Technological readiness and implementation of genomic-driven precision medicine for complex diseases

AI-enabled clinical decision support tools for mental healthcare: A product review

The review seeks to promote transparency in the availability of regulated AI-enabled Clinical Decision Support Systems (AI-CDSS) for mental healthcare. From 84 potential products, seven fulfilled the inclusion criteria. The products can be categorized into three major areas: diagnosis of autism spectrum disorder (ASD) based on clinical history, behavioral, and eye-tracking data; diagnosis of multiple disorders based on conversational data; and medication selection based on clinical history and genetic data. We found five scientific articles evaluating the devices' performance and external validity. The average completeness of reporting, indicated by 52 % adherence to the Consolidated Standards of Reporting Trials Artificial Intelligence (CONSORT-AI) checklist, was modest, signaling room for improvement in reporting quality. Our findings stress the importance of obtaining regulatory approval, adhering to scientific standards, and staying up-to-date with the latest changes in the regulatory landscape. Refining regulatory guidelines and implementing effective tracking systems for AI-CDSS could enhance transparency and oversight in the field.

Latent space arithmetic on data embeddings from healthy multi-tissue human RNA-seq decodes disease modules

Computational analyses of transcriptomic data have dramatically improved our understanding of complex diseases. However, such approaches are limited by small sample sets of disease-affected material. We asked if a variational autoencoder trained on large groups of healthy human RNA sequencing (RNA-seq) data can capture the fundamental gene regulation system and generalize to unseen disease changes. Importantly, we found this model to successfully compress unseen transcriptomic changes from 25 independent disease datasets. We decoded disease-specific signals from the latent space and found them to contain more disease-specific genes than the corresponding differential expression analysis in 20 of 25 cases. Finally, we matched these disease signals with known drug targets and extracted sets of known and potential pharmaceutical candidates. In summary, our study demonstrates how data-driven representation learning enables the arithmetic deconstruction of the latent space, facilitating the dissection of disease mechanisms and drug targets.

How Real-World Data Can Facilitate the Development of Precision Medicine Treatment in Psychiatry

Precision medicine has the ambition to improve treatment response and clinical outcomes through patient stratification and holds great potential for the treatment of mental disorders. However, several important factors are needed to transform current practice into a precision psychiatry framework. Most important are 1) the generation of accessible large real-world training and test data including genomic data integrated from multiple sources, 2) the development and validation of advanced analytical tools for stratification and prediction, and 3) the development of clinically useful management platforms for patient monitoring that can be integrated into health care systems in real-life settings. This narrative review summarizes strategies for obtaining the key elements-well-powered samples from large biobanks integrated with electronic health records and health registry data using novel artificial intelligence algorithms-to predict outcomes in severe mental disorders and translate these models into clinical management and treatment approaches. Key elements are massive mental health data and novel artificial intelligence algorithms. For the clinical translation of these strategies, we discuss a precision medicine platform for improved management of mental disorders. We use cases to illustrate how precision medicine interventions could be brought into psychiatry to improve the clinical outcomes of mental disorders.

Precision medicine for cardiometabolic disease: a framework for clinical translation

Cardiometabolic disease is a major threat to global health. Precision medicine has great potential to help to reduce the burden of this common and complex disease cluster, and to enhance contemporary evidence-based medicine. Its key pillars are diagnostics; prediction (of the primary disease); prevention (of the primary disease); prognosis (prediction of complications of the primary disease); treatment (of the primary disease or its complications); and monitoring (of risk exposure, treatment response, and disease progression or remission). To contextualise precision medicine in both research and clinical settings, and to encourage the successful translation of discovery science into clinical practice, in this Series paper we outline a model (the EPPOS model) that builds on contemporary evidence-based approaches; includes precision medicine that improves disease-related predictions by stratifying a cohort into subgroups of similar characteristics, or using participants' characteristics to model treatment outcomes directly; includes personalised medicine with the use of a person's data to objectively gauge the efficacy, safety, and tolerability of therapeutics; and subjectively tailors medical decisions to the individual's preferences, circumstances, and capabilities. Precision medicine requires a well functioning system comprised of multiple stakeholders, including health-care recipients, health-care providers, scientists, health economists, funders, innovators of medicines and technologies, regulators, and policy makers. Powerful computing infrastructures supporting appropriate analysis of large-scale, well curated, and accessible health databases that contain high-quality, multidimensional, time-series data will be required; so too will prospective cohort studies in diverse populations designed to generate novel hypotheses, and clinical trials designed to test them. Here, we carefully consider these topics and describe a framework for the integration of precision medicine in cardiometabolic disease.

