Addressing 6 challenges in generative AI for digital health: A scoping review.

Generative artificial intelligence (AI) can exhibit biases, compromise data privacy, misinterpret prompts that are adversarial attacks, and produce hallucinations. Despite the potential of generative AI for many applications in digital health, practitioners must understand these tools and their limitations. This scoping review pays particular attention to the challenges with generative AI technologies in medical settings and surveys potential solutions. Using PubMed, we identified a total of 120 articles published by March 2024, which reference and evaluate generative AI in medicine, from which we synthesized themes and suggestions for future work. After first discussing general background on generative AI, we focus on collecting and presenting 6 challenges key for digital health practitioners and specific measures that can be taken to mitigate these challenges. Overall, bias, privacy, hallucination, and regulatory compliance were frequently considered, while other concerns around generative AI, such as overreliance on text models, adversarial misprompting, and jailbreaking, are not commonly evaluated in the current literature.

SCGB1D2 inhibits growth of Borrelia burgdorferi and affects susceptibility to Lyme disease.

Lyme disease is a tick-borne disease caused by bacteria of the genus Borrelia. The host factors that modulate susceptibility for Lyme disease have remained mostly unknown. Using epidemiological and genetic data from FinnGen and Estonian Biobank, we identify two previously known variants and an unknown common missense variant at the gene encoding for Secretoglobin family 1D member 2 (SCGB1D2) protein that increases the susceptibility for Lyme disease. Using live Borrelia burgdorferi (Bb) we find that recombinant reference SCGB1D2 protein inhibits the growth of Bb in vitro more efficiently than the recombinant protein with SCGB1D2 P53L deleterious missense variant. Finally, using an in vivo murine infection model we show that recombinant SCGB1D2 prevents infection by Borrelia in vivo. Together, these data suggest that SCGB1D2 is a host defense factor present in the skin, sweat, and other secretions which protects against Bb infection and opens an exciting therapeutic avenue for Lyme disease.

Nightmares share genetic risk factors with sleep and psychiatric traits.

Nightmares are vivid, extended, and emotionally negative or negative dreams that awaken the dreamer. While sporadic nightmares and bad dreams are common and generally harmless, frequent nightmares often reflect underlying pathologies of emotional regulation. Indeed, insomnia, depression, anxiety, or alcohol use have been associated with nightmares in epidemiological and clinical studies. However, the connection between nightmares and their comorbidities are poorly understood. Our goal was to examine the genetic risk factors for nightmares and estimate correlation or causality between nightmares and comorbidities. We performed a genome-wide association study (GWAS) in 45,255 individuals using a questionnaire-based assessment on the frequency of nightmares during the past month and genome-wide genotyping data. While the GWAS did not reveal individual risk variants, heritability was estimated at 5%. In addition, the genetic correlation analysis showed a robust correlation (rg > 0.4) of nightmares with anxiety (rg = 0.671, p = 7.507e-06), depressive (rg = 0.562, p = 1.282e-07) and posttraumatic stress disorders (rg = 0.4083, p = 0.0152), and personality trait neuroticism (rg = 0.667, p = 4.516e-07). Furthermore, Mendelian randomization suggested causality from insomnia to nightmares (beta = 0.027, p = 0.0002). Our findings suggest that nightmares share genetic background with psychiatric traits and that insomnia may increase an individual's liability to experience frequent nightmares. Given the significant correlations with psychiatric and psychological traits, it is essential to grow awareness of how nightmares affect health and disease and systematically collect information about nightmares, especially from clinical samples and larger cohorts.

SIRPα controls CD47-dependent platelet clearance in mice and humans.

