Approximating facial expression effects on diagnostic accuracy via generative AI in medical genetics.

Artificial intelligence (AI) is increasingly used in genomics research and practice, and generative AI has garnered significant recent attention. In clinical applications of generative AI, aspects of the underlying datasets can impact results, and confounders should be studied and mitigated. One example involves the facial expressions of people with genetic conditions. Stereotypically, Williams (WS) and Angelman (AS) syndromes are associated with a "happy" demeanor, including a smiling expression. Clinical geneticists may be more likely to identify these conditions in images of smiling individuals. To study the impact of facial expression, we analyzed publicly available facial images of approximately 3500 individuals with genetic conditions. Using a deep learning (DL) image classifier, we found that WS and AS images with non-smiling expressions had significantly lower prediction probabilities for the correct syndrome labels than those with smiling expressions. This was not seen for 22q11.2 deletion and Noonan syndromes, which are not associated with a smiling expression. To further explore the effect of facial expressions, we computationally altered the facial expressions for these images. We trained HyperStyle, a GAN-inversion technique compatible with StyleGAN2, to determine the vector representations of our images. Then, following the concept of InterfaceGAN, we edited these vectors to recreate the original images in a phenotypically accurate way but with a different facial expression. Through online surveys and an eye-tracking experiment, we examined how altered facial expressions affect the performance of human experts. We overall found that facial expression is associated with diagnostic accuracy variably in different genetic conditions.

Genebe.net: Implementation and validation of an automatic ACMG variant pathogenicity criteria assignment.

We present GeneBe, an online platform streamlining the automated application of American College of Medical Genetics and Genomics (ACMG), Association for Molecular Pathology (AMP), and the College of American Pathologists (CAP) criteria for assessment of pathogenicity of genetic variants. GeneBe utilizes automated algorithms that evaluate 17 criteria from 28, closely aligning with current guidelines and leveraging data from diverse sources, including ClinVar. The user-friendly web interface enables manual refinement of assignments for specific criteria based on site-collected data. Our algorithm demonstrates a high correlation (r = 0.90) of assigned pathogenicity scores compared to expert assessments from the ClinGen Evidence Repository and substantial concordance with ClinVar verdict assignments (κ = 0.69). Comparative analysis with other published tools reveals that GeneBe performs similarly to VarSome while being superior over TAPES and InterVar. In contrast to some other tools, GeneBe's web implementation is tracker-free and third-party request-free, safeguarding user privacy. Additionally, GeneBe offers an Application Programming Interface (API) for enhanced flexibility and integration into existing workflows and is provided free of charge for research purposes. GeneBe is available at https://genebe.net.

Detection of mobile elements insertions for routine clinical diagnostics in targeted sequencing data.

BACKGROUND: Targeted sequencing approaches such as gene panel or exome sequencing have become standard of care for the diagnosis of rare and common genetic disease. The detection and interpretation of point mutations, small insertions and deletions, and even exon-level copy number variants are well established in clinical genetic testing. Other types of genetic variation such as mobile elements insertions (MEIs) are technically difficult to detect. In addition, their downstream clinical interpretation is more complex compared to point mutations due to a larger genomic footprint that can not only predict a clear loss of protein function but might disturb gene regulation and splicing even when located within the non-coding regions. As a consequence, the contribution of MEIs to disease and tumor development remains largely unexplored in routine diagnostics. METHODS: In this study, we investigated the occurrence of MEIs in 7,693 exome datasets from individuals with rare diseases and healthy relatives as well as 788 cancer patients analyzed by panel sequencing. RESULTS: We present several exemplary cases highlighting the diagnostic value of MEIs and propose a strategy for the detection, prioritization, and clinical interpretation of MEIs in routine clinical diagnostics. CONCLUSION: In this paper, we state that detection and interpretation of MEIs in clinical practice in targeted NGS data can be performed relatively easy despite the fact that MEIs very rarely occur in coding parts of the human genome. Large scale reanalysis of MEIs in existing cohorts may solve otherwise unsolvable cases.

Opportunities and challenges for artificial intelligence in clinical cardiovascular genetics.

