Evaluation of the antigenic similarity degree between the strains of the influenza virus is highly important for vaccine production. The conventional method used to measure such a degree is related to performing the immunological assays of hemagglutinin inhibition. Namely, the antigenic distance between two strains is calculated on the basis of HI assays. Usually, such distances are visualized by using some kind of antigenic cartography method. The known drawback of the HI assay is that it is rather time-consuming and expensive. In this paper, we propose a novel approach for antigenic distance approximation based on deep learning in the feature spaces induced by hemagglutinin protein sequences and Convolutional Neural Networks (CNNs). To apply a CNN to compare the protein sequences, we utilize the encoding based on the physical and chemical characteristics of amino acids. By varying (hyper)parameters of the CNN architecture design, we find the most robust network. Further, we provide insight into the relationship between approximated antigenic distance and antigenicity by evaluating the network on the HI assay database for the H1N1 subtype. The results indicate that the best-trained network gives a high-precision approximation for the ground-truth antigenic distances, and can be used as a good exploratory tool in practical tasks.

Steganography is widely applied by information security systems. The aim of steganography is to create a secret and secure channel between the sender and receiver. Steganography is basically performed in the different data types, such as image and video. Given the rapid growth of digital systems and imaging tools, the number of images and transmission of secret information is also growing. JPEG images are very popular because of their smaller size that makes them suitable for the transmission. The steganography procedure in an image can usually be performed in two domain, space domain and transform domain such as Fourier. In this preliminary study, a text steganography technique in JPEG images is presented. The text steganography is carried out on the bits with the least significant value in the discrete matrix, thus the embedded message insertion has less impact on the image quality. In the proposed method, two less significant bits of pixels are used to hide the embedded message in the image. In JPEG compression procedure before encoding, the steganography operation is applied on the image after its transformation from time into the frequency space and exactly(or right away) after the discretization of transformed data. The experimental results suggest that our approach has high capacity performance in comparison with the conventional methods.

The aim of content-based image retrieval system is finding similar images to the query image from a database based on its visual content. In this paper, a novel retrieval system based on human vision is proposed. A factor that has a high impact on the search process is a set of features which are used in. The recent studies emerged that the human eye system considers the image content, texture, and color properties more than other features. Therefore, to retrieve more precisely the images, features should be used that are close to the human eye system. In the current paper, at first, the texture is extracted from the images using the local binary patterns algorithm. After that, the color differences of two adjacent pixels with the same texture are calculated in the HSV color space. Afterward, the histogram is taken from the color difference values. The obtained features from the histogram can describe the visual content of the images in more detail. Finally, the effective features are selected based on their entropy value. The prominent advantage of the proposed method is the lack of implementation of segmentation, clustering, training, and any other method of machine learning, which requires a lot of processing and time. The method is evaluated on two standard Corel 10K and Corel 5K databases, and its retrieval rate is significantly improved compared to some recent methods.

Following its emergence at the end of 2021, the Omicron SARS-CoV-2 variant rapidly spread around the world and became a dominant variant of concern (VOC). The appearance of the new strain provoked a new pandemic wave with record incidence rates. Here, we analyze the dissemination dynamics of Omicron strains in Saint Petersburg, Russia’s second largest city. The first case of Omicron lineage BA.1 was registered in St. Petersburg on 10 December 2021. Rapid expansion of the variant and increased incidence followed. The peak incidence was reached in February 2022, followed by an observed decline coinciding with the beginning of spread of the BA.2 variant. SARS-CoV-2 lineage change dynamics were shown in three categories: airport arrivals; clinical outpatients; and clinical inpatients. It is shown that the distribution of lineage BA.1 occurred as a result of multiple imports. Variability within the BA.1 and BA.2 lineages in St. Petersburg was also revealed. On the basis of phylogenetic analysis, an attempt was made to trace the origin of the first imported strain, and an assessment was made of the quarantine measures used to prevent the spread of this kind of infection.

As a first step of genomics signal processing, alphabetical sequence is mapped to numerical. The choice of mapping techniques depends on the application and affects the result of the study. Since biological function is the result of amino acids interactions, a significant method for alphabetical to numerical conversion of sequence is to use the physico-chemical and biochemical properties of amino acids. AAindex database is a rich collection of such properties that can be used for numerical representation of protein. Each of these properties gives a viewpoint in the study of biological functions. Taking into account all AAindex indices leads to a multi-viewpoint representation and provides more options to observe and study the target biological phenomena. But this advantage increases variables number, space dimension and computation time. Since there is correlation between AAindex databases, to handle the issue of space dimension increasement, compact versions of correlated indices are extracted. This paper aims at the construction of new indices through clustering of AAindex database with correlation distance. The results suggest that due to the correlation of these new maps with groups of AAindex indices (in clusters); they have the potential to be used for numerical representation of protein sequence in different studies.

Tick-borne encephalitis virus (TBEV) is a causative agent an extremely dangerous infectious disease, often characterized by damage to the central nervous system, which sometimes leads to serious health problems, such as disability and even death. Currently, there is no global organized platform that could help researchers to study the virus, understand its evolution and localization, conduct a variety of modern mathematical and phylogenetic analyzes, automatically draw conclusions and visualize them for interpretation and decision making. Such a system could lead, as a result, to more effective actions for predicting the virus evolution. In this paper, we propose an online platform called TBEV analyzer which serves as an analytical tool in two directions - fundamental research on the virus evolution and the solution of practical problems related to public health. The platform has been developed specifically for virologists, molecular epidemiologists, evolutionists and other researchers who work with tick-borne encephalitis virus. The platform has two major benefits: first, it allows the user to concentrate on the result of analysis without concerning about computational aspects, and second, with reproducibility of system, it provides unique results associated with specific target query.