Prediction of incident atrial fibrillation using deep learning, clinical models and polygenic scores.

BACKGROUND AND AIMS: Deep learning applied to electrocardiograms (ECG-AI) is an emerging approach for predicting atrial fibrillation or flutter (AF). This study introduces an ECG-AI model developed and tested at a tertiary cardiac centre, comparing its performance with clinical and AF polygenic scores (PGS). METHODS: ECG in sinus rhythm from the Montreal Heart Institute were analysed, excluding those from patients with preexisting AF. The primary outcome was incident AF at 5 years. An ECG-AI model was developed by splitting patients into non-overlapping datasets: 70% for training, 10% for validation, and 20% for testing. Performance of ECG-AI, clinical models and PGS was assessed in the test dataset. The ECG-AI model was externally validated in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) hospital dataset. RESULTS: A total of 669,782 ECGs from 145,323 patients were included. Mean age was 61±15 years, and 58% were male. The primary outcome was observed in 15% of patients and the ECG-AI model showed an area under the receiver operating characteristic curve (AUC) of 0.78. In time-to-event analysis including the first ECG, ECG-AI inference of high risk identified 26% of the population with a 4.3-fold increased risk of incident AF (95% confidence interval 4.02-4.57). In a subgroup analysis of 2,301 patients, ECG-AI outperformed CHARGE-AF (AUC=0.62) and PGS (AUC=0.59). Adding PGS and CHARGE-AF to ECG-AI improved goodness-of-fit (likelihood ratio test p<0.001), with minimal changes to the AUC (0.76-0.77). In the external validation cohort (mean age 59±18 years, 47% male, median follow-up 1.1 year) ECG-AI model performance= remained consistent (AUC=0.77). CONCLUSIONS: ECG-AI provides an accurate tool to predict new-onset AF in a tertiary cardiac centre, surpassing clinical and polygenic scores.

Plasma myo-inositol elevation in heart failure: clinical implications and prognostic significance. Results from the BElgian and CAnadian MEtabolomics in HFpEF (BECAME-HF) research project.

BACKGROUND: The metabolic environment plays a crucial role in the development of heart failure (HF). Our prior research demonstrated that myo-inositol, a metabolite transported by the sodium-myo-inositol co-transporter 1 (SMIT-1), can induce oxidative stress and may be detrimental to heart function. However, plasmatic myo-inositol concentration has not been comprehensively assessed in large cohorts of patients with heart failure with reduced ejection fraction (HFrEF) and heart failure with preserved ejection fraction (HFpEF). METHODS: Plasmatic myo-inositol levels were measured using mass spectrometry and correlated with clinical characteristics in no HF subjects and patients with HFrEF and HFpEF from Belgian (male, no HF, 53%; HFrEF, 84% and HFpEF, 40%) and Canadian cohorts (male, no HF, 51%; HFrEF, 92% and HFpEF, 62%). FINDINGS: Myo-inositol levels were significantly elevated in patients with HF, with a more pronounced increase observed in the HFpEF population of both cohorts. After adjusting for age, sex, body mass index, hypertension, diabetes, and atrial fibrillation, we observed that both HFpEF status and impaired kidney function were associated with elevated plasma myo-inositol. Unlike HFrEF, abnormally high myo-inositol (≥69.8 µM) was linked to unfavourable clinical outcomes (hazard ratio, 1.62; 95% confidence interval, [1.05-2.5]) in patients with HFpEF. These elevated levels were correlated with NTproBNP, troponin, and cardiac fibrosis in this subset of patients. INTERPRETATION: Myo-inositol is a metabolite elevated in patients with HF and strongly correlated to kidney failure. In patients with HFpEF, high myo-inositol levels predict poor clinical outcomes and are linked to markers of cardiac adverse remodelling. This suggests that myo-inositol and its transporter SMIT1 may have a role in the pathophysiology of HFpEF. FUNDING: BECAME-HF was supported by Collaborative Bilateral Research Program Québec - Wallonie-Brussels Federation.

Temperature-dependent Spike-ACE2 interaction of Omicron subvariants is associated with viral transmission.

