PEDIA: prioritization of exome data by image analysis

Artificial intelligence-driven genotype-epigenotype-phenotype approaches to resolve challenges in syndrome diagnostics

BACKGROUND

Decisions to split two or more phenotypic manifestations related to genetic variations within the same gene can be challenging, especially during the early stages of syndrome discovery. Genotype-based diagnostics with artificial intelligence (AI)-driven approaches using next-generation phenotyping (NGP) and DNA methylation (DNAm) can be utilized to expedite syndrome delineation within a single gene.

METHODS

We utilized an expanded cohort of 56 patients (22 previously unpublished individuals) with truncating variants in the MN1 gene and attempted different methods to assess plausible strategies to objectively delineate phenotypic differences between the C-Terminal Truncation (CTT) and N-Terminal Truncation (NTT) groups. This involved transcriptomics analysis on available patient fibroblast samples and AI-assisted approaches, including a new statistical method of GestaltMatcher on facial photos and blood DNAm analysis using a support vector machine (SVM) model.

FINDINGS

RNA-seq analysis was unable to show a significant difference in transcript expression despite our previous hypothesis that NTT variants would induce nonsense mediated decay. DNAm analysis on nine blood DNA samples revealed an episignature for the CTT group. In parallel, the new statistical method of GestaltMatcher objectively distinguished the CTT and NTT groups with a low requirement for cohort number. Validation of this approach was performed on syndromes with known DNAm signatures of SRCAP, SMARCA2 and ADNP to demonstrate the effectiveness of this approach.

INTERPRETATION

We demonstrate the potential of using AI-based technologies to leverage genotype, phenotype and epigenetics data in facilitating splitting decisions in diagnosis of syndromes with minimal sample requirement.

FUNDING

The specific funding of this article is provided in the acknowledgements section.

GestaltGAN: synthetic photorealistic portraits of individuals with rare genetic disorders

The facial gestalt (overall facial morphology) is a characteristic clinical feature in many genetic disorders that is often essential for suspecting and establishing a specific diagnosis. Therefore, publishing images of individuals affected by pathogenic variants in disease-associated genes has been an important part of scientific communication. Furthermore, medical imaging data is also crucial for teaching and training deep-learning models such as GestaltMatcher. However, medical data is often sparsely available, and sharing patient images involves risks related to privacy and re-identification. Therefore, we explored whether generative neural networks can be used to synthesize accurate portraits for rare disorders. We modified a StyleGAN architecture and trained it to produce artificial condition-specific portraits for multiple disorders. In addition, we present a technique that generates a sharp and detailed average patient portrait for a given disorder. We trained our GestaltGAN on the 20 most frequent disorders from the GestaltMatcher database. We used REAL-ESRGAN to increase the resolution of portraits from the training data with low-quality and colorized black-and-white images. To augment the model's understanding of human facial features, an unaffected class was introduced to the training data. We tested the validity of our generated portraits with 63 human experts. Our findings demonstrate the model's proficiency in generating photorealistic portraits that capture the characteristic features of a disorder while preserving patient privacy. Overall, the output from our approach holds promise for various applications, including visualizations for publications and educational materials and augmenting training data for deep learning.

Artificial intelligence in clinical genetics

Artificial intelligence (AI) has been growing more powerful and accessible, and will increasingly impact many areas, including virtually all aspects of medicine and biomedical research. This review focuses on previous, current, and especially emerging applications of AI in clinical genetics. Topics covered include a brief explanation of different general categories of AI, including machine learning, deep learning, and generative AI. After introductory explanations and examples, the review discusses AI in clinical genetics in three main categories: clinical diagnostics; management and therapeutics; clinical support. The review concludes with short, medium, and long-term predictions about the ways that AI may affect the field of clinical genetics. Overall, while the precise speed at which AI will continue to change clinical genetics is unclear, as are the overall ramifications for patients, families, clinicians, researchers, and others, it is likely that AI will result in dramatic evolution in clinical genetics. It will be important for all those involved in clinical genetics to prepare accordingly in order to minimize the risks and maximize benefits related to the use of AI in the field.