A combination of emerging genomic and artificial intelligence (AI) techniques may ultimately unlock a deeper understanding of heterogeneity and biological complexities in cardiovascular diseases (CVDs), leading to advances in prognostic guidance and personalized therapies. We discuss the state of AI in cardiovascular genetics, current applications, limitations, and future directions of the field.

Partners in care.

This festschrift contribution, written for my colleague and mentor John Graham, reflects on geneticist-genetic counselor interactions in clinical care, samples of alternative models of care for pediatric and general genetic counselors, and avenues for expanding access to genetic healthcare services utilizing genetic counselors.

Pediatric medical genetics house call: Telemedicine for the next generation of patients and providers.

In an era of increasing technology and interaction with the patient bedside, we explore the role of relocating the bedside from the hospital to the home using telemedicine. The COVID-19 pandemic pushed telemedicine from small and pilot programs to widespread practice at an unprecedented rate. With the rapid implementation of telemedicine, it is important to consider how to create a telehealth system that provides both good care for patients and families while maintaining an excellent education environment for trainees of all levels. To this end, we developed telemedicine educational milestones to describe novel skills required to provide high quality telemedicine care, and allow trainees and clinical educators a metric by which to assess trainee progress. We also created methods and tools to help trainees learn and families feel comfortable in their new role as virtual collaborators. We envision a time when safety does not set the venue; instead the needs of the patient will dictate whether a virtual or in-person visit is the right choice for a family. We expect that pediatric medical genetics and metabolism groups across the country will continue to set a standard of a hybrid care system to meet the unique needs of each individual patient, using telemedicine technology.

Variant Classification Concordance using the ACMG-AMP Variant Interpretation Guidelines across Nine Genomic Implementation Research Studies.

Harmonization of variant pathogenicity classification across laboratories is important for advancing clinical genomics. The two CLIA-accredited Electronic Medical Record and Genomics Network sequencing centers and the six CLIA-accredited laboratories and one research laboratory performing genome or exome sequencing in the Clinical Sequencing Evidence-Generating Research Consortium collaborated to explore current sources of discordance in classification. Eight laboratories each submitted 20 classified variants in the ACMG secondary finding v.2.0 genes. After removing duplicates, each of the 158 variants was annotated and independently classified by two additional laboratories using the ACMG-AMP guidelines. Overall concordance across three laboratories was assessed and discordant variants were reviewed via teleconference and email. The submitted variant set included 28 P/LP variants, 96 VUS, and 34 LB/B variants, mostly in cancer (40%) and cardiac (27%) risk genes. Eighty-six (54%) variants reached complete five-category (i.e., P, LP, VUS, LB, B) concordance, and 17 (11%) had a discordance that could affect clinical recommendations (P/LP versus VUS/LB/B). 21% and 63% of variants submitted as P and LP, respectively, were discordant with VUS. Of the 54 originally discordant variants that underwent further review, 32 reached agreement, for a post-review concordance rate of 84% (118/140 variants). This project provides an updated estimate of variant concordance, identifies considerations for LP classified variants, and highlights ongoing sources of discordance. Continued and increased sharing of variant classifications and evidence across laboratories, and the ongoing work of ClinGen to provide general as well as gene- and disease-specific guidance, will lead to continued increases in concordance.

Bioinformatics Methods in Medical Genetics and Genomics.

Medical genomics relies on next-gen sequencing methods to decipher underlying molecular mechanisms of gene expression. This special issue collects materials originally presented at the "Centenary of Human Population Genetics" Conference-2019, in Moscow. Here we present some recent developments in computational methods tested on actual medical genetics problems dissected through genomics, transcriptomics and proteomics data analysis, gene networks, protein-protein interactions and biomedical literature mining. We have selected materials based on systems biology approaches, database mining. These methods and algorithms were discussed at the Digital Medical Forum-2019, organized by I.M. Sechenov First Moscow State Medical University presenting bioinformatics approaches for the drug targets discovery in cancer, its computational support, and digitalization of medical research, as well as at "Systems Biology and Bioinformatics"-2019 (SBB-2019) Young Scientists School in Novosibirsk, Russia. Selected recent advancements discussed at these events in the medical genomics and genetics areas are based on novel bioinformatics tools.

Genetic counseling during COVID-19 pandemic: Tuscany experience.