Over the last decade, more data has revealed that increased surface expression of the "don't eat me" CD47 protein on cancer cells plays a role in immune evasion and tumor progression, with CD47 blockade emerging as a new therapy in immuno-oncology. CD47 is critical in regulating cell homeostasis and clearance, as binding of CD47 to the inhibitory receptor SIRPα can prevent phagocytosis and macrophage-mediated cell clearance. The purpose of this study was to examine the role of the CD47-SIRPα signal in platelet homeostasis and clearance. Therapeutic reagents targeting the CD47-SIRPα axis are very promising for treatment of hematologic malignancies and solid tumors, but lead to transient anemia or thrombocytopenia in a subset of patients. We found that platelet homeostatic clearance is regulated through the CD47-SIRPα axis and that therapeutic blockade to disrupt this interaction in mice and in humans has a significant impact on platelet levels. Furthermore, we identified genetic variations at the SIRPA locus that impact platelet levels in humans such that higher SIRPA gene expression is associated with higher platelet levels. SIRPA expression at either end of the normal range may affect clinical outcomes of treatment with anti-CD47 therapy.

Metabolomic epidemiology offers insights into disease aetiology.

Metabolomic epidemiology is the high-throughput study of the relationship between metabolites and health-related traits. This emerging and rapidly growing field has improved our understanding of disease aetiology and contributed to advances in precision medicine. As the field continues to develop, metabolomic epidemiology could lead to the discovery of diagnostic biomarkers predictive of disease risk, aiding in earlier disease detection and better prognosis. In this Review, we discuss key advances facilitated by the field of metabolomic epidemiology for a range of conditions, including cardiometabolic diseases, cancer, Alzheimer's disease and COVID-19, with a focus on potential clinical utility. Core principles in metabolomic epidemiology, including study design, causal inference methods and multi-omic integration, are briefly discussed. Future directions required for clinical translation of metabolomic epidemiology findings are summarized, emphasizing public health implications. Further work is needed to establish which metabolites reproducibly improve clinical risk prediction in diverse populations and are causally related to disease progression.

Discovering cellular programs of intrinsic and extrinsic drivers of metabolic traits using LipocyteProfiler.

A primary obstacle in translating genetic associations with disease into therapeutic strategies is elucidating the cellular programs affected by genetic risk variants and effector genes. Here, we introduce LipocyteProfiler, a cardiometabolic-disease-oriented high-content image-based profiling tool that enables evaluation of thousands of morphological and cellular profiles that can be systematically linked to genes and genetic variants relevant to cardiometabolic disease. We show that LipocyteProfiler allows surveillance of diverse cellular programs by generating rich context- and process-specific cellular profiles across hepatocyte and adipocyte cell-state transitions. We use LipocyteProfiler to identify known and novel cellular mechanisms altered by polygenic risk of metabolic disease, including insulin resistance, fat distribution, and the polygenic contribution to lipodystrophy. LipocyteProfiler paves the way for large-scale forward and reverse deep phenotypic profiling in lipocytes and provides a framework for the unbiased identification of causal relationships between genetic variants and cellular programs relevant to human disease.

An epidemiological introduction to human metabolomic investigations.

Metabolomics holds great promise for uncovering insights around biological processes impacting disease in human epidemiological studies. Metabolites can be measured across biological samples, including plasma, serum, saliva, urine, stool, and whole organs and tissues, offering a means to characterize metabolic processes relevant to disease etiology and traits of interest. Metabolomic epidemiology studies face unique challenges, such as identifying metabolites from targeted and untargeted assays, defining standards for quality control, harmonizing results across platforms that often capture different metabolites, and developing statistical methods for high-dimensional and correlated metabolomic data. In this review, we introduce metabolomic epidemiology to the broader scientific community, discuss opportunities and challenges presented by these studies, and highlight emerging innovations that hold promise to uncover new biological insights.

Narcolepsy risk loci outline role of T cell autoimmunity and infectious triggers in narcolepsy.

