Phenotype Ontology Research Articles

NeoGx: Machine-Recommended Rapid Genome Sequencing for Neonates.

Genetic disease is common in the Level IV Neonatal Intensive Care Unit (NICU), but neonatology providers are not always able to identify the need for genetic evaluation. We trained a machine learning (ML) algorithm to predict the need for genetic testing within the first 18 months of life using health record phenotypes. For a decade of NICU patients, we extracted Human Phenotype Ontology (HPO) terms from clinical text with Natural Language Processing tools. Considering multiple feature sets, classifier architectures, and hyperparameters, we selected a classifier and made predictions on a validation cohort of 2,241 Level IV NICU admits born 2020-2021. Our classifier had ROC AUC of 0.87 and PR AUC of 0.73 when making predictions during the first week in the Level IV NICU. We simulated testing policies under which subjects begin testing at the time of first ML prediction, estimating diagnostic odyssey length both with and without the additional benefit of pursuing rGS at this time. Just by using ML to accelerate initial genetic testing (without changing the tests ordered), the median time to first genetic test dropped from 10 days to 1 day, and the number of diagnostic odysseys resolved within 14 days of NICU admission increased by a factor of 1.8. By additionally requiring rGS at the time of positive ML prediction, the number of diagnostic odysseys resolved within 14 days was 3.8 times higher than the baseline. ML predictions of genetic testing need, together with the application of the right rapid testing modality, can help providers accelerate genetics evaluation and bring about earlier and better outcomes for patients.

FastHPOCR: pragmatic, fast, and accurate concept recognition using the human phenotype ontology.

Human Phenotype Ontology (HPO)-based phenotype concept recognition (CR) underpins a faster and more effective mechanism to create patient phenotype profiles or to document novel phenotype-centred knowledge statements. While the increasing adoption of large language models (LLMs) for natural language understanding has led to several LLM-based solutions, we argue that their intrinsic resource-intensive nature is not suitable for realistic management of the phenotype CR lifecycle. Consequently, we propose to go back to the basics and adopt a dictionary-based approach that enables both an immediate refresh of the ontological concepts as well as efficient re-analysis of past data. We developed a dictionary-based approach using a pre-built large collection of clusters of morphologically equivalent tokens-to address lexical variability and a more effective CR step by reducing the entity boundary detection strictly to candidates consisting of tokens belonging to ontology concepts. Our method achieves state-of-the-art results (0.76 F1 on the GSC+ corpus) and a processing efficiency of 10 000 publication abstracts in 5 s. FastHPOCR is available as a Python package installable via pip. The source code is available at https://github.com/tudorgroza/fast_hpo_cr. A Java implementation of FastHPOCR will be made available as part of the Fenominal Java library available at https://github.com/monarch-initiative/fenominal. The up-to-date GCS-2024 corpus is available at https://github.com/tudorgroza/code-for-papers/tree/main/gsc-2024.

Evidence for sodium valproate toxicity in mitochondrial diseases: a systematic analysis

BackgroundWe aimed to determine whether sodium valproate (VPA) should be contraindicated in all mitochondrial diseases, due to known VPA-induced severe hepatotoxicity in some mitochondrial diseases.MethodsWe systematically reviewed the published literature...

Fine-tuning large language models for rare disease concept normalization.

We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO). We developed an in-house template-based script to generate two corpora for fine-tuning. The first (NAME) contains standardized HPO names, sourced from the HPO vocabularies, along with their corresponding identifiers. The second (NAME+SYN) includes HPO names and half of the concept's synonyms as well as identifiers. Subsequently, we fine-tuned Llama 2 (Llama2-7B) for each sentence set and conducted an evaluation using a range of sentence prompts and various phenotype terms. When the phenotype terms for normalization were included in the fine-tuning corpora, both models demonstrated nearly perfect performance, averaging over 99% accuracy. In comparison, ChatGPT-3.5 has only ∼20% accuracy in identifying HPO IDs for phenotype terms. When single-character typos were introduced in the phenotype terms, the accuracy of NAME and NAME+SYN is 10.2% and 36.1%, respectively, but increases to 61.8% (NAME+SYN) with additional typo-specific fine-tuning. For terms sourced from HPO vocabularies as unseen synonyms, the NAME model achieved 11.2% accuracy, while the NAME+SYN model achieved 92.7% accuracy. Our fine-tuned models demonstrate ability to normalize phenotype terms unseen in the fine-tuning corpus, including misspellings, synonyms, terms from other ontologies, and laymen's terms. Our approach provides a solution for the use of LLMs to identify named medical entities from clinical narratives, while successfully normalizing them to standard concepts in a controlled vocabulary.

