Encoding Clinical Data with the Human Phenotype Ontology for Computational Differential Diagnostics

Online Mendelian Inheritance in Animals (OMIA): a genetic resource for vertebrate animals

Online Mendelian Inheritance in Animals (OMIA) is a freely available curated knowledgebase that contains information and facilitates research on inherited traits and diseases in animals. For the past 29 years, OMIA has been used by animal geneticists, breeders, and veterinarians worldwide as a definitive source of information. Recent increases in curation capacity and funding for software engineering support have resulted in software upgrades and commencement of several initiatives, which include the enhancement of variant information and links to human data resources, and the introduction of ontology-based breed information and categories. We provide an overview of current information and recent enhancements to OMIA and discuss how we are expanding the integration of OMIA into other resources and databases via the use of ontologies and the adaptation of tools used in human genetics.

MSeqDR Quick-Mitome (QM): Combining Phenotype-Guided Variant Interpretation and Machine Learning Classifiers to Aid Primary Mitochondrial Disease Genetic Diagnosis

The international Mitochondrial Disease Sequence Data Resource Consortium (MSeqDR) Quick-Mitome (QM) is a web-based platform enabling automated variant interpretation of whole-exome sequencing (WES) datasets for the genetic diagnosis of primary mitochondrial diseases (PMD). Designed specifically to address the unique dual genome nature of PMD etiologies, QM includes features for both nuclear and mitochondrial DNA (mtDNA) genome analysis. QM requires VCF variant lists, HPO ID clinical phenotypes, and pedigree files for multiple-sample VCF inputs. QM maps phenotypes to HPO terms before analysis. QM analysis requires 2 to 20 min for 100,000 variants on an 8-vCPU AWS server using Exomiser's "PASS_ONLY" mode for nuclear variants. QM ranks variants based on allele frequency, phenotype-gene association, functional impact, and inheritance mode. Variants are further annotated with multiple data sources such as OMIM, ClinVar, dbNSFP, gnoMAD, MITOMAP, and MSeqDR. In addition to standard Exomiser results, QM generates an Analysis Report and QM Integrated Report with add-on mtDNA-specific analyses, including haplogroup prediction with Phy-Mer, heteroplasmy calculation, and mvTool annotations. We developed the Mitochondrial Disease Variant (MDV) classifier using XGBoost to predict variant pathogenicity for PMD. The MDV classifier was trained on >120 features and performance benchmarking showed that it correctly classified >98% of nuclear gene variants as being pathogenic or benign, and predicted PMD-causing variants with 94% precision. The MSeqDR QM server is an open-access resource for phenotype-driven dual-genome analyses for PMD diagnosis by the global mitochondrial disease community. It is publicly available for non-commercial, non-clinical research use at https://mseqdr.org/quickmitome.php. © 2024 Wiley Periodicals LLC. Basic Protocol 1: Standardizing clinical phenotypes into human phenotype ontology (HPO) terms as the phenotype input for Quick-Mitome (QM) Basic Protocol 2: Prepare the pedigree input for multiple-sample VCF Basic Protocol 3: Quick-Mitome (QM) analysis Basic Protocol 4: Reviewing and understanding the QM Integrated Report and Analysis Report.

Clinical Genetics Assessment Triangle (CGAT): A simple tool to identify patients with genetic conditions

OBJECTIVE

The objective of this study was to develop a simple tool for general physicians to promptly identify and refer pediatric patients with a higher probability of having a genetic condition.

STUDY DESIGN

This retrospective, descriptive study was conducted at a tertiary pediatric hospital's Clinical Genetics Unit from June 2019 to January 2020. We included patients under 18 years of age who visited the unit, excluding those without genetic testing. Epidemiological, clinical, and genetic variables were collected from electronic medical records. The primary outcome was the diagnosis of a genetic condition based on genetic testing.