GestaltMatcher Database - A global reference for facial phenotypic variability in rare human diseases

The most important factor that complicates the work of dysmorphologists is the significant phenotypic variability of the human face. Next-Generation Phenotyping (NGP) tools that assist clinicians with recognizing characteristic syndromic patterns are particularly challenged when confronted with patients from populations different from their training data. To that end, we systematically analyzed the impact of genetic ancestry on facial dysmorphism. For that purpose, we established the GestaltMatcher Database (GMDB) as a reference dataset for medical images of patients with rare genetic disorders from around the world. We collected 10,980 frontal facial images - more than a quarter previously unpublished - from 8,346 patients, representing 581 rare disorders. Although the predominant ancestry is still European (67%), data from underrepresented populations have been increased considerably via global collaborations (19% Asian and 7% African). This includes previously unpublished reports for more than 40% of the African patients. The NGP analysis on this diverse dataset revealed characteristic performance differences depending on the composition of training and test sets corresponding to genetic relatedness. For clinical use of NGP, incorporating non-European patients resulted in a profound enhancement of GestaltMatcher performance. The top-5 accuracy rate increased by +11.29%. Importantly, this improvement in delineating the correct disorder from a facial portrait was achieved without decreasing the performance on European patients. By design, GMDB complies with the FAIR principles by rendering the curated medical data findable, accessible, interoperable, and reusable. This means GMDB can also serve as data for training and benchmarking. In summary, our study on facial dysmorphism on a global sample revealed a considerable cross ancestral phenotypic variability confounding NGP that should be counteracted by international efforts for increasing data diversity. GMDB will serve as a vital reference database for clinicians and a transparent training set for advancing NGP technology.

Acromesomelic Dysplasia With Homozygosity for a Likely Pathogenic BMPR1B Variant: Postaxial Polydactyly as a Novel Clinical Finding

BACKGROUND

Acromesomelic chondrodysplasias are a rare subgroup of the clinically and genetically heterogeneous osteochondrodysplasias that are characterised by abnormalities in the limb development and short stature. Here, we report a 2-year-old boy, offspring of consanguineous parents, with acromesomelic dysplasia and postaxial polydactyly in which exome sequencing identified a novel homozygous missense variant in BMPR1B. The patient showed skeletal malformation of both hands and feet that included complex brachydactyly with the thumbs most severely affected, postaxial polydactyly of both hands, shortened toes as well as a bilateral hypoplasia of the fibula.

METHODS

Whole trio exome sequencing was conducted to identify potential genetic variants in the patient.

RESULTS

The analysis identified the biallelic variant NM_001203.3:c.821A > G;p.(Gln274Arg) in BMPR1B, a gene encoding bone morphogenetic protein receptor 1B.

CONCLUSION

The skeletal phenotype can be brought in line with the phenotypes of previously reported cases of BMPR1B-associated chondrodysplasias. However, the postaxial polydactyly described here is a novel clinical finding in a BMPR1B-related case; notably, it has previously been reported in other acromesomelic dysplasia cases caused by homozygous pathogenic variants in GDF5-a gene which encodes for growth differentiation factor 5, a high-affinity ligand to BMPR1B.

Next-generation phenotyping in Nigerian children with Cornelia de Lange syndrome

Next-generation phenotyping (NGP) can be used to compute the similarity of dysmorphic patients to known syndromic diseases. So far, the technology has been evaluated in variant prioritization and classification, providing evidence for pathogenicity if the phenotype matched with other patients with a confirmed molecular diagnosis. In a Nigerian cohort of individuals with facial dysmorphism, we used the NGP tool GestaltMatcher to screen portraits prior to genetic testing and subjected individuals with high similarity scores to exome sequencing (ES). Here, we report on two individuals with global developmental delay, pulmonary artery stenosis, and genital and limb malformations for whom GestaltMatcher yielded Cornelia de Lange syndrome (CdLS) as the top hit. ES revealed a known pathogenic nonsense variant, NM_133433.4: c.598C>T; p.(Gln200*), as well as a novel frameshift variant c.7948dup; p.(Ile2650Asnfs*11) in NIPBL. Our results suggest that NGP can be used as a screening tool and thresholds could be defined for achieving high diagnostic yields in ES. Training the artificial intelligence (AI) with additional cases of the same ethnicity might further increase the positive predictive value of GestaltMatcher.