Advances in big data and omics: Paving the way for discovery in childhood epilepsies

The insights gained from big data and omics approaches have transformed the field of childhood genetic epilepsy. With an increasing number of individuals receiving genetic testing for seizures, we are provided with an opportunity to identify clinically relevant subgroups and extract meaningful observations from this large-scale clinical data. However, the volume of data from electronic medical records and omics (e.g., genomics, transcriptomics) is so vast that standardized methods, such as the Human Phenotype Ontology, are necessary for reliable and comprehensive characterization. Here, we explore the integration of clinical and omics data, highlighting how these approaches pave the way for discovery in childhood epilepsies.

Objectivizing issues in the diagnosis of complex rare diseases: lessons learned from testing existing diagnosis support systems on ciliopathies

BackgroundThere are approximately 8,000 different rare diseases that affect roughly 400 million people worldwide. Many of them suffer from delayed diagnosis. Ciliopathies are rare monogenic disorders characterized by a significant phenotypic and genetic heterogeneity that raises an important challenge for clinical diagnosis. Diagnosis support systems (DSS) applied to electronic health record (EHR) data may help identify undiagnosed patients, which is of paramount importance to improve patients’ care. Our objective was to evaluate three online-accessible rare disease DSSs using phenotypes derived from EHRs for the diagnosis of ciliopathies.MethodsTwo datasets of ciliopathy cases, either proven or suspected, and two datasets of controls were used to evaluate the DSSs. Patient phenotypes were automatically extracted from their EHRs and converted to Human Phenotype Ontology terms. We tested the ability of the DSSs to diagnose cases in contrast to controls based on Orphanet ontology.ResultsA total of 79 cases and 38 controls were selected. Performances of the DSSs on ciliopathy real world data (best DSS with area under the ROC curve = 0.72) were not as good as published performances on the test set used in the DSS development phase. None of these systems obtained results which could be described as “expert-level”. Patients with multisystemic symptoms were generally easier to diagnose than patients with isolated symptoms. Diseases easily confused with ciliopathy generally affected multiple organs and had overlapping phenotypes. Four challenges need to be considered to improve the performances: to make the DSSs interoperable with EHR systems, to validate the performances in real-life settings, to deal with data quality, and to leverage methods and resources for rare and complex diseases.ConclusionOur study provides insights into the complexities of diagnosing highly heterogenous rare diseases and offers lessons derived from evaluation existing DSSs in real-world settings. These insights are not only beneficial for ciliopathy diagnosis but also hold relevance for the enhancement of DSS for various complex rare disorders, by guiding the development of more clinically relevant rare disease DSSs, that could support early diagnosis and finally make more patients eligible for treatment.

#958 Development and Validation of a Score Estimating the Probability of obtaining a genetic diagnosis in adults with CKD of uncertain origin