RESULTS

Among 445 patients, 304 were included; 163 (53.6%) were male, and mean age was 7.4 years (SD 5.1 years). A genetic condition was diagnosed in 139 patients (45.7%). Using a multiple logistic regression model, five variables significantly contributed to reaching a diagnosis: suspected diagnosis at referral (OR 3.45, P < 0.001), short stature (OR 3.11, P < 0.001), global developmental delay/intellectual disability (OR 2.65, P < 0.001), dysmorphic craniofacial features (OR 1.99, P = 0.035), and multiple congenital anomalies (OR 2.54, P = 0.033). The association strength (OR) increased when these variables were paired with each other. The study's findings are presented in the form of a triangle, known as the Clinical Genetics Assessment Triangle (CGAT), which summarizes the results. A decision tree model is applied to guide clinical department referrals based on the affected sides of the triangle.

CONCLUSIONS

The CGAT has the potential to enable general physicians to promptly identify pediatric patients with an increased probability of having a genetic condition.

GA4GH Phenopackets: A Practical Introduction

The Global Alliance for Genomics and Health (GA4GH) is developing a suite of coordinated standards for genomics for healthcare. The Phenopacket is a new GA4GH standard for sharing disease and phenotype information that characterizes an individual person, linking that individual to detailed phenotypic descriptions, genetic information, diagnoses, and treatments. A detailed example is presented that illustrates how to use the schema to represent the clinical course of a patient with retinoblastoma, including demographic information, the clinical diagnosis, phenotypic features and clinical measurements, an examination of the extirpated tumor, therapies, and the results of genomic analysis. The Phenopacket Schema, together with other GA4GH data and technical standards, will enable data exchange and provide a foundation for the computational analysis of disease and phenotype information to improve our ability to diagnose and conduct research on all types of disorders, including cancer and rare diseases.

The practice of genomic medicine: A delineation of the process and its governing principles

Genomic medicine, an emerging medical discipline, applies the principles of evolution, developmental biology, functional genomics, and structural genomics within clinical care. Enabling widespread adoption and integration of genomic medicine into clinical practice is key to achieving precision medicine. We delineate a biological framework defining diagnostic utility of genomic testing and map the process of genomic medicine to inform integration into clinical practice. This process leverages collaboration and collective cognition of patients, principal care providers, clinical genomic specialists, laboratory geneticists, and payers. We detail considerations for referral, triage, patient intake, phenotyping, testing eligibility, variant analysis and interpretation, counseling, and management within the utilitarian limitations of health care systems. To reduce barriers for clinician engagement in genomic medicine, we provide several decision-making frameworks and tools and describe the implementation of the proposed workflow in a prototyped electronic platform that facilitates genomic care. Finally, we discuss a vision for the future of genomic medicine and comment on areas for continued efforts.

IMPROVE-DD: Integrating multiple phenotype resources optimizes variant evaluation in genetically determined developmental disorders

Diagnosing rare developmental disorders using genome-wide sequencing data commonly necessitates review of multiple plausible candidate variants, often using ontologies of categorical clinical terms. We show that Integrating Multiple Phenotype Resources Optimizes Variant Evaluation in Developmental Disorders (IMPROVE-DD) by incorporating additional classes of data commonly available to clinicians and recorded in health records. In doing so, we quantify the distinct contributions of sex, growth, and development in addition to Human Phenotype Ontology (HPO) terms and demonstrate added value from these readily available information sources. We use likelihood ratios for nominal and quantitative data and propose a classifier for HPO terms in this framework. This Bayesian framework results in more robust diagnoses. Using data systematically collected in the Deciphering Developmental Disorders study, we considered 77 genes with pathogenic/likely pathogenic variants in ≥10 individuals. All genes showed at least a satisfactory prediction by receiver operating characteristic when testing on training data (AUC ≥ 0.6), and HPO terms were the best predictor for the majority of genes, though a minority (13/77) of genes were better predicted by other phenotypic data types. Overall, classifiers based upon multiple integrated phenotypic data sources performed better than those based upon any individual source, and importantly, integrated models produced notably fewer false positives. Finally, we show that IMPROVE-DD models with good predictive performance on cross-validation can be constructed from relatively few individuals. This suggests new strategies for candidate gene prioritization and highlights the value of systematic clinical data collection to support diagnostic programs.