Next-generation phenotyping integrated in a national framework for patients with ultrarare disorders improves genetic diagnostics and yields new molecular findings

Individuals with ultrarare disorders pose a structural challenge for healthcare systems since expert clinical knowledge is required to establish diagnoses. In TRANSLATE NAMSE, a 3-year prospective study, we evaluated a novel diagnostic concept based on multidisciplinary expertise in Germany. Here we present the systematic investigation of the phenotypic and molecular genetic data of 1,577 patients who had undergone exome sequencing and were partially analyzed with next-generation phenotyping approaches. Molecular genetic diagnoses were established in 32% of the patients totaling 370 distinct molecular genetic causes, most with prevalence below 1:50,000. During the diagnostic process, 34 novel and 23 candidate genotype-phenotype associations were identified, mainly in individuals with neurodevelopmental disorders. Sequencing data of the subcohort that consented to computer-assisted analysis of their facial images with GestaltMatcher could be prioritized more efficiently compared with approaches based solely on clinical features and molecular scores. Our study demonstrates the synergy of using next-generation sequencing and phenotyping for diagnosing ultrarare diseases in routine healthcare and discovering novel etiologies by multidisciplinary teams.

Should AI-Powered Whole-Genome Sequencing Be Used Routinely for Personalized Decision Support in Surgical Oncology—A Scoping Review

In this scoping review, we delve into the transformative potential of artificial intelligence (AI) in addressing challenges inherent in whole-genome sequencing (WGS) analysis, with a specific focus on its implications in oncology. Unveiling the limitations of existing sequencing technologies, the review illuminates how AI-powered methods emerge as innovative solutions to surmount these obstacles. The evolution of DNA sequencing technologies, progressing from Sanger sequencing to next-generation sequencing, sets the backdrop for AI’s emergence as a potent ally in processing and analyzing the voluminous genomic data generated. Particularly, deep learning methods play a pivotal role in extracting knowledge and discerning patterns from the vast landscape of genomic information. In the context of oncology, AI-powered methods exhibit considerable potential across diverse facets of WGS analysis, including variant calling, structural variation identification, and pharmacogenomic analysis. This review underscores the significance of multimodal approaches in diagnoses and therapies, highlighting the importance of ongoing research and development in AI-powered WGS techniques. Integrating AI into the analytical framework empowers scientists and clinicians to unravel the intricate interplay of genomics within the realm of multi-omics research, paving the way for more successful personalized and targeted treatments.

Molecular mechanisms of human overgrowth and use of omics in its diagnostics: chances and challenges

Overgrowth disorders comprise a group of entities with a variable phenotypic spectrum ranging from tall stature to isolated or lateralized overgrowth of body parts and or organs. Depending on the underlying physiological pathway affected by pathogenic genetic alterations, overgrowth syndromes are associated with a broad spectrum of neoplasia predisposition, (cardio) vascular and neurodevelopmental anomalies, and dysmorphisms. Pathologic overgrowth may be of prenatal or postnatal onset. It either results from an increased number of cells (intrinsic cellular hyperplasia), hypertrophy of the normal number of cells, an increase in interstitial spaces, or from a combination of all of these. The underlying molecular causes comprise a growing number of genetic alterations affecting skeletal growth and Growth-relevant signaling cascades as major effectors, and they can affect the whole body or parts of it (mosaicism). Furthermore, epigenetic modifications play a critical role in the manifestation of some overgrowth diseases. The diagnosis of overgrowth syndromes as the prerequisite of a personalized clinical management can be challenging, due to their clinical and molecular heterogeneity. Physicians should consider molecular genetic testing as a first diagnostic step in overgrowth syndromes. In particular, the urgent need for a precise diagnosis in tumor predisposition syndromes has to be taken into account as the basis for an early monitoring and therapy. With the (future) implementation of next-generation sequencing approaches and further omic technologies, clinical diagnoses can not only be verified, but they also confirm the clinical and molecular spectrum of overgrowth disorders, including unexpected findings and identification of atypical cases. However, the limitations of the applied assays have to be considered, for each of the disorders of interest, the spectrum of possible types of genomic variants has to be considered as they might require different methodological strategies. Additionally, the integration of artificial intelligence (AI) in diagnostic workflows significantly contribute to the phenotype-driven selection and interpretation of molecular and physiological data.

