The Use of In Silico Methods to Identify and Assess Antigenic Regions Suitable for the Development of Peptide-based Pan-viral Vaccines.

The constant evolution of pathogenic viral variants and the emergence of new viruses have reinforced the need for broad-spectrum vaccines to combat such threats. The spread of new viral variants leading to epidemic and pandemic infection can be effectively contained, if broad-spectrum vaccines effective against the newer viral variants are readily available. The development of broad-spectrum, pan-neutralising antibodies against viruses which, in general terms, are very antigenically different - such as HIV, influenza virus and paramyxoviruses - has been reported in the literature. The amino acid sequences used to generate a range of approved recombinant anti-viral vaccines were analysed by using in silico methods, with the aim of identifying highly antigenic peptide regions that may be suitable for the development of broad-spectrum peptide-based anti-viral vaccines. This was achieved through the use of open-source data, an algorithm-driven probability matrix, and published in silico prediction tools (SVMTriP, IEDB-AR, VaxiJen 2.0, AllergenFP v. 1.0, AllerTOP v. 2.0, ToxinPred and ProtParam) to evaluate antigenicity, MHC-I and MHC-II binding potential, immunogenicity, allergenicity, toxicity and physicochemical properties. We report a pan-antigenic peptide region with strong affinity for MHC-I and MHC-II, and good immunogenic potential. According to the output from the relevant in silico tools, the peptide was predicted to be non-toxic, non-allergic and to possess the desired physicochemical properties for potentially successful vaccine production. With further investigation and optimisation, this peptide could be considered for use in the development of a broad-spectrum anti-viral vaccine that may protect against emerging new viruses. Our approach of using in silico methods to identify candidate antigenic peptides with the desired physicochemical properties could potentially circumvent the use of some animal studies for peptide vaccine candidate evaluation.

A Comparison of Machine Learning Models for Survival Prediction of Patients with Glioma Using Radiomic Features from MRI Scans.

Background Glioma is a primary, malignant, highly aggressive brain tumor, with patients having an average life expectancy of 14 to 16 months after diagnosis. Magnetic resonance imaging (MRI) scans of these patients can be used to extract and analyze quantifiable features with potential clinical significance. We hypothesize that there is a correlation between radiomic features extracted from MRI scans and survival. Along with clinical data, the radiomic features could be used in survival prediction of patients, providing beneficial information for clinicians to design personalized treatment plans. Methods In our study, we have utilized 3D Slicer for tumor segmentation and feature extraction and performed survival prediction of patients with glioma using four different machine learning models. Results and Conclusion Among the models compared, we have achieved a maximum prediction accuracy of 64.4% using the k-nearest neighbors model, which was trained and tested on a combination of clinical data and radiomic features extracted from MRI images provided in the BraTS 2020 dataset.