Differentiation of T Helper 17 Cells May Mediate the Abnormal Humoral Immunity in IgA Nephropathy and Inflammatory Bowel Disease Based on Shared Genetic Effects

Background

IgA nephropathy (IgAN) is the most frequent glomerulonephritis in inflammatory bowel disease (IBD). However, the inter-relational mechanisms between them are still unclear. This study aimed to explore the shared gene effects and potential immune mechanisms in IgAN and IBD.

Methods

The microarray data of IgAN and IBD in the Gene Expression Omnibus (GEO) database were downloaded. The differential expression analysis was used to identify the shared differentially expressed genes (SDEGs). Besides, the shared transcription factors (TFs) and microRNAs (miRNAs) in IgAN and IBD were screened using humanTFDB, HMDD, ENCODE, JASPAR, and ChEA databases. Moreover, weighted gene co-expression network analysis (WGCNA) was used to identify the shared immune-related genes (SIRGs) related to IgAN and IBD, and R software package org.hs.eg.db (Version3.1.0) were used to identify common immune pathways in IgAN and IBD.

Results

In this study, 64 SDEGs and 28 SIRGs were identified, and the area under the receiver operating characteristic curve (ROC) of 64 SDEGs was calculated and two genes (MVP, PDXK) with high area under the curve (AUC) in both IgAN and IBD were screened out as potential diagnostic biomarkers. We then screened 3 shared TFs (SRY, MEF2D and SREBF1) and 3 miRNAs (hsa-miR-146, hsa-miR-21 and hsa-miR-320), and further found that the immune pathways of 64SDEGs, 28SIRGs and 3miRNAs were mainly including B cell receptor signaling pathway, FcγR-mediated phagocytosis, IL-17 signaling pathway, toll-like receptor signaling pathway, TNF signaling pathway, TRP channels, T cell receptor signaling pathway, Th17 cell differentiation, and cytokine-cytokine receptor interaction.

Conclusion

Our work revealed the differentiation of Th17 cells may mediate the abnormal humoral immunity in IgAN and IBD patients and identified novel gene candidates that could be used as biomarkers or potential therapeutic targets.

Deep phenotyping and whole-exome sequencing improved the diagnostic yield for nuclear pedigrees with neurodevelopmental disorders

Background

Neurodevelopmental disorders, a group of early‐onset neurological disorders with significant clinical and genetic heterogeneity, remain a diagnostic challenge for clinical genetic evaluation. Therefore, we assessed the diagnostic yield by combining standard phenotypes and whole‐exome sequencing in families with these disorders that were “not yet diagnosed” by the traditional testing methods.

Methods

Using a standardized vocabulary of phenotypic abnormalities from human phenotype ontology (HPO), we performed deep phenotyping for 45 “not yet diagnosed” pedigrees to characterize multiple clinical features extracted from Chinese electronic medical records (EMRs). By matching HPO terms with known human diseases and phenotypes from model organisms, together with whole‐exome sequencing data, we prioritized candidate mutations/genes. We made probable genetic diagnoses for the families.

Results

We obtained a diagnostic yield of 29% (13 out of 45) with probably genetic diagnosis, of which compound heterozygosity and de novo mutations accounted for 77% (10/13) of the diagnosis. Of note, these pedigrees are accompanied by a more significant number of non‐neurological features.

Conclusions

Deep phenotyping and whole‐exome sequencing improve the etiological evaluation for neurodevelopmental disorders in the clinical setting.