Abstract Background and Aims We aim to derive and validate a score estimating the probability of identifying a variant explicative of the renal phenotype using Exome Sequencing (ES) in adults with CKD of uncertain origin. Method Participants: prospective cohort study including all consecutive index patients with a CKD from uncertain origin in three French nephrology units (metropolitan: Sorbonne University Hospitals, Paris, and Conception Hospital, Marseille; overseas: La Réunion University Hospital, Réunion island) who underwent ES between October 11th, 2017 and May 31st, 2023. Outcome measure: identification of a causal variant using ES data, according to the American College of Medical Genetics and Genomics diagnostic criteria. Candiate variables and feature engineering: raw data regarding patients’ phenotypes was prospectively entered in a collection form at the time of ES by the prescribing physician. Structured data (yes/no questions and lists) was mapped to Human Phenotype Ontology (HPO) terms. Unstructured data (free text) was manually translated into HPO terms by the same investigator (nephrologist), which was blinded to ES results. First, second and third-order ancestor HPO terms were included in the analysis. Score's derivation: an optimal weighted average of multiple models (“ensemble model”) was specified, following guidelines provided in a recently published article (PMID:36905602). Score's validation: internal validation using 10-fold cross validation, followed by internal-external validation (data from 2/3 centers was used to develop a model which was then tested using data from the remaining center; this process was repeated in each center). Results We included 2,490 patients, 560/2,490 (22.5%) of whom had a causal variant identified by ES. We collected 1,028 distinct HPO terms describing the patients’ phenotypes. The most common term was “Hypertension”, occurring in 2,079/2,490 (83.5%) patients. In internal validation, the score showed accurate calibration and discrimination (area under the receiver operating characteristics curve (AUC): 0.71, 95% CI 0.68 to 0.73; index of precision accuracy (IPA): 0.11, 95% CI 0.09 to 0.13). Performances were moderately diminished in internal-external validation but remained satisfactory (Tenon: AUC 0.64, IPA 0.04; Marseille: AUC 0.67, IPA 0.04; La Réunion: 0.68, IPA 0.09). Conclusion We derived, internally and internally-externally validated a clinical score which accurately predicts the probability of obtaining a genetic diagnosis using Exome Sequencing. Feature engineering could further increase the score's performances. Automatic computation by clinicians using an interactive tool is achievable and could be of clinical utility, especially to guide resource allocation in case of a low pretest probability.

#787 Kidney genetics—a reproducible and curated database of kidney-disease associated genes

Abstract Background and Aims Genetic insights are becoming increasingly influential in the understanding and treatment of various kidney diseases (KD). Hundreds of genes associated with monogenic kidney disease have been identified, providing valuable insights into their diagnosis, management, and monitoring. However, the lack of a unified and standardized database of genes assigned to kidney diseases has led to diagnostic blind spots and comparability issues among current studies of kidney genetics. To address this gap, we created “Kidney-Genetics”, a regularly updated, automated and publicly accessible database, which aims to provide a comprehensive list of all relevant genes associated with kidney disease. Methods Kidney disease-associated gene information was compiled from various sources, including: (1) Genomics England and Australia PanelApp [1], (2) a comprehensive literature review of published gene lists, (3) clinical diagnostic panels for kidney disease, (4) a Human Phenotype Ontology (HPO)-based [2] search in rare disease databases (OMIM, Orphanet), and (5) a PubTator [3] API-based automated literature extraction from PubMed. An evidence-scoring system was developed to distinguish high- evidence genes from low evidence genes and candidate genes. High-evidence genes were defined as those present in two or more of the five resources and were manually curated based on predetermined criteria or, in the case of existing ClinGen [4] curation, their data and scores were used. Genes with a score of one or less were accordingly classified as candidate genes. Additionally, genes were grouped into different categories for later genotype-phenotype correlation matching (see Fig. 1). Results The Kidney-Genetics database currently contains detailed information on 3025 kidney-associated genes with detailed annotations on gene expression, kidney phenotype, inheritance mode, disease onset, possible syndromic disease mode and genetic variation. The number of genes extracted from the five analyzed sources of information are as follows: (1) 534, (2) 822, (3) 956, (4) 789, and (5) 2158 (see Fig. 2). Notably, 598 genes (19.8%) of the total 3025 genes are present in two or more of the analyzed information sources, thus meeting our evidence criteria, indicating high confidence and their potential for diagnostic use. Of these high-evidence genes, 526 (88.0%) are present in at least one, and 56 (9.4%) are present in all 10 comprehensive diagnostic laboratory panels. To ensure currency, Kidney-Genetics will be updated regularly and automatically on a monthly basis. We will also provide phenotypic and functional clustering results to facilitate gene grouping. Conclusion By utilizing Kidney-Genetics, clinicians, geneticists, and researchers can examine genomic data and improve their understanding of the genetic components of diverse KDs. The code and results are freely available on GitHub (kidney-genetics.org) [5]. A standardized pipeline and automated system keep our database on the cutting edge of kidney research and diagnostics. Screening efforts toward manual curation (such as through the ClinGen initiative) and assignment of diagnostic genes to kidney disease groups (e.g., syndromic vs. isolated; adult vs. pediatric; cystic, nephrotic, etc.) are currently under development.

Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data.

The ongoing expansion of human genomic datasets propels therapeutic target identification; however, extracting gene-disease associations from gene annotations remains challenging. Here, we introduce Mantis-ML 2.0, a framework integrating AstraZeneca's Biological Insights Knowledge Graph and numerous tabular datasets, to assess gene-disease probabilities throughout the phenome. We use graph neural networks, capturing the graph's holistic structure, and train them on hundreds of balanced datasets via a robust semi-supervised learning framework to provide gene-disease probabilities across the human exome. Mantis-ML 2.0 incorporates natural language processing to automate disease-relevant feature selection for thousands of diseases. The enhanced models demonstrate a 6.9% average classification power boost, achieving a median receiver operating characteristic (ROC) area under curve (AUC) score of 0.90 across 5220 diseases from Human Phenotype Ontology, OpenTargets, and Genomics England. Notably, Mantis-ML 2.0 prioritizes associations from an independent UK Biobank phenome-wide association study (PheWAS), providing a stronger form of triaging and mitigating against underpowered PheWAS associations. Results are exposed through an interactive web resource.

Human Phenotype Ontology: Developing HPO Terms for Mood Disorders to Integrate Diverse Phenotypic Datasets

Human Phenotype Ontology: Developing HPO Terms for Mood Disorders to Integrate Diverse Phenotypic Datasets

Possible New Candidates Involved to Thalidomide-Related Limbs and Cardiac Defects: A Systems Biology Approach.

Thalidomide is a known teratogen that causes malformations especially in heart and limbs. Its mechanism of teratogenicity is still not fully elucidated. Recently, a new target of thalidomide was described, TBX5, and was observed a new interaction between HAND2 and TBX5 that is disrupted in the presence of thalidomide. Therefore, our study aimed to raise potential candidates for thalidomide teratogenesis, through systems biology, evaluating HAND2 and TBX5 interaction and heart and limbs malformations of thalidomide. Genes and proteins related to TBX5 and HAND2 were selected through TF2DNA, REACTOME, Human Phenotype Ontology, and InterPro databases. Networks were assembled using STRING © database. Network analysis were performed in Cytoscape © and R v3.6.2. Differential gene expression (DGE) analysis was performed through gene expression omnibus. We constructed a network for HAND2 and TBX5 interaction; a network for heart and limbs malformations of TE; and the two joined networks. We observed that EP300 protein seemed to be important in all networks. We also looked for proteins containing C2H2 domain in the assembled networks. ZIC3, GLI1, GLI3, ZNF148, and PRDM16 were the ones present in both heart and limbs malformations of TE networks. Furthermore, in the DGE analysis after treatment with thalidomide, we observed that FANCB, ESCO2, and XRCC2 were downregulated and present both in heart and limbs networks. Through systems biology, we were able to point to different new proteins and genes, and selected specially EP300, which was important in all the analyzed networks, to be further evaluated in the TE teratogenicity.

Learning from conect4children: A Collaborative Approach towards Standardisation of Disease-Specific Paediatric Research Data