GestaltMML: Enhancing Rare Genetic Disease Diagnosis through Multimodal Machine Learning Combining Facial Images and Clinical Texts

Individuals with suspected rare genetic disorders often undergo multiple clinical evaluations, imaging studies, laboratory tests and genetic tests, to find a possible answer over a prolonged period of time. Addressing this "diagnostic odyssey" thus has substantial clinical, psychosocial, and economic benefits. Many rare genetic diseases have distinctive facial features, which can be used by artificial intelligence algorithms to facilitate clinical diagnosis, in prioritizing candidate diseases to be further examined by lab tests or genetic assays, or in helping the phenotype-driven reinterpretation of genome/exome sequencing data. Existing methods using frontal facial photos were built on conventional Convolutional Neural Networks (CNNs), rely exclusively on facial images, and cannot capture non-facial phenotypic traits and demographic information essential for guiding accurate diagnoses. Here we introduce GestaltMML, a multimodal machine learning (MML) approach solely based on the Transformer architecture. It integrates facial images, demographic information (age, sex, ethnicity), and clinical notes (optionally, a list of Human Phenotype Ontology terms) to improve prediction accuracy. Furthermore, we also evaluated GestaltMML on a diverse range of datasets, including 528 diseases from the GestaltMatcher Database, several in-house datasets of Beckwith-Wiedemann syndrome (BWS, over-growth syndrome with distinct facial features), Sotos syndrome (overgrowth syndrome with overlapping features with BWS), NAA10-related neurodevelopmental syndrome, Cornelia de Lange syndrome (multiple malformation syndrome), and KBG syndrome (multiple malformation syndrome). Our results suggest that GestaltMML effectively incorporates multiple modalities of data, greatly narrowing candidate genetic diagnoses of rare diseases and may facilitate the reinterpretation of genome/exome sequencing data.

Computational frameworks integrating deep learning and statistical models in mining multimodal omics data

BACKGROUND

In health research, multimodal omics data analysis is widely used to address important clinical and biological questions. Traditional statistical methods rely on the strong assumptions of distribution. Statistical methods such as testing and differential expression are commonly used in omics analysis. Deep learning, on the other hand, is an advanced computer science technique that is powerful in mining high-dimensional omics data for prediction tasks. Recently, integrative frameworks or methods have been developed for omics studies that combine statistical models and deep learning algorithms.

METHODS AND RESULTS

The aim of these integrative frameworks is to combine the strengths of both statistical methods and deep learning algorithms to improve prediction accuracy while also providing interpretability and explainability. This review report discusses the current state-of-the-art integrative frameworks, their limitations, and potential future directions in survival and time-to-event longitudinal analysis, dimension reduction and clustering, regression and classification, feature selection, and causal and transfer learning.

Enhancing Variant Prioritization in VarFish through On-Premise Computational Facial Analysis

Genomic variant prioritization is crucial for identifying disease-associated genetic variations. Integrating facial and clinical feature analyses into this process enhances performance. This study demonstrates the integration of facial analysis (GestaltMatcher) and Human Phenotype Ontology analysis (CADA) within VarFish, an open-source variant analysis framework. Challenges related to non-open-source components were addressed by providing an open-source version of GestaltMatcher, facilitating on-premise facial analysis to address data privacy concerns. Performance evaluation on 163 patients recruited from a German multi-center study of rare diseases showed PEDIA's superior accuracy in variant prioritization compared to individual scores. This study highlights the importance of further benchmarking and future integration of advanced facial analysis approaches aligned with ACMG guidelines to enhance variant classification.

Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study

BACKGROUND

While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism.

OBJECTIVE

We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt.

METHODS

Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity.

RESULTS

DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88%, SD 18%) than for GestaltMatcher (76%, SD 26%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score's levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores.

CONCLUSIONS

If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face.

Artificial intelligence and the impact on medical genetics

Virtually all areas of biomedicine will be increasingly affected by applications of artificial intelligence (AI). We discuss how AI may affect fields of medical genetics, including both clinicians and laboratorians. In addition to reviewing the anticipated impact, we provide recommendations for ways in which these groups may want to evolve in light of the influence of AI. We also briefly discuss how educational and training programs can play a key role in preparing the future workforce given these anticipated changes.