The continued evolution of severe acute respiratory syndrome 2 (SARS-CoV-2) requires persistent monitoring of its subvariants. Omicron subvariants are responsible for the vast majority of SARS-CoV-2 infections worldwide, with XBB and BA.2.86 sublineages representing more than 90% of circulating strains as of January 2024. To better understand parameters involved in viral transmission, we characterized the functional properties of Spike glycoproteins from BA.2.75, CH.1.1, DV.7.1, BA.4/5, BQ.1.1, XBB, XBB.1, XBB.1.16, XBB.1.5, FD.1.1, EG.5.1, HK.3, BA.2.86 and JN.1. We tested their capacity to evade plasma-mediated recognition and neutralization, binding to angiotensin-converting enzyme 2 (ACE2), their susceptibility to cold inactivation, Spike processing, as well as the impact of temperature on Spike-ACE2 interaction. We found that compared to the early wild-type (D614G) strain, most Omicron subvariants' Spike glycoproteins evolved to escape recognition and neutralization by plasma from individuals who received a fifth dose of bivalent (BA.1 or BA.4/5) mRNA vaccine and improve ACE2 binding, particularly at low temperatures. Moreover, BA.2.86 had the best affinity for ACE2 at all temperatures tested. We found that Omicron subvariants' Spike processing is associated with their susceptibility to cold inactivation. Intriguingly, we found that Spike-ACE2 binding at low temperature was significantly associated with growth rates of Omicron subvariants in humans. Overall, we report that Spikes from newly emerged Omicron subvariants are relatively more stable and resistant to plasma-mediated neutralization, present improved affinity for ACE2 which is associated, particularly at low temperatures, with their growth rates.IMPORTANCEThe persistent evolution of SARS-CoV-2 gave rise to a wide range of variants harboring new mutations in their Spike glycoproteins. Several factors have been associated with viral transmission and fitness such as plasma-neutralization escape and ACE2 interaction. To better understand whether additional factors could be of importance in SARS-CoV-2 variants' transmission, we characterize the functional properties of Spike glycoproteins from several Omicron subvariants. We found that the Spike glycoprotein of Omicron subvariants presents an improved escape from plasma-mediated recognition and neutralization, Spike processing, and ACE2 binding which was further improved at low temperature. Intriguingly, Spike-ACE2 interaction at low temperature is strongly associated with viral growth rate, as such, low temperatures could represent another parameter affecting viral transmission.

Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide.

Large language models (LLMs) have emerged as powerful tools in artificial intelligence, demonstrating remarkable capabilities in natural language processing and generation. In this article, we explore the potential applications of LLMs in enhancing cardiovascular care and research. We discuss how LLMs can be used to simplify complex medical information, improve patient-physician communication, and automate tasks such as summarising medical articles and extracting key information. In addition, we highlight the role of LLMs in categorising and analysing unstructured data, such as medical notes and test results, which could revolutionise data handling and interpretation in cardiovascular research. However, we also emphasise the limitations and challenges associated with LLMs, including potential biases, reasoning opacity, and the need for rigourous validation in medical contexts. This review provides a practical guide for cardiovascular professionals to understand and harness the power of LLMs while navigating their limitations. We conclude by discussing the future directions and implications of LLMs in transforming cardiovascular care and research.

A Responsible Framework for Applying Artificial Intelligence on Medical Images and Signals at the Point of Care: The PACS-AI Platform.

The potential of artificial intelligence (AI) in medicine lies in its ability to enhance clinicians' capacity to analyse medical images, thereby improving diagnostic precision and accuracy and thus enhancing current tests. However, the integration of AI within health care is fraught with difficulties. Heterogeneity among health care system applications, reliance on proprietary closed-source software, and rising cybersecurity threats pose significant challenges. Moreover, before their deployment in clinical settings, AI models must demonstrate their effectiveness across a wide range of scenarios and must be validated by prospective studies, but doing so requires testing in an environment mirroring the clinical workflow, which is difficult to achieve without dedicated software. Finally, the use of AI techniques in health care raises significant legal and ethical issues, such as the protection of patient privacy, the prevention of bias, and the monitoring of the device's safety and effectiveness for regulatory compliance. This review describes challenges to AI integration in health care and provides guidelines on how to move forward. We describe an open-source solution that we developed that integrates AI models into the Picture Archives Communication System (PACS), called PACS-AI. This approach aims to increase the evaluation of AI models by facilitating their integration and validation with existing medical imaging databases. PACS-AI may overcome many current barriers to AI deployment and offer a pathway toward responsible, fair, and effective deployment of AI models in health care. In addition, we propose a list of criteria and guidelines that AI researchers should adopt when publishing a medical AI model to enhance standardisation and reproducibility.

Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology.

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area for its technological advancements and clinical application. In this review we explore the complex issue of data bias, specifically addressing those encountered during the development and implementation of AI tools in cardiology. We dissect the origins and effects of these biases, which challenge their reliability and widespread applicability in health care. Using a case study, we highlight the complexities involved in addressing these biases from a clinical viewpoint. The goal of this review is to equip researchers and clinicians with the practical knowledge needed to identify, understand, and mitigate these biases, advocating for the creation of AI solutions that are not just technologically sound, but also fair and effective for all patients.

Intra-Host Evolution Analyses in an Immunosuppressed Patient Supports SARS-CoV-2 Viral Reservoir Hypothesis.

Throughout the SARS-CoV-2 pandemic, several variants of concern (VOCs) have been identified, many of which share recurrent mutations in the spike glycoprotein's receptor-binding domain (RBD). This region coincides with known epitopes and can therefore have an impact on immune escape. Protracted infections in immunosuppressed patients have been hypothesized to lead to an enrichment of such mutations and therefore drive evolution towards VOCs. Here, we present the case of an immunosuppressed patient that developed distinct populations with immune escape mutations throughout the course of their infection. Notably, by investigating the co-occurrence of substitutions on individual sequencing reads in the RBD, we found quasispecies harboring mutations that confer resistance to known monoclonal antibodies (mAbs) such as S:E484K and S:E484A. These mutations were acquired without the patient being treated with mAbs nor convalescent sera and without them developing a detectable immune response to the virus. We also provide additional evidence for a viral reservoir based on intra-host phylogenetics, which led to a viral substrain that evolved elsewhere in the patient's body, colonizing their upper respiratory tract (URT). The presence of SARS-CoV-2 viral reservoirs can shed light on protracted infections interspersed with periods where the virus is undetectable, and potential explanations for long-COVID cases.

Signatures of Co-evolution and Co-regulation in the CYP3A and CYP4F Genes in Humans.

Cytochromes P450 (CYP450) are hemoproteins generally involved in the detoxification of the body of xenobiotic molecules. They participate in the metabolism of many drugs and genetic polymorphisms in humans have been found to impact drug responses and metabolic functions. In this study, we investigate the genetic diversity of CYP450 genes. We found that two clusters, CYP3A and CYP4F, are notably differentiated across human populations with evidence for selective pressures acting on both clusters: we found signals of recent positive selection in CYP3A and CYP4F genes and signals of balancing selection in CYP4F genes. Furthermore, an extensive amount of unusual linkage disequilibrium is detected in this latter cluster, indicating co-evolution signatures among CYP4F genes. Several of the selective signals uncovered co-localize with expression quantitative trait loci (eQTL), which could suggest epistasis acting on co-regulation in these gene families. In particular, we detected a potential co-regulation event between CYP3A5 and CYP3A43, a gene whose function remains poorly characterized. We further identified a causal relationship between CYP3A5 expression and reticulocyte count through Mendelian randomization analyses, potentially involving a regulatory region displaying a selective signal specific to African populations. Our findings linking natural selection and gene expression in CYP3A and CYP4F subfamilies are of importance in understanding population differences in metabolism of nutrients and drugs.

Gene-metabolite annotation with shortest reactional distance enhances metabolite genome-wide association studies results.

Metabolite genome-wide association studies (mGWAS) have advanced our understanding of the genetic control of metabolite levels. However, interpreting these associations remains challenging due to a lack of tools to annotate gene-metabolite pairs beyond the use of conservative statistical significance threshold. Here, we introduce the shortest reactional distance (SRD) metric, drawing from the comprehensive KEGG database, to enhance the biological interpretation of mGWAS results. We applied this approach to three independent mGWAS, including a case study on sickle cell disease patients. Our analysis reveals an enrichment of small SRD values in reported mGWAS pairs, with SRD values significantly correlating with mGWAS p values, even beyond the standard conservative thresholds. We demonstrate the utility of SRD annotation in identifying potential false negatives and inaccuracies within current metabolic pathway databases. Our findings highlight the SRD metric as an objective, quantitative and easy-to-compute annotation for gene-metabolite pairs, suitable to integrate statistical evidence to biological networks.