Subsumption reduces dataset dimensionality without decreasing performance of a machine learning classifier

When features in a high dimension dataset are organized hierarchically, there is an inherent opportunity to reduce dimensionality. Since more specific concepts are subsumed by more general concepts, subsumption can be applied successively to reduce dimensionality. We tested whether sub-sumption could reduce the dimensionality of a disease dataset without impairing classification accuracy. We started with a dataset that had 168 neurological patients, 14 diagnoses, and 293 unique features. We applied subsumption repeatedly to create eight successively smaller datasets, ranging from 293 dimensions in the largest dataset to 11 dimensions in the smallest dataset. We tested a MLP classifier on all eight datasets. Precision, recall, accuracy, and validation declined only at the lowest dimensionality. Our preliminary results suggest that when features in a high dimension dataset are derived from a hierarchical ontology, subsumption is a viable strategy to reduce dimensionality.Clinical relevance- Datasets derived from electronic health records are often of high dimensionality. If features in the dataset are based on concepts from a hierarchical ontology, subsumption can reduce dimensionality.

Towards similarity-based differential diagnostics for common diseases

Ontology-based phenotype profiles have been utilised for the purpose of differential diagnosis of rare genetic diseases, and for decision support in specific disease domains. Particularly, semantic similarity facilitates diagnostic hypothesis generation through comparison with disease phenotype profiles. However, the approach has not been applied for differential diagnosis of common diseases, or generalised clinical diagnostics from uncurated text-derived phenotypes. In this work, we describe the development of an approach for deriving patient phenotype profiles from clinical narrative text, and apply this to text associated with MIMIC-III patient visits. We then explore the use of semantic similarity with those text-derived phenotypes to classify primary patient diagnosis, comparing the use of patient-patient similarity and patient-disease similarity using phenotype-disease profiles previously mined from literature. We also consider a combined approach, in which literature-derived phenotypes are extended with the content of text-derived phenotypes we mined from 500 patients. The results reveal a powerful approach, showing that in one setting, uncurated text phenotypes can be used for differential diagnosis of common diseases, making use of information both inside and outside the setting. While the methods themselves should be explored for further optimisation, they could be applied to a variety of clinical tasks, such as differential diagnosis, cohort discovery, document and text classification, and outcome prediction.

How to design a registry for undiagnosed patients in the framework of rare disease diagnosis: suggestions on software, data set and coding system

BACKGROUND

About 30 million people in the EU and USA, respectively, suffer from a rare disease. Driven by European legislative requirements, national strategies for the improvement of care in rare diseases are being developed. To improve timely and correct diagnosis for patients with rare diseases, the development of a registry for undiagnosed patients was recommended by the German National Action Plan. In this paper we focus on the question on how such a registry for undiagnosed patients can be built and which information it should contain.

RESULTS

To develop a registry for undiagnosed patients, a software for data acquisition and storage, an appropriate data set and an applicable terminology/classification system for the data collected are needed. We have used the open-source software Open-Source Registry System for Rare Diseases (OSSE) to build the registry for undiagnosed patients. Our data set is based on the minimal data set for rare disease patient registries recommended by the European Rare Disease Registries Platform. We extended this Common Data Set to also include symptoms, clinical findings and other diagnoses. In order to ensure findability, comparability and statistical analysis, symptoms, clinical findings and diagnoses have to be encoded. We evaluated three medical ontologies (SNOMED CT, HPO and LOINC) for their usefulness. With exact matches of 98% of tested medical terms, a mean number of five deposited synonyms, SNOMED CT seemed to fit our needs best. HPO and LOINC provided 73% and 31% of exacts matches of clinical terms respectively. Allowing more generic codes for a defined symptom, with SNOMED CT 99%, with HPO 89% and with LOINC 39% of terms could be encoded.

CONCLUSIONS

With the use of the OSSE software and a data set, which, in addition to the Common Data Set, focuses on symptoms and clinical findings, a functioning and meaningful registry for undiagnosed patients can be implemented. The next step is the implementation of the registry in centres for rare diseases. With the help of medical informatics and big data analysis, case similarity analyses could be realized and aid as a decision-support tool enabling diagnosis of some undiagnosed patients.

The role of phenotype-based search approaches using public online databases in diagnostics of Mendelian disorders

PURPOSE

To investigate the effectiveness of phenotype-based search approaches using publicly available online databases.

METHODS

We included consecutively solved cases from our exome database. For each case, the combination of Human Phenotype Ontology terms reported by the referring clinician was used to perform a search in three commonly used databases: OMIM (first 300 results), Phenolyzer (first 300 results), and Mendelian (all 100 results).

