Physicochemical properties-based hybrid machine learning technique for the prediction of SARS-CoV-2 T-cell epitopes as vaccine targets.

Majority of the existing SARS-CoV-2 vaccines work by presenting the whole pathogen in the attenuated form to immune system to invoke an immune response. On the other hand, the concept of a peptide based vaccine (PBV) is based on the identification and chemical synthesis of only immunodominant peptides known as T-cell epitopes (TCEs) to induce a specific immune response against a particular pathogen. However PBVs have received less attention despite holding huge untapped potential for boosting vaccine safety and immunogenicity. To identify these TCEs for designing PBV, wet-lab experiments are difficult, expensive, and time-consuming. Machine learning (ML) techniques can accurately predict TCEs, saving time and cost for speedy vaccine development. This work proposes novel hybrid ML techniques based on the physicochemical properties of peptides to predict SARS-CoV-2 TCEs. The proposed hybrid ML technique was evaluated using various ML model evaluation metrics and demonstrated promising results. The hybrid technique of decision tree classifier with chi-squared feature weighting technique and forward search optimal feature searching algorithm has been identified as the best model with an accuracy of 98.19%. Furthermore, K-fold cross-validation (KFCV) was performed to ensure that the model is reliable and the results indicate that the hybrid random forest model performs consistently well in terms of accuracy with respect to other hybrid approaches. The predicted TCEs are highly likely to serve as promising vaccine targets, subject to evaluations both in-vivo and in-vitro. This development could potentially save countless lives globally, prevent future epidemic-scale outbreaks, and reduce the risk of mutation escape.

A comparative study of adult patient doses in film screen and computed radiography in some Sudanese hospitals.

A study was performed to compare adult patient doses in film screen (FS) and computed radiography (CR) diagnostic X-ray examinations in some hospitals in Sudan over a period of 1 y; during this period of time, the CR systems were introduced to replace FS systems. Radiation doses were estimated for 354 patients in five hospitals (two FS units and three CR units). Entrance surface air kerma (ESAK) was estimated from incident air kerma using patient exposure parameters and tube output. Dose calculations were performed using CALDOSE X 3.5 Monte Carlo-based software. In FS, third quartile of ESAK values for skull PA, skull LAT, chest PA, pelvis AP, lumbar spine AP and lumbar spine LAT were 1.5, 1.3, 0.3, 1.9, 2.8 and 5.9 mGy, respectively, while in CR, third quartile of ESAK values for the same examinations were 2.7, 1.7, 0.18, 1.7, 3.2 and 10.8 mGy, respectively. Comparable ESAK values were presented in FS and CR units. The results are important for future dose optimisation and setting national diagnostic reference levels.

Examination frequency and population dose from medical X-ray examinations in Sudan in 2010.

This study was performed to estimate examination frequency and collective and per caput effective doses arising from medical X-ray procedures in Sudan, 2010. Information was collected from 30 hospitals performing radiography, computed tomography (CT), fluoroscopy and interventional radiology (IR) procedures. The estimated annual number of examinations was 33 million radiographic X-ray procedures (99 %), 0.34 million CT exams per year (14 % paediatrics CT), 0.02 million fluoroscopy and IR procedures. The estimated annual number of examinations was 326 per 1000 people. The estimated annual collective and per caput effective doses from medical X-ray procedures mount 7197 man Sv and 0.18 mSv, respectively. The study offered the first projection of frequency and population dose from medical X-ray examinations in Sudan and provides estimates of the impact of the medical X-ray procedures at the national level.

Performance evaluation of two computed radiography systems and patient dose in pelvic examination.

This study was carried out to evaluate the performance of two computed radiography (CR) units. These evaluations became necessary following the introduction of CR systems in Sudan. Evaluation of the CR systems was performed using physical image quality parameters: signal transfer property, modulation transfer function, normalised noise power spectrum, detective quantum efficiency and the subjective contrast detail detectability. Patient dose was measured in terms of entrance surface air kerma estimated from tube output and exposure factors for 100 patients who had undergone pelvic X-ray examinations. Fuji computed radiography velocity system with columnar screen dose results was much lower than those using CR975 system with granular screen. Patient doses delivered by both systems were within the international diagnostic reference levels.

Radiation doses from some common paediatric X-ray examinations in Sudan.

Radiation doses to patients from some common paediatric X-ray examinations were studied in three hospitals in Khartoum state, Sudan. Entrance surface dose (ESD) was determined from exposure settings using DosCal software. Totally, 459 patients were included in this study. Mean ESDs obtained from anteroposterior projection for chest, skull, abdomen and pelvis for neonates falls in the range of 52-100, 115-169, 145-183, 204-242 microGy, respectively. For a 1-y-old infant, mean ESD range was 80-114, 153-202, 204-209, 181-264 microGy, respectively. Some doses for neonates and infants were exceeding the reference doses by >20%. The results highlighted that a good technique has to adhere to guidelines necessarily. As demonstrated elsewhere, patients' doses were high in departments using single-phase generators compared with those using constant potential. The results presented will serve as a baseline data needed for deriving reference doses for paediatric X-ray examinations in Sudan.