Toward computing attributions for dimensionality reduction techniques.

Summary: We describe the problem of computing local feature attributions for dimensionality reduction methods. We use one such method that is well established within the context of supervised classification-using the gradients of target outputs with respect to the inputs-on the popular dimensionality reduction technique t-SNE, widely used in analyses of biological data. We provide an efficient implementation for the gradient computation for this dimensionality reduction technique. We show that our explanations identify significant features using novel validation methodology; using synthetic datasets and the popular MNIST benchmark dataset. We then demonstrate the practical utility of our algorithm by showing that it can produce explanations that agree with domain knowledge on a SARS-CoV-2 sequence dataset. Throughout, we provide a road map so that similar explanation methods could be applied to other dimensionality reduction techniques to rigorously analyze biological datasets. Availability and implementation: We have created a Python package that can be installed using the following command: pip install interpretable_tsne. All code used can be found at github.com/MattScicluna/interpretable_tsne.

Selection for immune evasion in SARS-CoV-2 revealed by high-resolution epitope mapping and sequence analysis.

Here, we exploit a deep serological profiling strategy coupled with an integrated, computational framework for the analysis of SARS-CoV-2 humoral immune responses. Applying a high-density peptide array (HDPA) spanning the entire proteomes of SARS-CoV-2 and endemic human coronaviruses allowed identification of B cell epitopes and relate them to their evolutionary and structural properties. We identify hotspots of pre-existing immunity and identify cross-reactive epitopes that contribute to increasing the overall humoral immune response to SARS-CoV-2. Using a public dataset of over 38,000 viral genomes from the early phase of the pandemic, capturing both inter- and within-host genetic viral diversity, we determined the evolutionary profile of epitopes and the differences across proteins, waves, and SARS-CoV-2 variants. Lastly, we show that mutations in spike and nucleocapsid epitopes are under stronger selection between than within patients, suggesting that most of the selective pressure for immune evasion occurs upon transmission between hosts.

Gene-metabolite annotation with shortest reactional distance enhances metabolite genome-wide association studies results.

Studies combining metabolomics and genetics, known as metabolite genome-wide association studies (mGWAS), have provided valuable insights into our understanding of the genetic control of metabolite levels. However, the biological interpretation of these associations remains challenging due to a lack of existing tools to annotate mGWAS gene-metabolite pairs beyond the use of conservative statistical significance threshold. Here, we computed the shortest reactional distance (SRD) based on the curated knowledge of the KEGG database to explore its utility in enhancing the biological interpretation of results from three independent mGWAS, including a case study on sickle cell disease patients. Results show that, in reported mGWAS pairs, there is an excess of small SRD values and that SRD values and p-values significantly correlate, even beyond the standard conservative thresholds. The added-value of SRD annotation is shown for identification of potential false negative hits, exemplified by the finding of gene-metabolite associations with SRD ≤1 that did not reach standard genome-wide significance cut-off. The wider use of this statistic as an mGWAS annotation would prevent the exclusion of biologically relevant associations and can also identify errors or gaps in current metabolic pathway databases. Our findings highlight the SRD metric as an objective, quantitative and easy-to-compute annotation for gene-metabolite pairs that can be used to integrate statistical evidence to biological networks.

The race to understand immunopathology in COVID-19: Perspectives on the impact of quantitative approaches to understand within-host interactions.

The COVID-19 pandemic has revealed the need for the increased integration of modelling and data analysis to public health, experimental, and clinical studies. Throughout the first two years of the pandemic, there has been a concerted effort to improve our understanding of the within-host immune response to the SARS-CoV-2 virus to provide better predictions of COVID-19 severity, treatment and vaccine development questions, and insights into viral evolution and the impacts of variants on immunopathology. Here we provide perspectives on what has been accomplished using quantitative methods, including predictive modelling, population genetics, machine learning, and dimensionality reduction techniques, in the first 26 months of the COVID-19 pandemic approaches, and where we go from here to improve our responses to this and future pandemics.