RESULTS

One hundred cases were included (43 females; mean age: 10 years). The actual molecular diagnosis identified through exome sequencing was not included in the search results of any of the queried databases in 33% of cases. In 85% of cases it was not found within the top five search results. When included, its median rank was 61 (range: 1-295), 21 (1-270), and 29 (1-92) in OMIM, Phenolyzer and Mendelian, respectively.

CONCLUSION

This study demonstrates that, in most cases, phenotype-based search approaches using public online databases is ineffective in providing a probable diagnosis for Mendelian conditions. Genotype-first approach through molecular-guided diagnostics with backward phenotyping may be a more appropriate approach for these disorders, unless a specific diagnosis is considered a priori based on highly unique phenotypic features or a specific facial gestalt.

A flexible computational pipeline for research analyses of unsolved clinical exome cases

Exome sequencing has enabled molecular diagnoses for rare disease patients but often with initial diagnostic rates of ~25-30%. Here we develop a robust computational pipeline to rank variants for reassessment of unsolved rare disease patients. A comprehensive web-based patient report is generated in which all deleterious variants can be filtered by gene, variant characteristics, OMIM disease and Phenolyzer scores, and all are annotated with an ACMG classification and links to ClinVar. The pipeline ranked 21/34 previously diagnosed variants as top, with 26 in total ranked ≤7th, 3 ranked ≥13th; 5 failed the pipeline filters. Pathogenic/likely pathogenic variants by ACMG criteria were identified for 22/145 unsolved cases, and a previously undefined candidate disease variant for 27/145. This open access pipeline supports the partnership between clinical and research laboratories to improve the diagnosis of unsolved exomes. It provides a flexible framework for iterative developments to further improve diagnosis.

A pipeline-friendly software tool for genome diagnostics to prioritize genes by matching patient symptoms to literature

Despite an explosive growth of next-generation sequencing data, genome diagnostics only provides a molecular diagnosis to a minority of patients. Software tools that prioritize genes based on patient symptoms using known gene-disease associations may complement variant filtering and interpretation to increase chances of success. However, many of these tools cannot be used in practice because they are embedded within variant prioritization algorithms, or exist as remote services that cannot be relied upon or are unacceptable because of legal/ethical barriers. In addition, many tools are not designed for command-line usage, closed-source, abandoned, or unavailable. We present Variant Interpretation using Biomedical literature Evidence (VIBE), a tool to prioritize disease genes based on Human Phenotype Ontology codes. VIBE is a locally installed executable that ensures operational availability and is built upon DisGeNET-RDF, a comprehensive knowledge platform containing gene-disease associations mostly from literature and variant-disease associations mostly from curated source databases. VIBE's command-line interface and output are designed for easy incorporation into bioinformatic pipelines that annotate and prioritize variants for further clinical interpretation. We evaluate VIBE in a benchmark based on 305 patient cases alongside seven other tools. Our results demonstrate that VIBE offers consistent performance with few cases missed, but we also find high complementarity among all tested tools. VIBE is a powerful, free, open source and locally installable solution for prioritizing genes based on patient symptoms. Project source code, documentation, benchmark and executables are available at https://github.com/molgenis/vibe.

Healthcare Applications of Artificial Intelligence and Analytics: A Review and Proposed Framework

Healthcare is considered as one of the most promising application areas for artificial intelligence and analytics (AIA) just after the emergence of the latter. AI combined to analytics technologies is increasingly changing medical practice and healthcare in an impressive way using efficient algorithms from various branches of information technology (IT). Indeed, numerous works are published every year in several universities and innovation centers worldwide, but there are concerns about progress in their effective success. There are growing examples of AIA being implemented in healthcare with promising results. This review paper summarizes the past 5 years of healthcare applications of AIA, across different techniques and medical specialties, and discusses the current issues and challenges, related to this revolutionary technology. A total of 24,782 articles were identified. The aim of this paper is to provide the research community with the necessary background to push this field even further and propose a framework that will help integrate diverse AIA technologies around patient needs in various healthcare contexts, especially for chronic care patients, who present the most complex comorbidities and care needs.