Precision medicine in complex diseases-Molecular subgrouping for improved prediction and treatment stratification

Complex diseases are caused by a combination of genetic, lifestyle, and environmental factors and comprise common noncommunicable diseases, including allergies, cardiovascular disease, and psychiatric and metabolic disorders. More than 25% of Europeans suffer from a complex disease, and together these diseases account for 70% of all deaths. The use of genomic, molecular, or imaging data to develop accurate diagnostic tools for treatment recommendations and preventive strategies, and for disease prognosis and prediction, is an important step toward precision medicine. However, for complex diseases, precision medicine is associated with several challenges. There is a significant heterogeneity between patients of a specific disease-both with regards to symptoms and underlying causal mechanisms-and the number of underlying genetic and nongenetic risk factors is often high. Here, we summarize precision medicine approaches for complex diseases and highlight the current breakthroughs as well as the challenges. We conclude that genomic-based precision medicine has been used mainly for patients with highly penetrant monogenic disease forms, such as cardiomyopathies. However, for most complex diseases-including psychiatric disorders and allergies-available polygenic risk scores are more probabilistic than deterministic and have not yet been validated for clinical utility. However, subclassifying patients of a specific disease into discrete homogenous subtypes based on molecular or phenotypic data is a promising strategy for improving diagnosis, prediction, treatment, prevention, and prognosis. The availability of high-throughput molecular technologies, together with large collections of health data and novel data-driven approaches, offers promise toward improved individual health through precision medicine.

Second international consensus report on gaps and opportunities for the clinical translation of precision diabetes medicine

Precision medicine is part of the logical evolution of contemporary evidence-based medicine that seeks to reduce errors and optimize outcomes when making medical decisions and health recommendations. Diabetes affects hundreds of millions of people worldwide, many of whom will develop life-threatening complications and die prematurely. Precision medicine can potentially address this enormous problem by accounting for heterogeneity in the etiology, clinical presentation and pathogenesis of common forms of diabetes and risks of complications. This second international consensus report on precision diabetes medicine summarizes the findings from a systematic evidence review across the key pillars of precision medicine (prevention, diagnosis, treatment, prognosis) in four recognized forms of diabetes (monogenic, gestational, type 1, type 2). These reviews address key questions about the translation of precision medicine research into practice. Although not complete, owing to the vast literature on this topic, they revealed opportunities for the immediate or near-term clinical implementation of precision diabetes medicine; furthermore, we expose important gaps in knowledge, focusing on the need to obtain new clinically relevant evidence. Gaps include the need for common standards for clinical readiness, including consideration of cost-effectiveness, health equity, predictive accuracy, liability and accessibility. Key milestones are outlined for the broad clinical implementation of precision diabetes medicine.

Optimisation Models for Pathway Activity Inference in Cancer

BACKGROUND

With advances in high-throughput technologies, there has been an enormous increase in data related to profiling the activity of molecules in disease. While such data provide more comprehensive information on cellular actions, their large volume and complexity pose difficulty in accurate classification of disease phenotypes. Therefore, novel modelling methods that can improve accuracy while offering interpretable means of analysis are required. Biological pathways can be used to incorporate a priori knowledge of biological interactions to decrease data dimensionality and increase the biological interpretability of machine learning models.

METHODOLOGY

A mathematical optimisation model is proposed for pathway activity inference towards precise disease phenotype prediction and is applied to RNA-Seq datasets. The model is based on mixed-integer linear programming (MILP) mathematical optimisation principles and infers pathway activity as the linear combination of pathway member gene expression, multiplying expression values with model-determined gene weights that are optimised to maximise discrimination of phenotype classes and minimise incorrect sample allocation.

RESULTS

The model is evaluated on the transcriptome of breast and colorectal cancer, and exhibits solution results of good optimality as well as good prediction performance on related cancer subtypes. Two baseline pathway activity inference methods and three advanced methods are used for comparison. Sample prediction accuracy, robustness against noise expression data, and survival analysis suggest competitive prediction performance of our model while providing interpretability and insight on key pathways and genes. Overall, our work demonstrates that the flexible nature of mathematical programming lends itself well to developing efficient computational strategies for pathway activity inference and disease subtype prediction.