Study of effect modifiers of genetically predicted CETP reduction.

Genetic variants in drug targets can be used to predict the long-term, on-target effect of drugs. Here, we extend this principle to assess how sex and body mass index may modify the effect of genetically predicted lower CETP levels on biomarkers and cardiovascular outcomes. We found sex and body mass index (BMI) to be modifiers of the association between genetically predicted lower CETP and lipid biomarkers in UK Biobank participants. Female sex and lower BMI were associated with higher high-density lipoprotein cholesterol and lower low-density lipoprotein cholesterol for the same genetically predicted reduction in CETP concentration. We found that sex also modulated the effect of genetically lower CETP on cholesterol efflux capacity in samples from the Montreal Heart Institute Biobank. However, these modifying effects did not extend to sex differences in cardiovascular outcomes in our data. Our results provide insight into the clinical effects of CETP inhibitors in the presence of effect modification based on genetic data. The approach can support precision medicine applications and help assess the external validity of clinical trials.

deepSimDEF: deep neural embeddings of gene products and gene ontology terms for functional analysis of genes.

MOTIVATION: There is a plethora of measures to evaluate functional similarity (FS) of genes based on their co-expression, protein-protein interactions and sequence similarity. These measures are typically derived from hand-engineered and application-specific metrics to quantify the degree of shared information between two genes using their Gene Ontology (GO) annotations. RESULTS: We introduce deepSimDEF, a deep learning method to automatically learn FS estimation of gene pairs given a set of genes and their GO annotations. deepSimDEF's key novelty is its ability to learn low-dimensional embedding vector representations of GO terms and gene products and then calculate FS using these learned vectors. We show that deepSimDEF can predict the FS of new genes using their annotations: it outperformed all other FS measures by >5-10% on yeast and human reference datasets on protein-protein interactions, gene co-expression and sequence homology tasks. Thus, deepSimDEF offers a powerful and adaptable deep neural architecture that can benefit a wide range of problems in genomics and proteomics, and its architecture is flexible enough to support its extension to any organism. AVAILABILITY AND IMPLEMENTATION: Source code and data are available at https://github.com/ahmadpgh/deepSimDEF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Comparative Study of Protein Aggregation Propensity and Mutation Tolerance Between Naked Mole-Rat and Mouse.

The molecular mechanisms of aging and life expectancy have been studied in model organisms with short lifespans. However, long-lived species may provide insights into successful strategies for healthy aging, potentially opening the door for novel therapeutic interventions in age-related diseases. Notably, naked mole-rats, the longest-lived rodent, present attenuated aging phenotypes compared with mice. Their resistance toward oxidative stress has been proposed as one hallmark of their healthy aging, suggesting their ability to maintain cell homeostasis, specifically their protein homeostasis. To identify the general principles behind their protein homeostasis robustness, we compared the aggregation propensity and mutation tolerance of naked mole-rat and mouse orthologous proteins. Our analysis showed no proteome-wide differential effects in aggregation propensity and mutation tolerance between these species, but several subsets of proteins with a significant difference in aggregation propensity. We found an enrichment of proteins with higher aggregation propensity in naked mole-rat, and these are functionally involved in the inflammasome complex and nucleic acid binding. On the other hand, proteins with lower aggregation propensity in naked mole-rat have a significantly higher mutation tolerance compared with the rest of the proteins. Among them, we identified proteins known to be associated with neurodegenerative and age-related diseases. These findings highlight the intriguing hypothesis about the capacity of the naked mole-rat proteome to delay aging through its proteomic intrinsic architecture.

Population Genomics Approaches for Genetic Characterization of SARS-CoV-2 Lineages.

