Genomic Surveillance of COVID-19 Variants With Language Models and Machine Learning

Multimodal data fusion using sparse canonical correlation analysis and cooperative learning: a COVID-19 cohort study

Through technological innovations, patient cohorts can be examined from multiple views with high-dimensional, multiscale biomedical data to classify clinical phenotypes and predict outcomes. Here, we aim to present our approach for analyzing multimodal data using unsupervised and supervised sparse linear methods in a COVID-19 patient cohort. This prospective cohort study of 149 adult patients was conducted in a tertiary care academic center. First, we used sparse canonical correlation analysis (CCA) to identify and quantify relationships across different data modalities, including viral genome sequencing, imaging, clinical data, and laboratory results. Then, we used cooperative learning to predict the clinical outcome of COVID-19 patients: Intensive care unit admission. We show that serum biomarkers representing severe disease and acute phase response correlate with original and wavelet radiomics features in the LLL frequency channel (cor(Xu1, Zv1) = 0.596, p value < 0.001). Among radiomics features, histogram-based first-order features reporting the skewness, kurtosis, and uniformity have the lowest negative, whereas entropy-related features have the highest positive coefficients. Moreover, unsupervised analysis of clinical data and laboratory results gives insights into distinct clinical phenotypes. Leveraging the availability of global viral genome databases, we demonstrate that the Word2Vec natural language processing model can be used for viral genome encoding. It not only separates major SARS-CoV-2 variants but also allows the preservation of phylogenetic relationships among them. Our quadruple model using Word2Vec encoding achieves better prediction results in the supervised task. The model yields area under the curve (AUC) and accuracy values of 0.87 and 0.77, respectively. Our study illustrates that sparse CCA analysis and cooperative learning are powerful techniques for handling high-dimensional, multimodal data to investigate multivariate associations in unsupervised and supervised tasks.

Innovative applications of artificial intelligence during the COVID-19 pandemic

The COVID-19 pandemic has created unprecedented challenges worldwide. Artificial intelligence (AI) technologies hold tremendous potential for tackling key aspects of pandemic management and response. In the present review, we discuss the tremendous possibilities of AI technology in addressing the global challenges posed by the COVID-19 pandemic. First, we outline the multiple impacts of the current pandemic on public health, the economy, and society. Next, we focus on the innovative applications of advanced AI technologies in key areas such as COVID-19 prediction, detection, control, and drug discovery for treatment. Specifically, AI-based predictive analytics models can use clinical, epidemiological, and omics data to forecast disease spread and patient outcomes. Additionally, deep neural networks enable rapid diagnosis through medical imaging. Intelligent systems can support risk assessment, decision-making, and social sensing, thereby improving epidemic control and public health policies. Furthermore, high-throughput virtual screening enables AI to accelerate the identification of therapeutic drug candidates and opportunities for drug repurposing. Finally, we discuss future research directions for AI technology in combating COVID-19, emphasizing the importance of interdisciplinary collaboration. Though promising, barriers related to model generalization, data quality, infrastructure readiness, and ethical risks must be addressed to fully translate these innovations into real-world impacts. Multidisciplinary collaboration engaging diverse expertise and stakeholders is imperative for developing robust, responsible, and human-centered AI solutions against COVID-19 and future public health emergencies.

Genetic justification of COVID-19 patient outcomes using DERGA, a novel data ensemble refinement greedy algorithm

Complement inhibition has shown promise in various disorders, including COVID-19. A prediction tool including complement genetic variants is vital. This study aims to identify crucial complement-related variants and determine an optimal pattern for accurate disease outcome prediction. Genetic data from 204 COVID-19 patients hospitalized between April 2020 and April 2021 at three referral centres were analysed using an artificial intelligence-based algorithm to predict disease outcome (ICU vs. non-ICU admission). A recently introduced alpha-index identified the 30 most predictive genetic variants. DERGA algorithm, which employs multiple classification algorithms, determined the optimal pattern of these key variants, resulting in 97% accuracy for predicting disease outcome. Individual variations ranged from 40 to 161 variants per patient, with 977 total variants detected. This study demonstrates the utility of alpha-index in ranking a substantial number of genetic variants. This approach enables the implementation of well-established classification algorithms that effectively determine the relevance of genetic variants in predicting outcomes with high accuracy.

