Single nucleotide polymorphisms (SNPs) contribute most of the genetic variation to the human genome. SNPs associate with many complex and common diseases like Alzheimer's disease (AD). Discovering SNP biomarkers at different loci can improve early diagnosis and treatment of these diseases. Bayesian network provides a comprehensible and modular framework for representing interactions between genes or single SNPs. Here, different Bayesian network structure learning algorithms have been applied in whole genome sequencing (WGS) data for detecting the causal AD SNPs and gene-SNP interactions. We focused on polymorphisms in the top ten genes associated with AD and identified by genome-wide association (GWA) studies. New SNP biomarkers were observed to be significantly associated with Alzheimer's disease. These SNPs are rs7530069, rs113464261, rs114506298, rs73504429, rs7929589, rs76306710, and rs668134. The obtained results demonstrated the effectiveness of using BN for identifying AD causal SNPs with acceptable accuracy. The results guarantee that the SNP set detected by Markov blanket based methods has a strong association with AD disease and achieves better performance than both naïve Bayes and tree augmented naïve Bayes. Minimal augmented Markov blanket reaches accuracy of 66.13% and sensitivity of 88.87% versus 61.58% and 59.43% in naïve Bayes, respectively.

Host-origin classification and signatures of influenza A viruses were investigated based on the HA protein for tracking of the HA host of origin. Hidden Markov models (HMMs), decision trees and associative classification for each influenza A virus subtype and its major hosts (human, avian, swine) were generated. Features of the HA protein signatures that were host-and subtype-specific were sought. Host-associated signatures that occurred in different subtypes of the virus were identified. Evaluation of the classification models based on ROC curves and support and confidence ratings for the amino acid class-association rules was performed. Host classification based on the HA subtype achieved accuracies between 91.2% and 100% using decision trees after feature selection. Host-specific class association rules for avian-host origins gave better support and confidence ratings, followed by human and finally swine origin. This finding indicated the lower specificity of the swine host, perhaps pointing to its ability to mix different strains.

SARS-CoV-2’s population structure might have a substantial impact on public health management and diagnostics if it can be identified. It is critical to rapidly monitor and characterize their lineages circulating globally for a more accurate diagnosis, improved care, and faster treatment. For a clearer picture of the SARS-CoV-2 population structure, clustering the sequencing data is essential. Here, deep clustering techniques were used to automatically group 29,017 different strains of SARS-CoV-2 into clusters. We aim to identify the main clusters of SARS-CoV-2 population structure based on convolutional autoencoder (CAE) trained with numerical feature vectors mapped from coronavirus Spike peptide sequences. Our clustering findings revealed that there are six large SARS-CoV-2 population clusters (C1, C2, C3, C4, C5, C6). These clusters contained 43 unique lineages in which the 29,017 publicly accessible strains were dispersed. In all the resulting six clusters, the genetic distances within the same cluster (intra-cluster distances) are less than the distances between inter-clusters (P-value 0.0019, Wilcoxon rank-sum test). This indicates substantial evidence of a connection between the cluster’s lineages. Furthermore, comparisons of the K-means and hierarchical clustering methods have been examined against the proposed deep learning clustering method. The intra-cluster genetic distances of the proposed method were smaller than those of K-means alone and hierarchical clustering methods. We used T-distributed stochastic-neighbor embedding (t-SNE) to show the outcomes of the deep learning clustering. The strains were isolated correctly between clusters in the t-SNE plot. Our results showed that the (C5) cluster exclusively includes Gamma lineage (P.1) only, suggesting that strains of P.1 in C5 are more diversified than those in the other clusters. Our study indicates that the genetic similarity between strains in the same cluster enables a better understanding of the major features of the unknown population lineages when compared to some of the more prevalent viral isolates. This information helps researchers figure out how the virus changed over time and spread to people all over the world.

The COVID-19 pandemic has introduced to mild the risks of deadly epidemic-prone illnesses sweeping our globalized planet. The pandemic is still going strong, with additional viral variations popping up all the time. For the close to future, the international response will have to continue. The molecular tests for SARS-CoV-2 detection may lead to False-negative results due to their genetic similarity with other coronaviruses, as well as their ability to mutate and evolve. Furthermore, the clinical features caused by SARS-CoV-2 seem to be like the symptoms of other viral infections, making identification even harder. We constructed seven hidden Markov models for each coronavirus family (SARS-CoV2, HCoV-OC43, HCoV-229E, HCoV-NL63, HCoV-HKU1, MERS-CoV, and SARS-CoV), using their complete genome to accurate diagnose human infections. Besides, this study characterized and classified the SARS-CoV2 strains according to their different geographical regions. We built six SARS-CoV2 classifiers for each world's continent (Africa, Asia, Europe, North America, South America, and Australia). The dataset used was retrieved from the NCBI virus database. The classification accuracy of these models achieves 100% in differentiating any virus model among others in the Coronavirus family. However, the accuracy of the continent models showed a variable range of accuracies, sensitivity, and specificity due to heterogeneous evolutional paths among strains from 27 countries. South America model was the highest accurate model compared to the other geographical models. This finding has vital implications for the management of COVID-19 and the improvement of vaccines.