The genome of the Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2), the pathogen that causes coronavirus disease 2019 (COVID-19), has been sequenced at an unprecedented scale leading to a tremendous amount of viral genome sequencing data. To assist in tracing infection pathways and design preventive strategies, a deep understanding of the viral genetic diversity landscape is needed. We present here a set of genomic surveillance tools from population genetics which can be used to better understand the evolution of this virus in humans. To illustrate the utility of this toolbox, we detail an in depth analysis of the genetic diversity of SARS-CoV-2 in first year of the COVID-19 pandemic. We analyzed 329,854 high-quality consensus sequences published in the GISAID database during the pre-vaccination phase. We demonstrate that, compared to standard phylogenetic approaches, haplotype networks can be computed efficiently on much larger datasets. This approach enables real-time lineage identification, a clear description of the relationship between variants of concern, and efficient detection of recurrent mutations. Furthermore, time series change of Tajima's D by haplotype provides a powerful metric of lineage expansion. Finally, principal component analysis (PCA) highlights key steps in variant emergence and facilitates the visualization of genomic variation in the context of SARS-CoV-2 diversity. The computational framework presented here is simple to implement and insightful for real-time genomic surveillance of SARS-CoV-2 and could be applied to any pathogen that threatens the health of populations of humans and other organisms.

Multiscale PHATE identifies multimodal signatures of COVID-19.

As the biomedical community produces datasets that are increasingly complex and high dimensional, there is a need for more sophisticated computational tools to extract biological insights. We present Multiscale PHATE, a method that sweeps through all levels of data granularity to learn abstracted biological features directly predictive of disease outcome. Built on a coarse-graining process called diffusion condensation, Multiscale PHATE learns a data topology that can be analyzed at coarse resolutions for high-level summarizations of data and at fine resolutions for detailed representations of subsets. We apply Multiscale PHATE to a coronavirus disease 2019 (COVID-19) dataset with 54 million cells from 168 hospitalized patients and find that patients who die show CD16hiCD66blo neutrophil and IFN-γ+ granzyme B+ Th17 cell responses. We also show that population groupings from Multiscale PHATE directly fed into a classifier predict disease outcome more accurately than naive featurizations of the data. Multiscale PHATE is broadly generalizable to different data types, including flow cytometry, single-cell RNA sequencing (scRNA-seq), single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq), and clinical variables.

Construction of a femininity score in the UK Biobank and its association with angina diagnosis prior to myocardial infarction.

Gender captures social components beyond biological sex and can add valuable insight to health studies in populations. However, assessment of gender typically relies on questionnaires which may not be available. The aim of this study is to construct a gender metric using available variables in the UK Biobank and to apply it to the study of angina diagnosis. Proxy variables for femininity characteristics were identified in the UK Biobank and regressed on sex to construct a composite femininity score (FS) validated using tenfold cross-validation. The FS was assessed as a predictor of angina diagnosis before incident myocardial infarction (MI) events. The FS was derived for 315,937 UK Biobank participants. In 3059 individuals with no history of MI at study entry who had an incident MI event, the FS was a significant predictor of angina diagnosis prior to MI (OR 1.24, 95% CI 1.10-1.39, P < 0.001) with a significant sex-by-FS interaction effect (P = 0.003). The FS was positively associated with angina diagnosis prior to MI in men (OR 1.37, 95% CI 1.19-1.57, P < 0.001), but not in women. We have provided a new tool to conduct gender-sensitive analyses in observational studies, and applied it to study of angina diagnosis prior to MI.

The mutational landscape of SARS-CoV-2 variants diversifies T cell targets in an HLA-supertype-dependent manner.

The rapid, global dispersion of SARS-CoV-2 has led to the emergence of a diverse range of variants. Here, we describe how the mutational landscape of SARS-CoV-2 has shaped HLA-restricted T cell immunity at the population level during the first year of the pandemic. We analyzed a total of 330,246 high-quality SARS-CoV-2 genome assemblies, sampled across 143 countries and all major continents from December 2019 to December 2020 before mass vaccination or the rise of the Delta variant. We observed that proline residues are preferentially removed from the proteome of prevalent mutants, leading to a predicted global loss of SARS-CoV-2 T cell epitopes in individuals expressing HLA-B alleles of the B7 supertype family; this is largely driven by a dominant C-to-U mutation type at the RNA level. These results indicate that B7-supertype-associated epitopes, including the most immunodominant ones, were more likely to escape CD8+ T cell immunosurveillance during the first year of the pandemic.