The conect4children (c4c) initiative was established to facilitate the development of new drugs and other therapies for paediatric patients. It is widely recognised that there are not enough medicines tested for all relevant ages of the paediatric population. To overcome this, it is imperative that clinical data from different sources are interoperable and can be pooled for larger post hoc studies. c4c has collaborated with the Clinical Data Interchange Standards Consortium (CDISC) to develop cross-cutting data resources that build on existing CDISC standards in an effort to standardise paediatric data. The natural next step was an extension to disease-specific data items. c4c brought together several existing initiatives and resources relevant to disease-specific data and analysed their use for standardising disease-specific data in clinical trials. Several case studies that combined disease-specific data from multiple trials have demonstrated the need for disease-specific data standardisation. We identified three relevant initiatives. These include European Reference Networks, European Joint Programme on Rare Diseases, and Pistoia Alliance. Other resources reviewed were National Cancer Institute Enterprise Vocabulary Services, CDISC standards, pharmaceutical company-specific data dictionaries, Human Phenotype Ontology, Phenopackets, Unified Registry for Inherited Metabolic Disorders, Orphacodes, Rare Disease Cures Accelerator-Data and Analytics Platform (RDCA-DAP), and Observational Medical Outcomes Partnership. The collaborative partners associated with these resources were also reviewed briefly. A plan of action focussed on collaboration was generated for standardising disease-specific paediatric clinical trial data. A paediatric data standards multistakeholder and multi-project user group was established to guide the remaining actions—FAIRification of metadata, a Phenopackets pilot with RDCA-DAP, applying Orphacodes to case report forms of clinical trials, introducing CDISC standards into European Reference Networks, testing of the CDISC Pediatric User Guide using data from the mentioned resources and organisation of further workshops and educational materials.

Variants in mitochondrial disease genes are common causes of inherited peripheral neuropathies

BackgroundPeripheral neuropathies in mitochondrial disease are caused by mutations in nuclear genes encoding mitochondrial proteins, or in the mitochondrial genome. Whole exome or genome sequencing enable parallel testing of nuclear and mtDNA genes, and it has significantly advanced the genetic diagnosis of inherited diseases. Despite this, approximately 40% of all Charcot-Marie-Tooth (CMT) cases remain undiagnosed.MethodsThe genome-phenome analysis platform (GPAP) in RD-Connect was utilised to create a cohort of 2087 patients with at least one Human Phenotype Ontology (HPO) term suggestive of a peripheral neuropathy, from a total of 10,935 patients. These patients’ genetic data were then analysed and searched for variants in known mitochondrial disease genes.ResultsA total of 1,379 rare variants were identified, 44 of which were included in this study as either reported pathogenic or likely causative in 42 patients from 36 families. The most common genes found to be likely causative for an autosomal dominant neuropathy were GDAP1 and GARS1. We also detected heterozygous likely pathogenic variants in DNA2, MFN2, DNM2, PDHA1, SDHA, and UCHL1. Biallelic variants in SACS, SPG7, GDAP1, C12orf65, UCHL1, NDUFS6, ETFDH and DARS2 and variants in the mitochondrial DNA (mtDNA)-encoded MT-ATP6 and MT-TK were also causative for mitochondrial CMT. Only 50% of these variants were already reported as solved in GPAP.ConclusionVariants in mitochondrial disease genes are frequent in patients with inherited peripheral neuropathies. Due to the clinical overlap between mitochondrial disease and CMT, agnostic exome or genome sequencing have better diagnostic yields than targeted gene panels.

Mouse Genome Informatics: an integrated knowledgebase system for the laboratory mouse.

Mouse Genome Informatics (MGI) is a federation of expertly curated information resources designed to support experimental and computational investigations into genetic and genomic aspects of human biology and disease using the laboratory mouse as a model system. The Mouse Genome Database (MGD) and the Gene Expression Database (GXD) are core MGI databases that share data and system architecture. MGI serves as the central community resource of integrated information about mouse genome features, variation, expression, gene function, phenotype, and human disease models acquired from peer-reviewed publications, author submissions, and major bioinformatics resources. To facilitate integration and standardization of data, biocuration scientists annotate using terms from controlled metadata vocabularies and biological ontologies (e.g. Mammalian Phenotype Ontology, Mouse Developmental Anatomy, Disease Ontology, Gene Ontology, etc.), and by applying international community standards for gene, allele, and mouse strain nomenclature. MGI serves basic scientists, translational researchers, and data scientists by providing access to FAIR-compliant data in both human-readable and compute-ready formats. The MGI resource is accessible at https://informatics.jax.org. Here, we present an overview of the core data types represented in MGI and highlight recent enhancements to the resource with a focus on new data and functionality for MGD and GXD.