BACKGROUND: COVID-19 outbreak prompted health centres to reorganize their clinical and surgical activity. In this paper, we show how medical genetics department's activity, in our tertiary pediatric hospital, has changed due to pandemic. METHODS: We stratified all our scheduled visits, from March 9th through April 30th, and assessed case-by-case which genetic consultations should be maintained as face-to-face visit, or postponed/switched to telemedicine. RESULTS: Out of 288 scheduled appointments, 60 were prenatal consultations and 228 were postnatal visits. We performed most of prenatal consultations as face-to-face visits, as women would have been present in the hospital to perform other procedures in addition to our consult. As for postnatal care, we suspended all outpatient first visits and opted for telemedicine for selected follow-up consultations: interestingly, 75% of our patients' parents revealed that they would have cancelled the appointment themselves for the fear to contract an infection. CONCLUSIONS: Spread of COVID-19 in Italy forced us to change our working habits. Given the necessity to optimize healthcare resources and minimize the risk of in-hospital infections, we experienced the benefits of telegenetics. Current pandemic made us familiar with telemedicine, laying the foundations for its application to deal with the increasing number of requests in clinical genetics.

Prediction of age at onset in Parkinson's disease using objective specific neuroimaging genetics based on a sparse canonical correlation analysis.

The age at onset (AAO) is an important determinant in Parkinson's disease (PD). Neuroimaging genetics is suitable for studying AAO in PD as it jointly analyzes imaging and genetics. We aimed to identify features associated with AAO in PD by applying the objective-specific neuroimaging genetics approach and constructing an AAO prediction model. Our objective-specific neuroimaging genetics extended the sparse canonical correlation analysis by an additional data type related to the target task to investigate possible associations of the imaging-genetic, genetic-target, and imaging-target pairs simultaneously. The identified imaging, genetic, and combined features were used to construct analytical models to predict the AAO in a nested five-fold cross-validation. We compared our approach with those from two feature selection approaches where only associations of imaging-target and genetic-target were explored. Using only imaging features, AAO prediction was accurate in all methods. Using only genetic features, the results from other methods were worse or unstable compared to our model. Using both imaging and genetic features, our proposed model predicted the AAO well (r = 0.5486). Our findings could have significant impacts on the characterization of prodromal PD and contribute to diagnosing PD early because genetic features could be measured accurately from birth.

Twin Research in the Post-Genomic Era: Dissecting the Pathophysiological Effects of Adversity and the Social Environment.

The role of twins in research is evolving as we move further into the post-genomic era. With the re-definition of what a gene is, it is becoming clear that biological family members who share a specific genetic variant may well not have a similar risk for future disease. This has somewhat invalidated the prior rationale for twin studies. Case co-twin study designs, however, are slowly emerging as the ideal tool to identify both environmentally induced epigenetic marks and epigenetic disease-associated processes. Here, we propose that twin lives are not as identical as commonly assumed and that the case co-twin study design can be used to investigate the effects of the adult social environment. We present the elements in the (social) environment that are likely to affect the epigenome and measures in which twins may diverge. Using data from the German TwinLife registry, we confirm divergence in both the events that occur and the salience for the individual start as early as age 11. Case co-twin studies allow for the exploitation of these divergences, permitting the investigation of the role of not only the adult social environment, but also the salience of an event or environment for the individual, in determining lifelong health trajectories. In cases like social adversity where it is clearly not possible to perform a randomised-controlled trial, we propose that the case co-twin study design is the most rigorous manner with which to investigate epigenetic mechanisms encoding environmental exposure. The role of the case co-twin design will continue to evolve, as we argue that it will permit causal inference from observational data.

Human accelerated genome regions with value in medical genetics and drug discovery.

Accumulated evolutionary knowledge not only benefits our understanding of the pathogenesis of diseases, but also help in the search for new drug targets. This is further supported by the recent finding that human accelerated regions (HARs) identified by comparative genomic studies are linked to human neural system evolution and are also associated with neurological disorders. Here, we analyze the associations between HARs and diseases and drugs. We found that 32.42% of approved drugs target at least one HAR gene, which is higher than the ratio of in-research drugs. More interestingly, HAR gene-targeted drugs are most significantly enriched with agents treating neurological disorders. Thus, HAR genes have important implications in medical genetics and drug discovery.