Improving diagnosis for rare diseases: the experience of the Italian undiagnosed Rare diseases network

Background

For a number of persons with rare diseases (RDs) a definite diagnosis remains undiscovered with relevant physical, psychological and social consequences. Undiagnosed RDs (URDs) require other than specialised clinical centres, outstanding molecular investigations, common protocols and dedicated actions at national and international levels; thus, many “Undiagnosed RDs programs” have been gradually developed on the grounds of a well-structured multidisciplinary approach.

Methods

The Italian Undiagnosed Rare Diseases Network (IURDN) was established in 2016 to improve the level of diagnosis of persons with URD living in Italy. Six Italian Centres of Expertise represented the network. The National Centre for Rare Diseases at the Istituto Superiore di Sanità coordinates the whole project. The software PhenoTips was used to collect the information of the clinical cases.

Results

One hundred and ten cases were analysed between March 2016 and June 2019. The age of onset of the diseases ranged from prenatal age to 51 years. Conditions were predominantly sporadic; almost all patients had multiple organs involvements. A total of 13/71 family cases were characterized by WES; in some families more than one individual was affected, so leading to 20/71 individuals investigated. Disease causing variants were identified in two cases and were associated to previously undescribed phenotypes. In 5 cases, new candidate genes were identified, although confirmatory tests are pending. In three families, investigations were not completed due to the scarce compliance of members and molecular investigations were temporary suspended. Finally, three cases (one familial) remain still unsolved. Twelve undiagnosed clinical cases were then selected to be shared at International level through PhenomeCentral in accordance to the UDNI statement.

Conclusions

Our results showed a molecular diagnostic yield of 53,8%; this value is comparable to the diagnostic rates reported in other international studies. Cases collected were also pooled with those collected by UDNI International Network. This represents a unique example of global initiative aimed at sharing and validating knowledge and experience in this field. IURDN is a multidisciplinary and useful initiative linking National and International efforts aimed at making timely and appropriate diagnoses in RD patients who still do not have a confirmed diagnosis even after a long time.

Ontologies, Knowledge Representation, and Machine Learning for Translational Research: Recent Contributions

Objectives : To select, present, and summarize the most relevant papers published in 2018 and 2019 in the field of Ontologies and Knowledge Representation, with a particular focus on the intersection between Ontologies and Machine Learning.

Methods : A comprehensive review of the medical informatics literature was performed to select the most interesting papers published in 2018 and 2019 and that document the utility of ontologies for computational analysis, including machine learning.

Results : Fifteen articles were selected for inclusion in this survey paper. The chosen articles belong to three major themes: (i) the identification of phenotypic abnormalities in electronic health record (EHR) data using the Human Phenotype Ontology ; (ii) word and node embedding algorithms to supplement natural language processing (NLP) of EHRs and other medical texts; and (iii) hybrid ontology and NLP-based approaches to extracting structured and unstructured components of EHRs.

Conclusion : Unprecedented amounts of clinically relevant data are now available for clinical and research use. Machine learning is increasingly being applied to these data sources for predictive analytics, precision medicine, and differential diagnosis. Ontologies have become an essential component of software pipelines designed to extract, code, and analyze clinical information by machine learning algorithms. The intersection of machine learning and semantics is proving to be an innovative space in clinical research.

Machine learning, the kidney, and genotype-phenotype analysis

With biomedical research transitioning into data-rich science, machine learning provides a powerful toolkit for extracting knowledge from large-scale biological data sets. The increasing availability of comprehensive kidney omics compendia (transcriptomics, proteomics, metabolomics, and genome sequencing), as well as other data modalities such as electronic health records, digital nephropathology repositories, and radiology renal images, makes machine learning approaches increasingly essential for analyzing human kidney data sets. Here, we discuss how machine learning approaches can be applied to the study of kidney disease, with a particular focus on how they can be used for understanding the relationship between genotype and phenotype.