Optimal Cycle Thresholds for Coronavirus Disease 2019 (COVID-19) Screening-Receiver Operating Characteristic (ROC)-Based Methods Highlight Between-Study Differences

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network

DNA methylation takes on critical significance to the regulation of gene expression by affecting the stability of DNA and changing the structure of chromosomes. DNA methylation modification sites should be identified, which lays a solid basis for gaining more insights into their biological functions. Existing machine learning-based methods of predicting DNA methylation have not fully exploited the hidden multidimensional information in DNA gene sequences, such that the prediction accuracy of models is significantly limited. Besides, most models have been built in terms of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model is capable of extracting feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). Moreover, the proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm using the cross-entropy loss function to increase the prediction accuracy of the model. Besides, the MEDCNN model can predict different types of DNA methylation sites. As indicated by the experimental results,the deep learning method based on coding from multiple dimensions outperformed single coding methods, and the MEDCNN model was highly applicable and outperformed existing models in predicting DNA methylation between different species. As revealed by the above-described findings, the MEDCNN model can be effective in predicting DNA methylation sites.

DeepLncPro: an interpretable convolutional neural network model for identifying long non-coding RNA promoters

Long non-coding RNA (lncRNA) plays important roles in a series of biological processes. The transcription of lncRNA is regulated by its promoter. Hence, accurate identification of lncRNA promoter will be helpful to understand its regulatory mechanisms. Since experimental techniques remain time consuming for gnome-wide promoter identification, developing computational tools to identify promoters are necessary. However, only few computational methods have been proposed for lncRNA promoter prediction and their performances still have room to be improved. In the present work, a convolutional neural network based model, called DeepLncPro, was proposed to identify lncRNA promoters in human and mouse. Comparative results demonstrated that DeepLncPro was superior to both state-of-the-art machine learning methods and existing models for identifying lncRNA promoters. Furthermore, DeepLncPro has the ability to extract and analyze transcription factor binding motifs from lncRNAs, which made it become an interpretable model. These results indicate that the DeepLncPro can server as a powerful tool for identifying lncRNA promoters. An open-source tool for DeepLncPro was provided at https://github.com/zhangtian-yang/DeepLncPro.

Systematic Review of Diagnostic Accuracy of DiaSorin Liaison SARS-CoV-2 Antigen Immunoassay

Background

Quantification of SARS-CoV-2 antigens by means of rapid, high-throughput and fully-automated techniques has been proposed as a feasible alternative to overcome the current shortage of resources for routine molecular diagnostics. To this end, we provide here a systematic review of diagnostic accuracy of DiaSorin Liaison SARS-CoV-2 antigen immunoassay.

Methods

An electronic search was conduced in Medline and Scopus, with no language or date restrictions (up to January 20, 2022), for identifying all published studies articles in which the diagnostic performance of the DiaSorin Liaison SARS-CoV-2 antigen immunoassay was compared with molecular diagnostic techniques.

Results

The electronic search identified a final number of 11 studies, totalling 4449 oro- and naso-pharyngeal specimens. The pooled diagnostic sensitivity, specificity and area under the curve (AUC) of the Liaison SARS-CoV-2 antigen immunoassay in all samples were 0.51 (95%CI, 0.49-0.54), 1.00 (95%CI, 1.00-1.00) and 0.994 (95%CI, 0.990-0.998), respectively, whilst the overall concordance with molecular diagnostics was 82.1%. The pooled diagnostic sensitivity, specificity and AUC of the Liaison SARS-CoV-2 antigen immunoassay in specimens with high viral load (i.e., cycle threshold values <25-30) were 0.79 (95%CI, 0.75-0.82), 1.00 (95%CI, 0.99-1.00) and 0.911 (95%CI, 0.879-0.943), respectively, whilst the overall concordance with molecular diagnostics in such samples increased to 94.2%.

Conclusion

The results of this systematic literature review suggest that there is sufficient accuracy of the DiaSorin Liaison SARS-CoV-2 antigen immunoassay in samples with high viral loads that would enable its reliable usage for identifying superspreaders, who are responsible for the vast majority of transmission events.