Diagnostic yield after next-generation sequencing in pediatric cardiovascular disease

Genetic testing with exome sequencing and genome sequencing is increasingly offered to infants and children with cardiovascular diseases. However, the rates of positive diagnoses after genetic testing within the different categories of cardiac disease and phenotypic subtypes of congenital heart disease (CHD) has been little studied. We report the diagnostic yield after next-generation sequencing in 500 patients with CHD from diverse population subgroups that were enrolled at three different sites in the Clinical Sequencing Evidence-Generating Research consortium. Patients were ascertained due to a primary cardiovascular issue comprising arrhythmia, cardiomyopathy and/or CHD and corresponding human phenotype ontology terms were selected to describe the cardiac and extracardiac findings. We examined the diagnostic yield for patients with arrhythmia, cardiomyopathy and/or CHD and phenotypic subtypes of CHD comprising conotruncal defects, heterotaxy, left ventricular outflow tract obstruction, septal defects, and ‘Other’ heart defects. We found a significant increase in the frequency of positive findings for patients who underwent genome sequencing compared to exome sequencing and for syndromic cardiac defects compared to isolated cardiac defects. We also found significantly higher diagnostic rates for patients who presented with isolated cardiomyopathy compared to isolated CHD. For patients with syndromic presentations who underwent genome sequencing, there were significant differences in the numbers of positive diagnoses for phenotypic subcategories of CHD, ranging from 31.7% for septal defects to 60% for Other. Despite variation in the diagnostic yield at each site, our results support genetic testing in pediatric patients with syndromic and isolated cardiovascular issues and in all subtypes of CHD.

An AI-based approach driven by genotypes and phenotypes to uplift the diagnostic yield of genetic diseases.

Identifying disease-causing variants in Rare Disease patients' genome is a challenging problem. To accomplish this task, we describe a machine learning framework, that we called "Suggested Diagnosis", whose aim is to prioritize genetic variants in an exome/genome based on the probability of being disease-causing. To do so, our method leverages standard guidelines for germline variant interpretation as defined by the American College of Human Genomics (ACMG) and the Association for Molecular Pathology (AMP), inheritance information, phenotypic similarity, and variant quality. Starting from (1) the VCF file containing proband's variants, (2) the list of proband's phenotypes encoded in Human Phenotype Ontology terms, and optionally (3) the information about family members (if available), the "Suggested Diagnosis" ranks all the variants according to their machine learning prediction. This method significantly reduces the number of variants that need to be evaluated by geneticists by pinpointing causative variants in the very first positions of the prioritized list. Most importantly, our approach proved to be among the top performers within the CAGI6 Rare Genome Project Challenge, where it was able to rank the true causative variant among the first positions and, uniquely among all the challenge participants, increased the diagnostic yield of 12.5% by solving 2 undiagnosed cases.

Common data elements for arthrogryposis multiplex congenita: An international framework.

To facilitate multisite studies and international clinical research, this study aimed to identify consensus-based, standardized common data elements (CDEs) for arthrogryposis multiplex congenita (AMC). A mixed-methods study comprising of several focus group discussions and three rounds of modified Delphi surveys to achieve consensus using two tiered-rating scales were conducted. Overall, 45 clinical experts and adults with lived experience (including 12 members of an AMC consortium) participated in this study from 11 countries in North America, Europe, and Australia. The CDEs include 321 data elements and 19 standardized measures across various domains from fetal development to adulthood. Data elements pertaining to AMC phenotypic traits were mapped according to the Human Phenotype Ontology. A universal governance structure, local operating protocols, and sustainability plans were identified as the main facilitators, whereas limited capacity for data sharing and the need for a federated informatics infrastructure were the main barriers. Collection of systematic data on AMC using CDEs will allow investigations on etiological pathways, describe epidemiological profile, and establish genotype-phenotype correlations in a standardized manner. The proposed CDEs will facilitate international multidisciplinary collaborations by improving large-scale studies and opportunities for data sharing, knowledge translation, and dissemination.

Multi-center implementation of rapid whole genome sequencing provides additional evidence of its utility in the pediatric inpatient setting.