Narcolepsy type 1 (NT1) is caused by a loss of hypocretin/orexin transmission. Risk factors include pandemic 2009 H1N1 influenza A infection and immunization with Pandemrix®. Here, we dissect disease mechanisms and interactions with environmental triggers in a multi-ethnic sample of 6,073 cases and 84,856 controls. We fine-mapped GWAS signals within HLA (DQ0602, DQB1*03:01 and DPB1*04:02) and discovered seven novel associations (CD207, NAB1, IKZF4-ERBB3, CTSC, DENND1B, SIRPG, PRF1). Significant signals at TRA and DQB1*06:02 loci were found in 245 vaccination-related cases, who also shared polygenic risk. T cell receptor associations in NT1 modulated TRAJ*24, TRAJ*28 and TRBV*4-2 chain-usage. Partitioned heritability and immune cell enrichment analyses found genetic signals to be driven by dendritic and helper T cells. Lastly comorbidity analysis using data from FinnGen, suggests shared effects between NT1 and other autoimmune diseases. NT1 genetic variants shape autoimmunity and response to environmental triggers, including influenza A infection and immunization with Pandemrix®.

A non-coding variant linked to metabolic obesity with normal weight affects actin remodelling in subcutaneous adipocytes.

Recent large-scale genomic association studies found evidence for a genetic link between increased risk of type 2 diabetes and decreased risk for adiposity-related traits, reminiscent of metabolically obese normal weight (MONW) association signatures. However, the target genes and cellular mechanisms driving such MONW associations remain to be identified. Here, we systematically identify the cellular programmes of one of the top-scoring MONW risk loci, the 2q24.3 risk locus, in subcutaneous adipocytes. We identify a causal genetic variant, rs6712203, an intronic single-nucleotide polymorphism in the COBLL1 gene, which changes the conserved transcription factor motif of POU domain, class 2, transcription factor 2, and leads to differential COBLL1 gene expression by altering the enhancer activity at the locus in subcutaneous adipocytes. We then establish the cellular programme under the genetic control of the 2q24.3 MONW risk locus and the effector gene COBLL1, which is characterized by impaired actin cytoskeleton remodelling in differentiating subcutaneous adipocytes and subsequent failure of these cells to accumulate lipids and develop into metabolically active and insulin-sensitive adipocytes. Finally, we show that perturbations of the effector gene Cobll1 in a mouse model result in organismal phenotypes matching the MONW association signature, including decreased subcutaneous body fat mass and body weight along with impaired glucose tolerance. Taken together, our results provide a mechanistic link between the genetic risk for insulin resistance and low adiposity, providing a potential therapeutic hypothesis and a framework for future identification of causal relationships between genome associations and cellular programmes in other disorders.

Diversity of ribosomes at the level of rRNA variation associated with human health and disease.

With hundreds of copies of ribosomal DNA (rDNA) it is unknown whether they possess sequence variations that ultimately form different types of ribosomes. Here, we developed an algorithm for variant-calling between paralog genes (termed RGA) and compared rDNA variations with rRNA variations from long-read sequencing of translating ribosomes (RIBO-RT). Our analyses identified dozens of highly abundant rRNA variants, largely indels, that are incorporated into translationally active ribosomes and assemble into distinct ribosome subtypes encoded on different chromosomes. We developed an in-situ rRNA sequencing method (SWITCH-seq) revealing that variants are co-expressed within individual cells and found that they possess different structures. Lastly, we observed tissue-specific rRNA-subtype expression and linked specific rRNA variants to cancer. This study therefore reveals the variation landscape of translating ribosomes within human cells.

Integrative analysis of metabolite GWAS illuminates the molecular basis of pleiotropy and genetic correlation.

