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. This review explores 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 impacts of these biases, which challenge their reliability and widespread applicability in healthcare. 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 patient demographics.

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.

Implementing Machine Learning in Interventional Cardiology: The Benefits Are Worth the Trouble.

Driven by recent innovations and technological progress, the increasing quality and amount of biomedical data coupled with the advances in computing power allowed for much progress in artificial intelligence (AI) approaches for health and biomedical research. In interventional cardiology, the hope is for AI to provide automated analysis and deeper interpretation of data from electrocardiography, computed tomography, magnetic resonance imaging, and electronic health records, among others. Furthermore, high-performance predictive models supporting decision-making hold the potential to improve safety, diagnostic and prognostic prediction in patients undergoing interventional cardiology procedures. These applications include robotic-assisted percutaneous coronary intervention procedures and automatic assessment of coronary stenosis during diagnostic coronary angiograms. Machine learning (ML) has been used in these innovations that have improved the field of interventional cardiology, and more recently, deep Learning (DL) has emerged as one of the most successful branches of ML in many applications. It remains to be seen if DL approaches will have a major impact on current and future practice. DL-based predictive systems also have several limitations, including lack of interpretability and lack of generalizability due to cohort heterogeneity and low sample sizes. There are also challenges for the clinical implementation of these systems, such as ethical limits and data privacy. This review is intended to bring the attention of health practitioners and interventional cardiologists to the broad and helpful applications of ML and DL algorithms to date in the field. Their implementation challenges in daily practice and future applications in the field of interventional cardiology are also discussed.

Patient health records and whole viral genomes from an early SARS-CoV-2 outbreak in a Quebec hospital reveal features associated with favorable outcomes.

The first confirmed case of COVID-19 in Quebec, Canada, occurred at Verdun Hospital on February 25, 2020. A month later, a localized outbreak was observed at this hospital. We performed tiled amplicon whole genome nanopore sequencing on nasopharyngeal swabs from all SARS-CoV-2 positive samples from 31 March to 17 April 2020 in 2 local hospitals to assess viral diversity (unknown at the time in Quebec) and potential associations with clinical outcomes. We report 264 viral genomes from 242 individuals-both staff and patients-with associated clinical features and outcomes, as well as longitudinal samples and technical replicates. Viral lineage assessment identified multiple subclades in both hospitals, with a predominant subclade in the Verdun outbreak, indicative of hospital-acquired transmission. Dimensionality reduction identified two subclades with mutations of clinical interest, namely in the Spike protein, that evaded supervised lineage assignment methods-including Pangolin and NextClade supervised lineage assignment tools. We also report that certain symptoms (headache, myalgia and sore throat) are significantly associated with favorable patient outcomes. Our findings demonstrate the strength of unsupervised, data-driven analyses whilst suggesting that caution should be used when employing supervised genomic workflows, particularly during the early stages of a pandemic.

A sex-specific evolutionary interaction between ADCY9 and CETP.

Pharmacogenomic studies have revealed associations between rs1967309 in the adenylyl cyclase type 9 (ADCY9) gene and clinical responses to the cholesteryl ester transfer protein (CETP) modulator dalcetrapib, however, the mechanism behind this interaction is still unknown. Here, we characterized selective signals at the locus associated with the pharmacogenomic response in human populations and we show that rs1967309 region exhibits signatures of positive selection in several human populations. Furthermore, we identified a variant in CETP, rs158477, which is in long-range linkage disequilibrium with rs1967309 in the Peruvian population. The signal is mainly seen in males, a sex-specific result that is replicated in the LIMAA cohort of over 3400 Peruvians. Analyses of RNA-seq data further suggest an epistatic interaction on CETP expression levels between the two SNPs in multiple tissues, which also differs between males and females. We also detected interaction effects of the two SNPs with sex on cardiovascular phenotypes in the UK Biobank, in line with the sex-specific genotype associations found in Peruvians at these loci. We propose that ADCY9 and CETP coevolved during recent human evolution due to sex-specific selection, which points toward a biological link between dalcetrapib's pharmacogene ADCY9 and its therapeutic target CETP.

Differential modulation of polyunsaturated fatty acids in patients with myocardial infarction treated with ticagrelor or clopidogrel.

Untargeted metabolomics is used to refine the development of biomarkers for the diagnosis of cardiovascular disease. Myocardial infarction (MI) has major individual and societal consequences for patients, who remain at high risk of secondary events, despite advances in pharmacological therapy. To monitor their differential response to treatment, we performed untargeted plasma metabolomics on 175 patients from the platelet inhibition and patient outcomes (PLATO) trial treated with ticagrelor and clopidogrel, two common P2Y12 inhibitors. We identified a signature that discriminates patients, which involves polyunsaturated fatty acids (PUFAs) and particularly the omega-3 fatty acids docosahexaenoate and eicosapentaenoate. The known cardiovascular benefits of PUFAs could contribute to the efficacy of ticagrelor. Our work, beyond pointing out the high relevance of untargeted metabolomics in evaluating response to treatment, establishes PUFA metabolism as a pathway of clinical interest in the recovery path from MI.