Detecting the most critical clinical variables of COVID-19 breakthrough infection in vaccinated persons using machine learning.

Background: COVID-19 vaccines offer different levels of immune protection but do not provide 100% protection. Vaccinated persons with pre-existing comorbidities may be at an increased risk of SARS-CoV-2 breakthrough infection or reinfection. The aim of this study is to identify the critical variables associated with a higher probability of SARS-CoV-2 breakthrough infection using machine learning. Methods: A dataset comprising symptoms and feedback from 257 persons, of whom 203 were vaccinated and 54 unvaccinated, was used for the investigation. Three machine learning algorithms - Deep Multilayer Perceptron (Deep MLP), XGBoost, and Logistic Regression - were trained with the original (imbalanced) dataset and the balanced dataset created by using the Random Oversampling Technique (ROT), and the Synthetic Minority Oversampling Technique (SMOTE). We compared the performance of the classification algorithms when the features highly correlated with breakthrough infection were used and when all features in the dataset were used. Result: The results show that when highly correlated features were considered as predictors, with Random Oversampling to address data imbalance, the XGBoost classifier has the best performance (F1 = 0.96; accuracy = 0.96; AUC = 0.98; G-Mean = 0.98; MCC = 0.88). The Deep MLP had the second best performance (F1 = 0.94; accuracy = 0.94; AUC = 0.92; G-Mean = 0.70; MCC = 0.42), while Logistic Regression had less accurate performance (F1 = 0.89; accuracy = 0.88; AUC = 0.89; G-Mean = 0.89; MCC = 0.68). We also used Shapley Additive Explanations (SHAP) to investigate the interpretability of the models. We found that body temperature, total cholesterol, glucose level, blood pressure, waist circumference, body weight, body mass index (BMI), haemoglobin level, and physical activity per week are the most critical variables indicating a higher risk of breakthrough infection. Conclusion: These results, evident from our unique data source derived from apparently healthy volunteers with cardiovascular risk factors, follow the expected pattern of positive or negative correlations previously reported in the literature. This information strengthens the body of knowledge currently applied in public health guidelines and may also be used by medical practitioners in the future to reduce the risk of SARS-CoV-2 breakthrough infection.

Entomopathogenic nematodes associated with organic honeybush (Cyclopia spp.) cultivation in South Africa.

Entomopathogenic nematodes (EPNs) of the genera Steinernema and Heterorhabditis have demonstrated great potential as useful bio-control agents in the management of certain important soil-inhabiting insect pests of agricultural crops. In a survey of nematodes associated with organic honeybush cultivation, soil samples were obtained from nine organic honeybush plots, which are located in the Bredasdorp area of the Western Cape province of South Africa. The EPNs were isolated from soil by baiting with larvae of Galleria mellonella (greater wax moth) and identified by the amplification of the internal transcribed spacer region using the primer set TW81 and AB28. EPNs were abundant in the honeybush orchards, accounting for about 50% of the sampled fields and five EPN species were identified including Heterorhabditis bacteriophora, Heterorhabditis safricana, Steinernema khoisanae,. Steinernema nguyeni, Oscheius sp. and an unknown EPN, therefore suggesting a substantial diversity of EPNs in the sampled fields. A 100% mortality of infected G. mellonella larvae was recorded within 48 h of exposure to the nematodes. However, although these EPNs have been previously reported in South Africa, it is the first time they are found in such diversity on a conservative tillage management system in organic honeybush cultivation.

Diversity and population distribution of nematodes associated with honeybush (Cyclopia spp.) and rooibos (Aspalathus linearis) in the Western Cape province of South Africa.

Nematodes are important soil organisms that constitute a key component of the soil ecosystem. A plant-parasitic survey was conducted to identify the diversity of nematodes associated with two endemic tea plants, honeybush (Cyclopia spp.) and rooibos (Aspalathus linearis) in the Western Cape province of South Africa. A total of 20 farmlands were surveyed and soil samples were collected from the rhizosphere of plants, for nematode isolation and identification based on morphological characters. Confirmation of the species of plant-parasitic nematodes was done using molecular-based tools. Nematodes were classified into various feeding groups based on their colonizer-persister (c-p) values. Plant-feeding nematodes identified from the honeybush tea plants include; Criconema mutabile, Meloidogyne hapla, M. javanica, and Xiphinema oxycaudatum, while Hoplolaimus sp., Neodolichorhynchus estherae and Pratylechus bolivianus were pathogenic on the rooibos monocultures. Bacterial and fungal feeders (Cephalobidae and Rhabditidae) were also abundant and frequently encountered in all samples. The study provides information on the diversity of nematodes associated with the indigenous herbal tea plants of South Africa.

Molecular characterization of Helicotylenchus multicinctus and H. dihystera (Tylenchida: Hoplolaimidae) from Theobroma cacao in Nigeria.

The genus Helicotylenchus contains cosmopolitan, ubiquitous plant-parasitic nematodes with some species capable of causing significant economic damage to agricultural crops. Accurate species identification in this genus is essential in recognizing the damaging species and establishing effective management options. In a study on cocoa plantations in Nigeria, two species of spiral nematodes were found in high numbers from soil samples obtained from a six-decade old cocoa plantation at the Cocoa Research Institute of Nigeria. An integrated approach involving a combination of morphology, morphometrics, and molecular tools was used to identify the nematode species. Morphological data indicate the presence of both H. multicinctus and H. dihystera. There is congruence in the morphological and molecular data obtained for H. multicinctus. However, phylogenetic analysis of the 28S rDNA expansion segment revealed a high variability in the sequences of the Nigerian population of H. dihystera, suggesting the need for a careful appraisal and more comparative studies.

First report and molecular characterization of the dagger nematode, Xiphinema oxycaudatum (Nematoda, Dorylaimidae) from South Africa.

Plant-parasitic nematodes of the genus Xiphinema Cobb, 1913 comprise a complex group of nematode species, some of which are important vectors of plant viruses. During a field survey to determine the soil health of an abandoned honeybush (Cyclopia genistoides) monoculture, a high density of the dagger nematode, Xiphinema oxycaudatum Lamberti & Bleve-Zacheo, 1979 (Nematoda, Dorylaimidae), was observed in soil around the roots of honeybush plants in an abandoned farmland at Bereaville, an old mission station in the Western Cape province of South Africa. Soil samples were taken from the rhizosphere of plants and nematodes were extracted from the soil using a modified extraction tray method. Specimen of the dagger nematodes were processed for scanning electron microscopy, morphological and molecular analysis. Molecular profiling of the nematode species was done in order to give an accurate diagnosis and to effectively discriminate the nematode from other species within the Xiphinema americanum group. Phylogenetic analysis based on the D2D3 expansion segment of the 28S gene supported a close relationship of species within the americanum group, however, the protein-coding cytochrome oxidase (coxI) of the mitochondrial gene provided a useful tool for distinguishing the nematode from other species within the group. This study represents the first report of X. oxycaudatum from South Africa.