Computational facial analysis for rare Mendelian disorders

With the advances in computer vision, computational facial analysis has become a powerful and effective tool for diagnosing rare disorders. This technology, also called next-generation phenotyping (NGP), has progressed significantly over the last decade. This review paper will introduce three key NGP approaches. In 2014, Ferry et al. first presented Clinical Face Phenotype Space (CFPS) trained on eight syndromes. After 5 years, Gurovich et al. proposed DeepGestalt, a deep convolutional neural network trained on more than 21,000 patient images with 216 disorders. It was considered a state-of-the-art disorder classification framework. In 2022, Hsieh et al. developed GestaltMatcher to support the ultra-rare and novel disorders not supported in DeepGestalt. It further enabled the analysis of facial similarity presented in a given cohort or multiple disorders. Moreover, this article will present the usage of NGP for variant prioritization and facial gestalt delineation. Although NGP approaches have proven their capability in assisting the diagnosis of many disorders, many limitations remain. This article will introduce two future directions to address two main limitations: enabling the global collaboration for a medical imaging database that fulfills the FAIR principles and synthesizing patient images to protect patient privacy. In the end, with more and more NGP approaches emerging, we envision that the NGP technology can assist clinicians and researchers in diagnosing patients and analyzing disorders in multiple directions in the near future.

PhenoScore quantifies phenotypic variation for rare genetic diseases by combining facial analysis with other clinical features using a machine-learning framework

Several molecular and phenotypic algorithms exist that establish genotype-phenotype correlations, including facial recognition tools. However, no unified framework that investigates both facial data and other phenotypic data directly from individuals exists. We developed PhenoScore: an open-source, artificial intelligence-based phenomics framework, combining facial recognition technology with Human Phenotype Ontology data analysis to quantify phenotypic similarity. Here we show PhenoScore's ability to recognize distinct phenotypic entities by establishing recognizable phenotypes for 37 of 40 investigated syndromes against clinical features observed in individuals with other neurodevelopmental disorders and show it is an improvement on existing approaches. PhenoScore provides predictions for individuals with variants of unknown significance and enables sophisticated genotype-phenotype studies by testing hypotheses on possible phenotypic (sub)groups. PhenoScore confirmed previously known phenotypic subgroups caused by variants in the same gene for SATB1, SETBP1 and DEAF1 and provides objective clinical evidence for two distinct ADNP-related phenotypes, already established functionally.

Krawitz PDMDPP. The future role of facial image analysis in ACMG classification guidelines

The use of next-generation sequencing (NGS) has dramatically improved the diagnosis of rare diseases. However, the analysis of genomic data has become complex with the increasing detection of variants by exome and genome sequencing. The American College of Medical Genetics and Genomics (ACMG) and the Association for Molecular Pathology (AMP) developed a 5-tier classification scheme in 2015 for variant interpretation, that has since been widely adopted. Despite efforts to minimise discrepancies in the application of these criteria, inconsistencies still occur. Further specifications for individual genes were developed by Variant Curation Expert Panels (VCEPs) of the Clinical Genome Resource (ClinGen) consortium, that also take into consideration gene or disease specific features. For instance, in disorders with a highly characerstic facial gestalt a "phenotypic match" (PP4) has higher pathogenic evidence than e.g. in a non-syndromic form of intellectual disability. With computational approaches for quantifying the similarity of dysmorphic features results of such analysis can now be used in a refined Bayesian framework for the ACMG/AMP criteria.

Carney complex- why thorough medical history taking is so important - report of three cases and review of the literature

PURPOSE

To present a new case series and to review the literature on Carney complex (CNC) with an emphasis on highlighting key clinical features of the disease and pointing out possibilities of shortening the diagnostic process.

METHOD

Searches of PubMed, identifying relevant reports up to April 2022.

RESULTS

CNC is a rare, autosomally dominant inherited neoplasia -endocrinopathy syndrome with high clinical variability, even among members of the same family. Data on length of diagnostic process are scarce with numerous case series reporting a diagnostic delay of decades. Suggestions to shorten the diagnostic process includes awareness of the multi-faceted clinical presentations of CNC, thorough history taking of index patients and family members and awareness of diagnostic pitfalls. Importantly, unusual symptom combinations should alert the clinician to suspect a rare endocrinopathy syndrome such as CNC. Already present and coming on the horizon are databases and novel phenotyping technologies that will aid endocrinologists in their quest for timely diagnosis.

CONCLUSION

In this review, we examine the current state of knowledge in CNC and suggest avenues for shortening the diagnostic journey for the afflicted patients.

