Analysis of DNA Sequence Classification Using CNN and Hybrid Models.

In a general computational context for biomedical data analysis, DNA sequence classification is a crucial challenge. Several machine learning techniques have used to complete this task in recent years successfully. Identification and classification of viruses are essential to avoid an outbreak like COVID-19. Regardless, the feature selection process remains the most challenging aspect of the issue. The most commonly used representations worsen the case of high dimensionality, and sequences lack explicit features. It also helps in detecting the effect of viruses and drug design. In recent days, deep learning (DL) models can automatically extract the features from the input. In this work, we employed CNN, CNN-LSTM, and CNN-Bidirectional LSTM architectures using Label and K-mer encoding for DNA sequence classification. The models are evaluated on different classification metrics. From the experimental results, the CNN and CNN-Bidirectional LSTM with K-mer encoding offers high accuracy with 93.16% and 93.13%, respectively, on testing data.

Determining a sampling regime for PCR detection of respiratory tract viral infection at coronial post-mortem examinations.

Death due to respiratory infection is commonly encountered at autopsy. With only one opportunity to obtain samples for identification of a causative agent, it is important to ensure that sampling regimes are optimized to provide the greatest detection, without the expense and redundancy that can arise from over-sampling. This study was performed retrospectively using data from Coronial autopsies over the period 2012-2019 from which swabs from the nasopharyngeal region, trachea and lung parenchyma, in addition to samples of lung tissue, had been submitted for multiplex PCR detection of respiratory pathogens. From 97 cases with all four samples, there were 24 with at least one positive result for viral infection. Some cases had multiple positive results and a total of 27 respiratory tract viruses were identified, of which rhinovirus, influenza A virus and respiratory syncytial virus were the most common. Seventeen of the 27 viral infections (63%) were identified in all four samples. However, in nearly all cases (96%) the nasopharyngeal swab detected the infective agent when the multiplex PCR panel had detected infection in any of the four sample types. A nasopharyngeal swab is considered to be an optimal sample for detection of respiratory tract viral infection. As the samples analyzed were acquired before the appearance of the COVID-19 virus, the applicability of this finding for COVID-19 screening is not established.