Multi-center implementation of rapid whole genome sequencing with assessment of the clinical utility of rapid whole genome sequencing (rWGS), including positive, negative and uncertain results, in admitted infants with a suspected genetic disease. rWGS tests were ordered at eight hospitals between November 2017 and April 2020. Investigators completed a survey of demographic data, Human Phenotype Ontology (HPO) terms, test results and impacts of results on clinical care. A total of 188 patients, on general hospital floors and intensive care unit (ICU) settings, underwent rWGS testing. Racial and ethnic characteristics of the tested infants were broadly representative of births in the country at large. 35% of infants received a diagnostic result in a median of 6 days. The most common HPO terms for tested infants indicated an abnormality of the nervous system, followed by the cardiovascular system, the digestive system, the respiratory system and the head and neck. Providers indicated a major change in clinical management because of rWGS for 32% of infants tested overall and 70% of those with a diagnostic result. Also, 7% of infants with a negative rWGS result and 23% with a variant of unknown significance (VUS) had a major change in management due to testing. Our study demonstrates that the implementation of rWGS is feasible across diverse institutions, and provides additional evidence to support the clinical utility of rWGS in a demographically representative sample of admitted infants and includes assessment of the clinical impact of uncertain rWGS results in addition to both positive and negative results.

A step-by-step, multidisciplinary strategy to maximize the yield of genetic testing in pediatric patients with chronic kidney diseases.

The use of genetic testing in pediatric patients with chronic kidney diseases (CKD) has increased exponentially in the past few years, particularly with the emergence of novel sequencing techniques. However, the genetic yield remains unexpectedly low in nephrology, with an impact on diagnosis, prognosis and treatment. Moreover, the increasing diversity of genetic testing possibilities can be seen as an obstacle by clinicians, in the absence of a strong background in genetics. Here, we propose a step-by-step, multidisciplinary strategy for the diagnostic evaluation of pediatric patients with CKD, and appropriate genetic test selection to maximize the yield of genetic testing. A total of 126 pediatric patients were enrolled in a retrospective file analysis. Genetic testing techniques used included phenotype-associated next-generation panel sequencing (N = 41), Sanger and SNaPshot sequencing (N = 3) and/or whole exome sequencing (N = 2). Overall genetic yield reached 63% and genetic testing significantly impacted patient management in 70%. The distribution of kidney diseases among patients was balanced and matched previously described pediatric cohorts in terms of glomerulopathies, tubulopathies and ciliopathies. Genetic analyses led to significant treatment modifications, kidney biopsy sparing and personalized nephroprotection, as well as tailored genetic counseling. Of note, the evaluation of Human Phenotype Ontology term accuracy in the cohort showed that causal mutations were precisely identified in 85% of the patients at most. Here we suggest a step-by-step, multidisciplinary strategy to maximize the yield of genetic testing in pediatric patients with CKD. This approach optimizes patient care while avoiding unnecessary treatments or procedures.

An evaluation of GPT models for phenotype concept recognition

ObjectiveClinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field. These processes rely on using ontology concepts, often from the Human Phenotype Ontology, in conjunction with a phenotype concept recognition task (supported usually by machine learning methods) to curate patient profiles or existing scientific literature. With the significant shift in the use of large language models (LLMs) for most NLP tasks, we examine the performance of the latest Generative Pre-trained Transformer (GPT) models underpinning ChatGPT as a foundation for the tasks of clinical phenotyping and phenotype annotation.Materials and methodsThe experimental setup of the study included seven prompts of various levels of specificity, two GPT models (gpt-3.5-turbo and gpt-4.0) and two established gold standard corpora for phenotype recognition, one consisting of publication abstracts and the other clinical observations.ResultsThe best run, using in-context learning, achieved 0.58 document-level F1 score on publication abstracts and 0.75 document-level F1 score on clinical observations, as well as a mention-level F1 score of 0.7, which surpasses the current best in class tool. Without in-context learning, however, performance is significantly below the existing approaches.ConclusionOur experiments show that gpt-4.0 surpasses the state of the art performance if the task is constrained to a subset of the target ontology where there is prior knowledge of the terms that are expected to be matched. While the results are promising, the non-deterministic nature of the outcomes, the high cost and the lack of concordance between different runs using the same prompt and input make the use of these LLMs challenging for this particular task.