AI-MARRVEL - A Knowledge-Driven AI System for Diagnosing Mendelian Disorders.

BACKGROUND: Diagnosing genetic disorders requires extensive manual curation and interpretation of candidate variants, a labor-intensive task even for trained geneticists. Although artificial intelligence (AI) shows promise in aiding these diagnoses, existing AI tools have only achieved moderate success for primary diagnosis. METHODS: AI-MARRVEL (AIM) uses a random-forest machine-learning classifier trained on over 3.5 million variants from thousands of diagnosed cases. AIM additionally incorporates expert-engineered features into training to recapitulate the intricate decision-making processes in molecular diagnosis. The online version of AIM is available at https://ai.marrvel.org. To evaluate AIM, we benchmarked it with diagnosed patients from three independent cohorts. RESULTS: AIM improved the rate of accurate genetic diagnosis, doubling the number of solved cases as compared with benchmarked methods, across three distinct real-world cohorts. To better identify diagnosable cases from the unsolved pools accumulated over time, we designed a confidence metric on which AIM achieved a precision rate of 98% and identified 57% of diagnosable cases out of a collection of 871 cases. Furthermore, AIM's performance improved after being fine-tuned for targeted settings including recessive disorders and trio analysis. Finally, AIM demonstrated potential for novel disease gene discovery by correctly predicting two newly reported disease genes from the Undiagnosed Diseases Network. CONCLUSIONS: AIM achieved superior accuracy compared with existing methods for genetic diagnosis. We anticipate that this tool may aid in primary diagnosis, reanalysis of unsolved cases, and the discovery of novel disease genes. (Funded by the NIH Common Fund and others.).

Exploring the complexity of systemic sclerosis etiology by trio whole genome sequencing.

Systemic sclerosis (SSc) is a heterogeneous rare autoimmune fibrosing disorder affecting connective tissue. The etiology of systemic sclerosis is largely unknown and many genes have been suggested as susceptibility loci of modest impact by genome-wide association study (GWAS). Multiple factors can contribute to the pathological process of the disease, which makes it more difficult to identify possible disease-causing genetic alterations. In this study, we have applied whole genome sequencing (WGS) in 101 indexed family trios, supplemented with transcriptome sequencing on cultured fibroblast cells of four patients and five family controls where available. Single nucleotide variants (SNVs) and copy number variants (CNVs) were examined, with emphasis on de novo variants. We also performed enrichment test for rare variants in candidate genes previously proposed in association with systemic sclerosis. We identified 42 exonic and 34 ncRNA de novo SNV changes in 101 trios, from a total of over 6000 de novo variants genome wide. We observed higher than expected de novo variants in PRKXP1 gene. We also observed such phenomenon along with increased expression in patient group in NEK7 gene. Additionally, we also observed significant enrichment of rare variants in candidate genes in the patient cohort, further supporting the complexity/multi-factorial etiology of systemic sclerosis. Our findings identify new candidate genes including PRKXP1 and NEK7 for future studies in SSc. We observed rare variant enrichment in candidate genes previously proposed in association with SSc, which suggest more efforts should be pursued to further investigate possible pathogenetic mechanisms associated with those candidate genes.

The IFITM5 mutation in osteogenesis imperfecta type V is associated with an ERK/SOX9-dependent osteoprogenitor differentiation defect.

Osteogenesis imperfecta (OI) type V is the second most common form of OI, distinguished by hyperplastic callus formation and calcification of the interosseous membranes, in addition to the bone fragility. It is caused by a recurrent, dominant pathogenic variant (c.-14C>T) in interferon-induced transmembrane protein 5 (IFITM5). Here, we generated a conditional Rosa26-knockin mouse model to study the mechanistic consequences of the recurrent mutation. Expression of the mutant Ifitm5 in osteo-chondroprogenitor or chondrogenic cells resulted in low bone mass and growth retardation. Mutant limbs showed impaired endochondral ossification, cartilage overgrowth, and abnormal growth plate architecture. The cartilage phenotype correlates with the pathology reported in patients with OI type V. Surprisingly, expression of mutant Ifitm5 in mature osteoblasts caused no obvious skeletal abnormalities. In contrast, earlier expression in osteo-chondroprogenitors was associated with an increase in the skeletal progenitor cell population within the periosteum. Lineage tracing showed that chondrogenic cells expressing the mutant Ifitm5 had decreased differentiation into osteoblastic cells in diaphyseal bone. Moreover, mutant IFITM5 disrupted early skeletal homeostasis in part by activating ERK signaling and downstream SOX9 protein, and inhibition of these pathways partially rescued the phenotype in mutant animals. These data identify the contribution of a signaling defect altering osteo-chondroprogenitor differentiation as a driver in the pathogenesis of OI type V.