A diagnostic support system based on pain drawings: binary and k-disease classification of EDS, GBS, FSHD, PROMM, and a control group with Pain2D

BACKGROUND AND OBJECTIVE

The diagnosis of rare diseases (RDs) is often challenging due to their rarity, variability and the high number of individual RDs, resulting in a delay in diagnosis with adverse effects for patients and healthcare systems. The development of computer assisted diagnostic decision support systems could help to improve these problems by supporting differential diagnosis and by prompting physicians to initiate the right diagnostic tests. Towards this end, we developed, trained and tested a machine learning model implemented as part of the software called Pain2D to classify four rare diseases (EDS, GBS, FSHD and PROMM), as well as a control group of unspecific chronic pain, from pen-and-paper pain drawings filled in by patients.

METHODS

Pain drawings (PDs) were collected from patients suffering from one of the four RDs, or from unspecific chronic pain. The latter PDs were used as an outgroup in order to test how Pain2D handles more common pain causes. A total of 262 (59 EDS, 29 GBS, 35 FSHD, 89 PROMM, 50 unspecific chronic pain) PDs were collected and used to generate disease specific pain profiles. PDs were then classified by Pain2D in a leave-one-out-cross-validation approach.

RESULTS

Pain2D was able to classify the four rare diseases with an accuracy of 61-77% with its binary classifier. EDS, GBS and FSHD were classified correctly by the Pain2D k-disease classifier with sensitivities between 63 and 86% and specificities between 81 and 89%. For PROMM, the k-disease classifier achieved a sensitivity of 51% and specificity of 90%.

CONCLUSIONS

Pain2D is a scalable, open-source tool that could potentially be trained for all diseases presenting with pain.

Perspectives on the future of dysmorphology

The field of clinical genetics and genomics continues to evolve. In the past few decades, milestones like the initial sequencing of the human genome, dramatic changes in sequencing technologies, and the introduction of artificial intelligence, have upended the field and offered fascinating new insights. Though difficult to predict the precise paths the field will follow, rapid change may continue to be inevitable. Within genetics, the practice of dysmorphology, as defined by pioneering geneticist David W. Smith in the 1960s as "the study of, or general subject of abnormal development of tissue form" has also been affected by technological advances as well as more general trends in biomedicine. To address possibilities, potential, and perils regarding the future of dysmorphology, a group of clinical geneticists, representing different career stages, areas of focus, and geographic regions, have contributed to this piece by providing insights about how the practice of dysmorphology will develop over the next several decades.

Deciphering Intellectual Disability

Intellectual disability (ID) is a common cause of referral to the pediatricians, geneticists, and pediatric neurologists. A thorough clinical evaluation and a stepwise investigative approach using a combination of traditional genetic techniques and appropriate latest genomic technologies can help in arriving at a diagnosis. In the current "omics" era, adopting a multiomics approach would further assist in solving the undiagnosed cases with intellectual disability.

KBG syndrome: videoconferencing and use of artificial intelligence driven facial phenotyping in 25 new patients

Genetic variants in Ankyrin Repeat Domain 11 (ANKRD11) and deletions in 16q24.3 are known to cause KBG syndrome, a rare syndrome associated with craniofacial, intellectual, and neurobehavioral anomalies. We report 25 unpublished individuals from 22 families with molecularly confirmed diagnoses. Twelve individuals have de novo variants, three have inherited variants, and one is inherited from a parent with low-level mosaicism. The mode of inheritance was unknown for nine individuals. Twenty are truncating variants, and the remaining five are missense (three of which are found in one family). We present a protocol emphasizing the use of videoconference and artificial intelligence (AI) in collecting and analyzing data for this rare syndrome. A single clinician interviewed 25 individuals throughout eight countries. Participants' medical records were reviewed, and data was uploaded to the Human Disease Gene website using Human Phenotype Ontology (HPO) terms. Photos of the participants were analyzed by the GestaltMatcher and DeepGestalt, Face2Gene platform (FDNA Inc, USA) algorithms. Within our cohort, common traits included short stature, macrodontia, anteverted nares, wide nasal bridge, wide nasal base, thick eyebrows, synophrys and hypertelorism. Behavioral issues and global developmental delays were widely present. Neurologic abnormalities including seizures and/or EEG abnormalities were common (44%), suggesting that early detection and seizure prophylaxis could be an important point of intervention. Almost a quarter (24%) were diagnosed with attention deficit hyperactivity disorder and 28% were diagnosed with autism spectrum disorder. Based on the data, we provide a set of recommendations regarding diagnostic and treatment approaches for KBG syndrome.