Pleiotropy and genetic correlation are widespread features in genome-wide association studies (GWAS), but they are often difficult to interpret at the molecular level. Here, we perform GWAS of 16 metabolites clustered at the intersection of amino acid catabolism, glycolysis, and ketone body metabolism in a subset of UK Biobank. We utilize the well-documented biochemistry jointly impacting these metabolites to analyze pleiotropic effects in the context of their pathways. Among the 213 lead GWAS hits, we find a strong enrichment for genes encoding pathway-relevant enzymes and transporters. We demonstrate that the effect directions of variants acting on biology between metabolite pairs often contrast with those of upstream or downstream variants as well as the polygenic background. Thus, we find that these outlier variants often reflect biology local to the traits. Finally, we explore the implications for interpreting disease GWAS, underscoring the potential of unifying biochemistry with dense metabolomics data to understand the molecular basis of pleiotropy in complex traits and diseases.

Large-scale genome-wide association study of coronary artery disease in genetically diverse populations.

We report a genome-wide association study (GWAS) of coronary artery disease (CAD) incorporating nearly a quarter of a million cases, in which existing studies are integrated with data from cohorts of white, Black and Hispanic individuals from the Million Veteran Program. We document near equivalent heritability of CAD across multiple ancestral groups, identify 95 novel loci, including nine on the X chromosome, detect eight loci of genome-wide significance in Black and Hispanic individuals, and demonstrate that two common haplotypes at the 9p21 locus are responsible for risk stratification in all populations except those of African origin, in which these haplotypes are virtually absent. Moreover, in the largest GWAS for angiographically derived coronary atherosclerosis performed to date, we find 15 loci of genome-wide significance that robustly overlap with established loci for clinical CAD. Phenome-wide association analyses of novel loci and polygenic risk scores (PRSs) augment signals related to insulin resistance, extend pleiotropic associations of these loci to include smoking and family history, and precisely document the markedly reduced transferability of existing PRSs to Black individuals. Downstream integrative analyses reinforce the critical roles of vascular endothelial, fibroblast, and smooth muscle cells in CAD susceptibility, but also point to a shared biology between atherosclerosis and oncogenesis. This study highlights the value of diverse populations in further characterizing the genetic architecture of CAD.

Systematic discovery and perturbation of regulatory genes in human T cells reveals the architecture of immune networks.

Gene regulatory networks ensure that important genes are expressed at precise levels. When gene expression is sufficiently perturbed, it can lead to disease. To understand how gene expression disruptions percolate through a network, we must first map connections between regulatory genes and their downstream targets. However, we lack comprehensive knowledge of the upstream regulators of most genes. Here, we developed an approach for systematic discovery of upstream regulators of critical immune factors-IL2RA, IL-2 and CTLA4-in primary human T cells. Then, we mapped the network of the target genes of these regulators and putative cis-regulatory elements using CRISPR perturbations, RNA-seq and ATAC-seq. These regulators form densely interconnected networks with extensive feedback loops. Furthermore, this network is enriched for immune-associated disease variants and genes. These results provide insight into how immune-associated disease genes are regulated in T cells and broader principles about the structure of human gene regulatory networks.

Genetic interactions drive heterogeneity in causal variant effect sizes for gene expression and complex traits.

Despite the growing number of genome-wide association studies (GWASs), it remains unclear to what extent gene-by-gene and gene-by-environment interactions influence complex traits in humans. The magnitude of genetic interactions in complex traits has been difficult to quantify because GWASs are generally underpowered to detect individual interactions of small effect. Here, we develop a method to test for genetic interactions that aggregates information across all trait-associated loci. Specifically, we test whether SNPs in regions of European ancestry shared between European American and admixed African American individuals have the same causal effect sizes. We hypothesize that in African Americans, the presence of genetic interactions will drive the causal effect sizes of SNPs in regions of European ancestry to be more similar to those of SNPs in regions of African ancestry. We apply our method to two traits: gene expression in 296 African Americans and 482 European Americans in the Multi-Ethnic Study of Atherosclerosis (MESA) and low-density lipoprotein cholesterol (LDL-C) in 74K African Americans and 296K European Americans in the Million Veteran Program (MVP). We find significant evidence for genetic interactions in our analysis of gene expression; for LDL-C, we observe a similar point estimate, although this is not significant, most likely due to lower statistical power. These results suggest that gene-by-gene or gene-by-environment interactions modify the effect sizes of causal variants in human complex traits.

