcholinesterase: nerve agents scavenger.

Organophosphate ester (OP) compounds are known for their ubiquitous use as insecticides. At the same time, these chemicals are highly toxic and can be used as nerve agents. G117H mutant of human Butyrylcholinesterase (BChE) was found to be capable of hydrolyzing certain OPs and protect against their toxicity. However, for therapeutic use, the rate of hydrolysis is too low. Its catalytic power can be improved by rational design, but the structure of the G117H mutant is first required. In this work, we determined, computationally, the three dimensional structure of the G117H BChE mutant. The structure was then validated by simulating acetylation of acetylthiocholine (ATC). Several plausible conformers of G117H BChE were examined but only the (62,-75) conformer fully reproduced catalytic effect. The (62,-75) conformer is, therefore, suggested as the structure adopted by the G117H BChE mutant. This conformer is shown to explain the loss of esterase activity observed for the G122H Acetylcholinesterase mutant together with its recovery when additional mutations are placed turning the enzyme also into an OP hydrolase. Furthermore, similarity of the structure to the structure of RNase A, which is known to hydrolyze the O--P bond in RNA, grants it further credibility and suggests a mechanism for the OP hydrolysis.