Look-alike humans identified by facial recognition algorithms show genetic similarities

The human face is one of the most visible features of our unique identity as individuals. Interestingly, monozygotic twins share almost identical facial traits and the same DNA sequence but could exhibit differences in other biometrical parameters. The expansion of the world wide web and the possibility to exchange pictures of humans across the planet has increased the number of people identified online as virtual twins or doubles that are not family related. Herein, we have characterized in detail a set of "look-alike" humans, defined by facial recognition algorithms, for their multiomics landscape. We report that these individuals share similar genotypes and differ in their DNA methylation and microbiome landscape. These results not only provide insights about the genetics that determine our face but also might have implications for the establishment of other human anthropometric properties and even personality characteristics.

A review of deep learning applications in human genomics using next-generation sequencing data

Genomics is advancing towards data-driven science. Through the advent of high-throughput data generating technologies in human genomics, we are overwhelmed with the heap of genomic data. To extract knowledge and pattern out of this genomic data, artificial intelligence especially deep learning methods has been instrumental. In the current review, we address development and application of deep learning methods/models in different subarea of human genomics. We assessed over- and under-charted area of genomics by deep learning techniques. Deep learning algorithms underlying the genomic tools have been discussed briefly in later part of this review. Finally, we discussed briefly about the late application of deep learning tools in genomic. Conclusively, this review is timely for biotechnology or genomic scientists in order to guide them why, when and how to use deep learning methods to analyse human genomic data.

Evaluation of phenotype-driven gene prioritization methods for Mendelian diseases

It’s challenging work to identify disease-causing genes from the next-generation sequencing (NGS) data of patients with Mendelian disorders. To improve this situation, researchers have developed many phenotype-driven gene prioritization methods using a patient’s genotype and phenotype information, or phenotype information only as input to rank the candidate’s pathogenic genes. Evaluations of these ranking methods provide practitioners with convenience for choosing an appropriate tool for their workflows, but retrospective benchmarks are underpowered to provide statistically significant results in their attempt to differentiate. In this research, the performance of ten recognized causal-gene prioritization methods was benchmarked using 305 cases from the Deciphering Developmental Disorders (DDD) project and 209 in-house cases via a relatively unbiased methodology. The evaluation results show that methods using Human Phenotype Ontology (HPO) terms and Variant Call Format (VCF) files as input achieved better overall performance than those using phenotypic data alone. Besides, LIRICAL and AMELIE, two of the best methods in our benchmark experiments, complement each other in cases with the causal genes ranked highly, suggesting a possible integrative approach to further enhance the diagnostic efficiency. Our benchmarking provides valuable reference information to the computer-assisted rapid diagnosis in Mendelian diseases and sheds some light on the potential direction of future improvement on disease-causing gene prioritization methods.

Knowledge-based approaches to drug discovery for rare diseases

The conventional drug discovery pipeline has proven to be unsustainable for rare diseases. Herein, we discuss recent advances in biomedical knowledge mining applied to discovering therapeutics for rare diseases. We summarize current chemogenomics data of relevance to rare diseases and provide a perspective on the effectiveness of machine learning (ML) and biomedical knowledge graph mining in rare disease drug discovery. We illustrate the power of these methodologies using a chordoma case study. We expect that a broader application of knowledge graph mining and artificial intelligence (AI) approaches will expedite the discovery of viable drug candidates against both rare and common diseases.

Mitochondrial "dysmorphology" in variant classification

Mitochondrial disorders are challenging to diagnose. Exome sequencing has greatly enhanced the diagnostic precision of these disorders although interpreting variants of uncertain significance (VUS) remains a formidable obstacle. Whether specific mitochondrial morphological changes can aid in the classification of these variants is unknown. Here, we describe two families (four patients), each with a VUS in a gene known to affect the morphology of mitochondria through a specific role in the fission-fusion balance. In the first, the missense variant in MFF, encoding a fission factor, was associated with impaired fission giving rise to a characteristically over-tubular appearance of mitochondria. In the second, the missense variant in DNAJA3, which has no listed OMIM phenotype, was associated with fragmented appearance of mitochondria consistent with its published deficiency states. In both instances, the highly specific phenotypes allowed us to upgrade the classification of the variants. Our results suggest that, in select cases, mitochondrial "dysmorphology" can be helpful in interpreting variants to reach a molecular diagnosis.