Resilience and coping: a qualitative analysis of cognitive and behavioral factors in adults with osteogenesis Imperfecta.

PURPOSE: The aim of this qualitative study was to investigate resilience among adults with Osteogenesis Imperfecta (OI). MATERIALS AND METHODS: Semi-structured interviews were conducted with 15 adults with OI. Transcripts were coded and subsequently abstracted, yielding themes specific to resilience and coping. Interview guides covered broad topics including pain challenges specific to OI, mental health issues related to OI, and priorities for future interventions for individuals with OI. RESULTS: Participants described resilience in the context of OI as the ability to grow from adversity, adapt to challenges resulting from OI-related injuries, and find identities apart from their condition. Psychological coping strategies included acceptance, self-efficacy, cognitive reframing, perspective-taking, and positivity. Behavioral factors that helped participants develop resilience included developing new skills, pursuing meaningful goals, practicing spirituality, and seeking external resources such as psychotherapy, education, and connection with community. CONCLUSION: Having identified how adults with OI define resilience and the strategies they use to cope, we can now develop interventions and guide healthcare providers in improving psychological wellbeing in this population.

Adults with Osteogenesis Imperfecta (OI) employ resilience factors to combat mobility and pain-related issues.Adults with OI report developing adaptive skills to cope with their disease, including forming one's identity outside of OI, growing through adversity, overcoming challenges resulting from OI-related injury, employing psychological adaptations, and practicing behavioral coping strategies.Resiliency factors such as behavioral and psychological coping (e.g., exercise, breathing strategies, acceptance) may buffer against OI-related challenges, and treatment modalities that foster these activities may be beneficial for adults with OI.

Machine learning in time-lapse imaging to differentiate embryos from young vs old mice†.

Time-lapse microscopy for embryos is a non-invasive technology used to characterize early embryo development. This study employs time-lapse microscopy and machine learning to elucidate changes in embryonic growth kinetics with maternal aging. We analyzed morphokinetic parameters of embryos from young and aged C57BL6/NJ mice via continuous imaging. Our findings show that aged embryos accelerated through cleavage stages (from 5-cells) to morula compared to younger counterparts, with no significant differences observed in later stages of blastulation. Unsupervised machine learning identified two distinct clusters comprising of embryos from aged or young donors. Moreover, in supervised learning, the extreme gradient boosting algorithm successfully predicted the age-related phenotype with 0.78 accuracy, 0.81 precision, and 0.83 recall following hyperparameter tuning. These results highlight two main scientific insights: maternal aging affects embryonic development pace, and artificial intelligence can differentiate between embryos from aged and young maternal mice by a non-invasive approach. Thus, machine learning can be used to identify morphokinetics phenotypes for further studies. This study has potential for future applications in selecting human embryos for embryo transfer, without or in complement with preimplantation genetic testing.

Genetic Evaluation for Monogenic Disorders of Low Bone Mass and Increased Bone Fragility: What Clinicians Need to Know.

PURPOSE OF REVIEW: The purpose of this review is to outline the principles of clinical genetic testing and to provide practical guidance to clinicians in navigating genetic testing for patients with suspected monogenic forms of osteoporosis. RECENT FINDINGS: Heritability assessments and genome-wide association studies have clearly shown the significant contributions of genetic variations to the pathogenesis of osteoporosis. Currently, over 50 monogenic disorders that present primarily with low bone mass and increased risk of fractures have been described. The widespread availability of clinical genetic testing offers a valuable opportunity to correctly diagnose individuals with monogenic forms of osteoporosis, thus instituting appropriate surveillance and treatment. Clinical genetic testing may identify the appropriate diagnosis in a subset of patients with low bone mass, multiple or unusual fractures, and severe or early-onset osteoporosis, and thus clinicians should be aware of how to incorporate such testing into their clinical practices.

The clinical utility and diagnostic implementation of human subject cell transdifferentiation followed by RNA sequencing.

RNA sequencing (RNA-seq) has recently been used in translational research settings to facilitate diagnoses of Mendelian disorders. A significant obstacle for clinical laboratories in adopting RNA-seq is the low or absent expression of a significant number of disease-associated genes/transcripts in clinically accessible samples. As this is especially problematic in neurological diseases, we developed a clinical diagnostic approach that enhanced the detection and evaluation of tissue-specific genes/transcripts through fibroblast-to-neuron cell transdifferentiation. The approach is designed specifically to suit clinical implementation, emphasizing simplicity, cost effectiveness, turnaround time, and reproducibility. For clinical validation, we generated induced neurons (iNeurons) from 71 individuals with primary neurological phenotypes recruited to the Undiagnosed Diseases Network. The overall diagnostic yield was 25.4%. Over a quarter of the diagnostic findings benefited from transdifferentiation and could not be achieved by fibroblast RNA-seq alone. This iNeuron transcriptomic approach can be effectively integrated into diagnostic whole-transcriptome evaluation of individuals with genetic disorders.