Dysmorphology in a Genomic Era.

Dysmorphology is the practice of defining the morphologic phenotype of syndromic disorders. Genomic sequencing has advanced our understanding of human variation and molecular dysmorphology has evolved in response to the science of relating embryologic developmental implications of abnormal gene signaling pathways to the resultant phenotypic presentation. Machine learning has enabled the application of deep convoluted neural networks to recognize the comparative likeness of these phenotypes relative to the causal genotype or disrupted gene pathway.

Leveraging Human Genetics to Identify Potential New Treatments for Fatty Liver Disease.

Fatty liver disease (FLD), including its more severe pathologies, namely steatohepatitis, hepatocarcinoma, and cirrhosis, is the most common cause of chronic liver disease worldwide and is projected to become the leading cause of hepatocellular carcinoma and end-stage liver disease. FLD is heterogeneous with multiple etiologies and diverse histological phenotypes, so therapies will ultimately need to be individualized for relevant targets. Inherited factors contribute to FLD, and most of the genetic variation influencing liver disease development and progression is derived from genes involved in lipid biology, including PNPLA3, TM6SF2, GCKR, MBOAT7, and HSD17B13. From this point of view, we focus in this perspective on how human molecular genetics of FLD have highlighted defects in hepatic lipid handling as a major common mechanism of its pathology and how this insight could be leveraged to treat and prevent its more serious complications.

Qualifying and quantifying the precision medicine rhetoric.

BACKGROUND: With the rise of precision medicine efforts worldwide, our study objective was to describe and map the emerging precision medicine landscape. A Google search was conducted between June 19, 2017 to July 20, 2017 to examine how "precision medicine" and its analogous terminology were used to describe precision medicine efforts. Resulting web-pages were reviewed for geographic location, data type(s), program aim(s), sample size, duration, and the key search terms used and recorded in a database. Descriptive statistics were applied to quantify terminology used to describe specific precision medicine efforts. Qualitative data were analyzed for content and patterns. RESULTS: Of the 108 programs identified through our search, 84% collected only biospecimen(s) and, of those that collected at least two data types, 42% mentioned both Electronic Health Records (EHR) and biospecimen. Given the majority of efforts limited to biospecimen(s) use, genetic research seems to be prioritized in association with precision medicine. Roughly, 54% were found to collect two or more data types, which limits the output of information that may contribute to understanding of the interplay of genetic, lifestyle, and environmental factors. Over half were government-funded with roughly a third being industry-funded. Most initiatives were concentrated in the United States, Europe, and Asia. CONCLUSIONS: To our knowledge, this is the first study to map and qualify the global precision medicine landscape. Our findings reveal that precision medicine efforts range from large model cohort studies involving multidimensional, longitudinal data to biorepositories with a collection of blood samples. We present a spectrum where past, present, and future PM-like efforts can fall based on their scope and potential impact. If precision medicine is based on genes, lifestyle and environmental factors, we recommend programs claiming to be precision medicine initiatives to incorporate multidimensional data that can inform a holistic approach to healthcare.

Artificial intelligence in clinical and genomic diagnostics.

Artificial intelligence (AI) is the development of computer systems that are able to perform tasks that normally require human intelligence. Advances in AI software and hardware, especially deep learning algorithms and the graphics processing units (GPUs) that power their training, have led to a recent and rapidly increasing interest in medical AI applications. In clinical diagnostics, AI-based computer vision approaches are poised to revolutionize image-based diagnostics, while other AI subtypes have begun to show similar promise in various diagnostic modalities. In some areas, such as clinical genomics, a specific type of AI algorithm known as deep learning is used to process large and complex genomic datasets. In this review, we first summarize the main classes of problems that AI systems are well suited to solve and describe the clinical diagnostic tasks that benefit from these solutions. Next, we focus on emerging methods for specific tasks in clinical genomics, including variant calling, genome annotation and variant classification, and phenotype-to-genotype correspondence. Finally, we end with a discussion on the future potential of AI in individualized medicine applications, especially for risk prediction in common complex diseases, and the challenges, limitations, and biases that must be carefully addressed for the successful deployment of AI in medical applications, particularly those utilizing human genetics and genomics data.