Building a precision medicine infrastructure at a national level: The Swedish experience

Precision medicine has the potential to transform healthcare by moving from one-size-fits-all to personalised treatment and care. This transition has been greatly facilitated through new high-throughput sequencing technologies that can provide the unique molecular profile of each individual patient, along with the rapid development of targeted therapies directed to the Achilles heels of each disease. To implement precision medicine approaches in healthcare, many countries have adopted national strategies and initiated genomic/precision medicine initiatives to provide equal access to all citizens. In other countries, such as Sweden, this has proven more difficult due to regionally organised healthcare. Using a bottom-up approach, key stakeholders from academia, healthcare, industry and patient organisations joined forces and formed Genomic Medicine Sweden (GMS), a national infrastructure for the implementation of precision medicine across the country. To achieve this, Genomic Medicine Centres have been established to provide regionally distributed genomic services, and a national informatics infrastructure has been built to allow secure data handling and sharing. GMS has a broad scope focusing on rare diseases, cancer, pharmacogenomics, infectious diseases and complex diseases, while also providing expertise in informatics, ethical and legal issues, health economy, industry collaboration and education. In this review, we summarise our experience in building a national infrastructure for precision medicine. We also provide key examples how precision medicine already has been successfully implemented within our focus areas. Finally, we bring up challenges and opportunities associated with precision medicine implementation, the importance of international collaboration, as well as the future perspective in the field of precision medicine.

Genetic testing for psychiatric illness in children: ethical issues

PURPOSE OF REVIEW

Genetic and genomic technologies are showing great potential in the field of psychiatry. Genetic testing for psychiatric conditions poses a range of ethical challenges, many of which are likely to be exacerbated for paediatric populations. As a large proportion of psychiatric conditions present in late adolescence and early adulthood, testing in childhood may be considered in some circumstances. Synthesis of issues specific to psychiatric genetic testing in paediatric populations has been limited.

RECENT FINDINGS

Balancing the autonomy of the child and parents requires consideration and judging capacity may be complicated by the presence of psychiatric illness in the child and their family. Health professionals' limited understanding of psychiatric genetics may inhibit delivery of effective psychiatric care. Risk of stigma and discrimination associated with genetic diagnosis and psychiatric illness is compounded for children, who inherently cannot make their own decisions and for whom the impact of a genetic diagnosis is likely to be longest lasting.

SUMMARY

Although the current evidence base suggests genetic testing may not be appropriate for clinical use in psychiatric populations right now, when it is, appropriate pre-test counselling and informed decision making will be essential to support and protect children's developing and future autonomy.

Polygenic risk scores of endo-phenotypes identify the effect of genetic background in congenital heart disease

Congenital heart disease (CHD) is a rare structural defect that occurs in ∼1% of live births. Studies on CHD genetic architecture have identified pathogenic single-gene mutations in less than 30% of cases. Single-gene mutations often show incomplete penetrance and variable expressivity. Therefore, we hypothesize that genetic background may play a role in modulating disease expression. Polygenic risk scores (PRSs) aggregate effects of common genetic variants to investigate whether, cumulatively, these variants are associated with disease penetrance or severity. However, the major limitations in this field have been in generating sufficient sample sizes for these studies. Here we used CHD-phenotype matched genome-wide association study (GWAS) summary statistics from the UK Biobank (UKBB) as our base study and whole-genome sequencing data from the CHD cohort (n1 = 711 trios, n2 = 362 European trios) of the Gabriella Miller Kids First dataset as our target study to develop PRSs for CHD. PRSs estimated using a GWAS for heart valve problems and heart murmur explain 2.5% of the variance in case-control status of CHD (all SNVs, p = 7.90 × 10-3; fetal cardiac SNVs, p = 8.00 × 10-3) and 1.8% of the variance in severity of CHD (fetal cardiac SNVs, p = 6.20 × 10-3; all SNVs, p = 0.015). These results show that common variants captured in CHD phenotype-matched GWASs have a modest but significant contribution to phenotypic expression of CHD. Further exploration of the cumulative effect of common variants is necessary for understanding the complex genetic etiology of CHD and other rare diseases.

