The Potentials of Deep Learning Techniques for the Classification of SARS-CoV-2 Variants Based on Genomic Sequence Information

Genetic mutations give rise to a quasispecies of drug/vaccine-resistant and virulent organisms. These organisms are classified as strains or variants depending on the extent of their phenotypic manifestation. Thus, there is a thin dichotomy between SARS-CoV-2 strains and their associated variants. This paper sought to comprehensively review the successes achieved in the classification of SARS-CoV-2 strains based on genomic sequences (GSs) using deep learning architectures, thereby stimulating further research on the variants identified recently. Selective screening and analysis of research articles centered on deep learning architectures employed for SARS-CoV-2 detection based on GS information were carried out. This incorporated the use of relevant key/search terms and logical/Boolean operators to scan through the Scopus repository. To provide a foundation for future investigations on the classification of SARS-CoV-2 strains, meticulous analysis of the three key aspects, such as , methodology, and conclusion, was implemented. Despite the high level of intra-species similarity, this article presents new studies that use deep learning technology to detect SARS-CoV-2 strains on the premise of the primary sequence of nucleotides in their genome. Manually searching through specific genes for mutations to identify variants after sequencing can be very laborious. This is where the use of computational acumen comes into play. Deep learning, an offshoot of machine learning, has been utilized in various literature to tackle such problems. Rapid identification of SARS-CoV-2 variant after sequencing aids quick response by clinicians to administer relevant drugs and save lives. Also, governments utilize this information to map out strategies for the timely containment of the spread of an identified variant with elevated virulence. The deep learning models reported in this paper show the remarkable predictive results achieved in identifying SARS-CoV-2 strains. However, no work has been done on the identification of recent variants reported globally. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep-Learning Approach to Predict Survival Outcomes Using Wearable Actigraphy Device Among End-Stage Cancer Patients.

Survival prediction is highly valued in end-of-life care clinical practice, and patient performance status evaluation stands as a predominant component in survival prognostication. While current performance status evaluation tools are limited to their subjective nature, the advent of wearable technology enables continual recordings of patients' activity and has the potential to measure performance status objectively. We hypothesize that wristband actigraphy monitoring devices can predict in-hospital death of end-stage cancer patients during the time of their hospital admissions. The objective of this study was to train and validate a long short-term memory (LSTM) deep-learning prediction model based on activity data of wearable actigraphy devices. The study recruited 60 end-stage cancer patients in a hospice care unit, with 28 deaths and 32 discharged in stable condition at the end of their hospital stay. The standard Karnofsky Performance Status score had an overall prognostic accuracy of 0.83. The LSTM prediction model based on patients' continual actigraphy monitoring had an overall prognostic accuracy of 0.83. Furthermore, the model performance improved with longer input data length up to 48 h. In conclusion, our research suggests the potential feasibility of wristband actigraphy to predict end-of-life admission outcomes in palliative care for end-stage cancer patients. Clinical Trial Registration: The study protocol was registered on ClinicalTrials.gov (ID: NCT04883879).

Digital twins based on bidirectional LSTM and GAN for modelling the COVID-19 pandemic.

The outbreak of the coronavirus disease 2019 (COVID-19) has now spread throughout the globe infecting over 150 million people and causing the death of over 3.2 million people. Thus, there is an urgent need to study the dynamics of epidemiological models to gain a better understanding of how such diseases spread. While epidemiological models can be computationally expensive, recent advances in machine learning techniques have given rise to neural networks with the ability to learn and predict complex dynamics at reduced computational costs. Here we introduce two digital twins of a SEIRS model applied to an idealised town. The SEIRS model has been modified to take account of spatial variation and, where possible, the model parameters are based on official virus spreading data from the UK. We compare predictions from one digital twin based on a data-corrected Bidirectional Long Short-Term Memory network with predictions from another digital twin based on a predictive Generative Adversarial Network. The predictions given by these two frameworks are accurate when compared to the original SEIRS model data. Additionally, these frameworks are data-agnostic and could be applied to towns, idealised or real, in the UK or in other countries. Also, more compartments could be included in the SEIRS model, in order to study more realistic epidemiological behaviour.