Multimodal Biomedical Data Fusion Using Sparse Canonical Correlation Analysis and Cooperative Learning: A Cohort Study on COVID-19

Through technological innovations, patient cohorts can be examined from multiple views with high-dimensional, multiscale biomedical data to classify clinical phenotypes and predict outcomes. Here, we aim to present our approach for analyzing multimodal data using unsupervised and supervised sparse linear methods in a COVID-19 patient cohort. This prospective cohort study of 149 adult patients was conducted in a tertiary care academic center. First, we used sparse canonical correlation analysis (CCA) to identify and quantify relationships across different data modalities, including viral genome sequencing, imaging, clinical data, and laboratory results. Then, we used cooperative learning to predict the clinical outcome of COVID-19 patients. We show that serum biomarkers representing severe disease and acute phase response correlate with original and wavelet radiomics features in the LLL frequency channel (corr(Xu1, Zv1) = 0.596, p-value < 0.001). Among radiomics features, histogram-based first-order features reporting the skewness, kurtosis, and uniformity have the lowest negative, whereas entropy-related features have the highest positive coefficients. Moreover, unsupervised analysis of clinical data and laboratory results gives insights into distinct clinical phenotypes. Leveraging the availability of global viral genome databases, we demonstrate that the Word2Vec natural language processing model can be used for viral genome encoding. It not only separates major SARS-CoV-2 variants but also allows the preservation of phylogenetic relationships among them. Our quadruple model using Word2Vec encoding achieves better prediction results in the supervised task. The model yields area under the curve (AUC) and accuracy values of 0.87 and 0.77, respectively. Our study illustrates that sparse CCA analysis and cooperative learning are powerful techniques for handling high-dimensional, multimodal data to investigate multivariate associations in unsupervised and supervised tasks.

The Epidemiology of Infectious Diseases Meets AI: A Match Made in Heaven

Infectious diseases remain a major threat to public health [...].

Predicting emerging SARS-CoV-2 variants of concern through a One Class dynamic anomaly detection algorithm

OBJECTIVES

The objective of this study is the implementation of an automatic procedure to weekly detect new SARS-CoV-2 variants and non-neutral variants (variants of concern (VOC) and variants of interest (VOI)).

METHODS

We downloaded spike protein primary sequences from the public resource GISAID and we represented each sequence as k-mer counts. For each week since 1 July 2020, we evaluate if each sequence represents an anomaly based on a One Class support vector machine (SVM) classification algorithm trained on neutral protein sequences collected from February to June 2020.

RESULTS

We assess the ability of the One Class classifier to detect known VOC and VOI, such as Alpha, Delta or Omicron, ahead of their official classification by health authorities. In median, the classifier predicts a non-neutral variant as outlier 10 weeks before the official date of designation as VOC/VOI.

DISCUSSION

The identification of non-neutral variants during a pandemic usually relies on indicators available during time, such as changing population size of a variant. Automatic variant surveillance systems based on protein sequences can enhance the fast identification of variants of potential concern.

CONCLUSION

Machine learning, and in particular One Class SVM classification, can support the detection of potentially VOC/VOI variants during an evolving pandemics.

Factors Modulating COVID-19: A Mechanistic Understanding Based on the Adverse Outcome Pathway Framework

Addressing factors modulating COVID-19 is crucial since abundant clinical evidence shows that outcomes are markedly heterogeneous between patients. This requires identifying the factors and understanding how they mechanistically influence COVID-19. Here, we describe how eleven selected factors (age, sex, genetic factors, lipid disorders, heart failure, gut dysbiosis, diet, vitamin D deficiency, air pollution and exposure to chemicals) influence COVID-19 by applying the Adverse Outcome Pathway (AOP), which is well-established in regulatory toxicology. This framework aims to model the sequence of events leading to an adverse health outcome. Several linear AOPs depicting pathways from the binding of the virus to ACE2 up to clinical outcomes observed in COVID-19 have been developed and integrated into a network offering a unique overview of the mechanisms underlying the disease. As SARS-CoV-2 infectibility and ACE2 activity are the major starting points and inflammatory response is central in the development of COVID-19, we evaluated how those eleven intrinsic and extrinsic factors modulate those processes impacting clinical outcomes. Applying this AOP-aligned approach enables the identification of current knowledge gaps orientating for further research and allows to propose biomarkers to identify of high-risk patients. This approach also facilitates expertise synergy from different disciplines to address public health issues.

A Bioinformatics Tool for Predicting Future COVID-19 Waves Based on a Retrospective Analysis of the Second Wave in India: Model Development Study

Background

Since the start of the COVID-19 pandemic, health policymakers globally have been attempting to predict an impending wave of COVID-19. India experienced a devastating second wave of COVID-19 in the late first week of May 2021. We retrospectively analyzed the viral genomic sequences and epidemiological data reflecting the emergence and spread of the second wave of COVID-19 in India to construct a prediction model.

Objective

We aimed to develop a bioinformatics tool that can predict an impending COVID-19 wave.

Methods

We analyzed the time series distribution of genomic sequence data for SARS-CoV-2 and correlated it with epidemiological data for new cases and deaths for the corresponding period of the second wave. In addition, we analyzed the phylodynamics of circulating SARS-CoV-2 variants in the Indian population during the study period.

Results

Our prediction analysis showed that the first signs of the arrival of the second wave could be seen by the end of January 2021, about 2 months before its peak in May 2021. By the end of March 2021, it was distinct. B.1.617 lineage variants powered the wave, most notably B.1.617.2 (Delta variant).

Conclusions

Based on the observations of this study, we propose that genomic surveillance of SARS-CoV-2 variants, complemented with epidemiological data, can be a promising tool to predict impending COVID-19 waves.