A dynamic single cell-based framework for digital twins to prioritize disease genes and drug targets

BACKGROUND

Medical digital twins are computational disease models for drug discovery and treatment. Unresolved problems include how to organize and prioritize between disease-associated changes in digital twins, on cellulome- and genome-wide scales. We present a dynamic framework that can be used to model such changes and thereby prioritize upstream regulators (URs) for biomarker- and drug discovery.

METHODS

We started with seasonal allergic rhinitis (SAR) as a disease model, by analyses of in vitro allergen-stimulated peripheral blood mononuclear cells (PBMC) from SAR patients. Time-series a single-cell RNA-sequencing (scRNA-seq) data of these cells were used to construct multicellular network models (MNMs) at each time point of molecular interactions between cell types. We hypothesized that predicted molecular interactions between cell types in the MNMs could be traced to find an UR gene, at an early time point. We performed bioinformatic and functional studies of the MNMs to develop a scalable framework to prioritize UR genes. This framework was tested on a single-cell and bulk-profiling data from SAR and other inflammatory diseases.

RESULTS

Our scRNA-seq-based time-series MNMs of SAR showed thousands of differentially expressed genes (DEGs) across multiple cell types, which varied between time points. Instead of a single-UR gene in each MNM, we found multiple URs dispersed across the cell types. Thus, at each time point, the MNMs formed multi-directional networks. The absence of linear hierarchies and time-dependent variations in MNMs complicated the prioritization of URs. For example, the expression and functions of Th2 cytokines, which are approved drug targets in allergies, varied across cell types, and time points. Our analyses of bulk- and single-cell data from other inflammatory diseases also revealed multi-directional networks that showed stage-dependent variations. We therefore developed a quantitative approach to prioritize URs: we ranked the URs based on their predicted effects on downstream target cells. Experimental and bioinformatic analyses supported that this kind of ranking is a tractable approach for prioritizing URs.

CONCLUSIONS

We present a scalable framework for modeling dynamic changes in digital twins, on cellulome- and genome-wide scales, to prioritize UR genes for biomarker and drug discovery.

Proteomic Analysis of Whole Blood Using Volumetric Absorptive Microsampling for Precision Medicine Biomarker Studies

Microsampling of patient blood promises several benefits over conventional phlebotomy practices to facilitate precision medicine studies. These include at-home patient blood collection, supporting telehealth monitoring, minimal postcollection processing, and compatibility with nonrefrigerated transport and storage. However, for proteomic biomarker studies, mass spectrometry of whole blood has generally been avoided in favor of using plasma or serum obtained from venepuncture. We evaluated the use of a volumetric absorptive microsampling (VAMS) device as a sample preparation matrix to enable LC-MS proteomic analyses of dried whole blood. We demonstrated the detection and robust quantitation of up to 1600 proteins from single-shot shotgun-LC-MS analysis of dried whole blood, greatly enhancing proteome depth compared with conventional single-shot LC-MS analyses of undepleted plasma. Some proteins not previously reported in blood were detected using this approach. Various washing reagents were used to demonstrate that proteins can be preferentially removed from VAMS devices prior to downstream analyses. We provide a demonstration that archival frozen blood cell pellets housed under long-term storage (exceeding 5 years) are compatible with VAMS to enable quantitation of potential biomarker proteins from biobank repositories. These demonstrations are important steps in establishing viable analysis workflows to underpin large-scale precision medicine studies. Data are available via ProteomeXchange with the identifier PXD028605.

Guidelines for genetic testing of healthy adults who deposit samples and related data in bioresource collections and biobanks

Currently, a significant part of research in the fields of human and medical genetics is carried out using tissue samples, genealogical, population, medical and personal data. Their use is of particular relevance in the “genome era”, since only joint analysis of genomic data and health status of the population is crucial for understanding how genes are associated with health and disease. Genetic studies of adults without symptoms of diseases are carried out to obtain data on a possible predisposition to multifactorial diseases, to establish the carrier status of autosomal recessive mutations as part of preconception care and to assess individual sensitivity to drugs. In addition, healthy individuals can be tested to detect an inherited disease at presymptomatic stage. This situation increasingly emphasizes the importance of storing data on genome sequencing or any other patient tests for subsequent data reanalysis, as well as their safety, including biosamples from an individual and one’s family. The review article, based on international experience, summarizes guidelines for genetic testing of healthy individuals. The options for storing biological samples and related data are considered.