A conserved YAP/Notch/REST network controls the neuroendocrine cell fate in the lungs.

The Notch pathway is a conserved cell-cell communication pathway that controls cell fate decisions. Here we sought to determine how Notch pathway activation inhibits the neuroendocrine cell fate in the lungs, an archetypal process for cell fate decisions orchestrated by Notch signaling that has remained poorly understood at the molecular level. Using intratumoral heterogeneity in small-cell lung cancer as a tractable model system, we uncovered a role for the transcriptional regulators REST and YAP as promoters of the neuroendocrine to non-neuroendocrine transition. We further identified the specific neuroendocrine gene programs repressed by REST downstream of Notch in this process. Importantly, we validated the importance of REST and YAP in neuroendocrine to non-neuroendocrine cell fate switches in both developmental and tissue repair processes in the lungs. Altogether, these experiments identify conserved roles for REST and YAP in Notch-driven inhibition of the neuroendocrine cell fate in embryonic lungs, adult lungs, and lung cancer.

Portability of Polygenic Risk Scores for Sleep Duration, Insomnia and Chronotype in 33,493 Individuals.

Polygenic risk scores (PRSs) estimate genetic liability for diseases and traits. However, the portability of PRSs in sleep traits has remained elusive. We generated PRSs for self-reported insomnia, chronotype and sleep duration using summary data from genome-wide association studies (GWASs) performed in 350,000 to 697,000 European-ancestry individuals. We then projected the scores in two independent Finnish population cohorts (N = 33,493) and tested whether the PRSs were associated with their respective sleep traits. We observed that all the generated PRSs were associated with their corresponding traits (p < 0.05 in all cases). Furthermore, we found that there was a 22.2 min difference in reported sleep between the 5% tails of the PRS for sleep duration (p < 0.001). Our findings indicate that sleep-related PRSs show portability across cohorts. The findings also demonstrate that sleep measures using PRSs for sleep behaviors may provide useful instruments for testing disease and trait associations in cohorts where direct sleep parameters have not yet been measured.

Extensive pleiotropism and allelic heterogeneity mediate metabolic effects of IRX3 and IRX5.

Whereas coding variants often have pleiotropic effects across multiple tissues, noncoding variants are thought to mediate their phenotypic effects by specific tissue and temporal regulation of gene expression. Here, we investigated the genetic and functional architecture of a genomic region within the FTO gene that is strongly associated with obesity risk. We show that multiple variants on a common haplotype modify the regulatory properties of several enhancers targeting IRX3 and IRX5 from megabase distances. We demonstrate that these enhancers affect gene expression in multiple tissues, including adipose and brain, and impart regulatory effects during a restricted temporal window. Our data indicate that the genetic architecture of disease-associated loci may involve extensive pleiotropy, allelic heterogeneity, shared allelic effects across tissues, and temporally restricted effects.

A genome-wide atlas of co-essential modules assigns function to uncharacterized genes.

A central question in the post-genomic era is how genes interact to form biological pathways. Measurements of gene dependency across hundreds of cell lines have been used to cluster genes into 'co-essential' pathways, but this approach has been limited by ubiquitous false positives. In the present study, we develop a statistical method that enables robust identification of gene co-essentiality and yields a genome-wide set of functional modules. This atlas recapitulates diverse pathways and protein complexes, and predicts the functions of 108 uncharacterized genes. Validating top predictions, we show that TMEM189 encodes plasmanylethanolamine desaturase, a key enzyme for plasmalogen synthesis. We also show that C15orf57 encodes a protein that binds the AP2 complex, localizes to clathrin-coated pits and enables efficient transferrin uptake. Finally, we provide an interactive webtool for the community to explore our results, which establish co-essentiality profiling as a powerful resource for biological pathway identification and discovery of new gene functions.