Generation of a humanized mAce2 and a conditional hACE2 mouse models permissive to SARS-COV-2 infection.

The Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) remains a public health concern and a subject of active research effort. Development of pre-clinical animal models is critical to study viral-host interaction, tissue tropism, disease mechanisms, therapeutic approaches, and long-term sequelae of infection. Here, we report two mouse models for studying SARS-CoV-2: A knock-in mAce2F83Y,H353K mouse that expresses a mouse-human hybrid form of the angiotensin-converting enzyme 2 (ACE2) receptor under the endogenous mouse Ace2 promoter, and a Rosa26 conditional knock-in mouse carrying the human ACE2 allele (Rosa26hACE2). Although the mAce2F83Y,H353K mice were susceptible to intranasal inoculation with SARS-CoV-2, they did not show gross phenotypic abnormalities. Next, we generated a Rosa26hACE2;CMV-Cre mouse line that ubiquitously expresses the human ACE2 receptor. By day 3 post infection with SARS-CoV-2, Rosa26hACE2;CMV-Cre mice showed significant weight loss, a variable degree of alveolar wall thickening and reduced survival rates. Viral load measurements confirmed inoculation in lung and brain tissues of infected Rosa26hACE2;CMV-Cre mice. The phenotypic spectrum displayed by our different mouse models translates to the broad range of clinical symptoms seen in the human patients and can serve as a resource for the community to model and explore both treatment strategies and long-term consequences of SARS-CoV-2 infection.

Psychosocial Outcomes of Pain and Pain Management in Adults with Osteogenesis Imperfecta: A Qualitative Study.

Osteogenesis imperfecta (OI) is a genetic disorder characterized by bone fragility and fractures, short stature, dental abnormalities, hearing loss, scoliosis, and chronic pain. Despite a growing literature on the functional outcomes of OI, limited research has explicitly examined the psychosocial outcomes of pain within OI. Adults with OI (N = 15) were interviewed to understand pain-related experiences through a thematic analysis of semi-structured interview data. Research team members, genetic research experts, and OI clinicians developed an interview guide focused on topics related to pain and mental health challenges. Participants' transcripts were coded by two independent coders; codes were then merged across coders and quotation outputs were subsequently abstracted (paraphrased then thematically classified) to identify common themes. Themes related to pain management variability regarding pain type, pain risk management and accessibility, pain outcomes (e.g., behavior, cognitive, affective), and pain exacerbating factors (e.g., individual, contextual) were identified. Participants reported chronic and acute pain, and despite the inaccessibility and stigmatization of pain medications (e.g., opioids), pharmacological treatments were the most common pain management approach. Participants reported negative pain outcomes, such as limited daily functioning and activity participation, fear, anger, anxiety, depression, and difficulty concentrating. Lastly, participants suggested that lack of physician and community knowledge on chronic pain in OI indirectly exacerbates both subjective pain intensity and outcomes. Although limited by a small, nondiverse sample, the current study provides valuable exploration of the unique pain experiences of adults with OI that may have implications for proactive management, treatment development, and clinician training.

Reducing Time to Diagnosis of Rare Genetic Diseases in a Medically Underserved Hispanic Population- Lessons Learned for Meaningful Engagement.

Background: The utilization of genomic information to improve health outcomes is progressively becoming more common in clinical practice. Nonetheless, disparities persist in accessing genetic services among ethnic minorities, individuals with low socioeconomic status, and other vulnerable populations. The Rio Grande Valley at the Texas-Mexico border is predominantly Hispanic with a high poverty rate and an increased prevalence of birth defects, with very limited access to genetics services. The cost of a diagnosis is often times out of reach for these underserved families. Funded by the National Center for Advancing Translational Sciences (NCATS), Project GIVE (Genetic Inclusion by Virtual Evaluation) was launched in 2022 to shorten the time to diagnosis and alleviate healthcare inequities in this region, with the goal of improving pediatric health outcomes. Methods: Utilizing Consultagene, an innovative electronic health record (EHR) agnostic virtual telehealth and educational platform, we designed the study to recruit 100 children with rare diseases over a period of two years from this region, through peer-to-peer consultation and referral. Conclusions: Project GIVE study has allowed advanced genetic evaluation and delivery of genome sequencing through the virtual portal, effectively circumventing the recognized socioeconomic and other barriers within this population. This paper explores the successful community engagement process and implementation of an alternate genomics evaluation platform and testing approach, aiming to reduce the diagnostic journey for individuals with rare diseases residing in a medically underserved region.