CADA: phenotype-driven gene prioritization based on a case-enriched knowledge graph

Many rare syndromes can be well described and delineated from other disorders by a combination of characteristic symptoms. These phenotypic features are best documented with terms of the Human Phenotype Ontology (HPO), which are increasingly used in electronic health records (EHRs), too. Many algorithms that perform HPO-based gene prioritization have also been developed; however, the performance of many such tools suffers from an over-representation of atypical cases in the medical literature. This is certainly the case if the algorithm cannot handle features that occur with reduced frequency in a disorder. With Cada, we built a knowledge graph based on both case annotations and disorder annotations. Using network representation learning, we achieve gene prioritization by link prediction. Our results suggest that Cada exhibits superior performance particularly for patients that present with the pathognomonic findings of a disease. Additionally, information about the frequency of occurrence of a feature can readily be incorporated, when available. Crucial in the design of our approach is the use of the growing amount of phenotype–genotype information that diagnostic labs deposit in databases such as ClinVar. By this means, Cada is an ideal reference tool for differential diagnostics in rare disorders that can also be updated regularly.

Genetic syndromes screening by facial recognition technology: VGG-16 screening model construction and evaluation

Background

Many genetic syndromes (GSs) have distinct facial dysmorphism, and facial gestalts can be used as a diagnostic tool for recognizing a syndrome. Facial recognition technology has advanced in recent years, and the screening of GSs by facial recognition technology has become feasible. This study constructed an automatic facial recognition model for the identification of children with GSs.

Results

A total of 456 frontal facial photos were collected from 228 children with GSs and 228 healthy children in Guangdong Provincial People's Hospital from Jun 2016 to Jan 2021. Only one frontal facial image was selected for each participant. The VGG-16 network (named after its proposal lab, Visual Geometry Group from Oxford University) was pretrained by transfer learning methods, and a facial recognition model based on the VGG-16 architecture was constructed. The performance of the VGG-16 model was evaluated by five-fold cross-validation. Comparison of VGG-16 model to five physicians were also performed. The VGG-16 model achieved the highest accuracy of 0.8860 ± 0.0211, specificity of 0.9124 ± 0.0308, recall of 0.8597 ± 0.0190, F1-score of 0.8829 ± 0.0215 and an area under the receiver operating characteristic curve of 0.9443 ± 0.0276 (95% confidence interval: 0.9210–0.9620) for GS screening, which was significantly higher than that achieved by human experts.

Conclusions

This study highlighted the feasibility of facial recognition technology for GSs identification. The VGG-16 recognition model can play a prominent role in GSs screening in clinical practice.

GenomeDiver: a platform for phenotype-guided medical genomic diagnosis

Purpose:

Making a diagnosis from clinical genomic sequencing requires well-structured phenotypic data to guide genotype interpretation. A patient’s phenotypic features can be documented using the Human Phenotype Ontology (HPO), generating terms used to prioritize genes potentially causing the patient’s disease. We have developed GenomeDiver to provide a user interface for clinicians that allows more effective collaboration with the clinical diagnostic laboratory, with the goal of improving the success of the diagnostic process.

Methods:

GenomeDiver uses genomic data to prompt reverse phenotyping of patients undergoing genetic testing, enriching the amount and quality of structured phenotype data for the diagnostic laboratory, and helping clinicians to explore and flag diseases potentially causing their patient’s presentation.

Results:

We show how GenomeDiver communicates the clinician’s informed insights to the diagnostic lab in the form of HPO terms for interpretation of genomic sequencing data. We describe our user-driven design process, the engineering of the software for efficiency, security and portability, and examples of the performance of GenomeDiver using genomic testing data.

Conclusions:

GenomeDiver is a first step in a new approach to genomic diagnostics that enhances laboratory-clinician interactions, with the goal of directly engaging clinicians to improve the outcome of genomic diagnostic testing.

SRD5A3-CDG: 3D structure modeling, clinical spectrum, and computer-based dysmorphic facial recognition

Pathogenic variants in Steroid 5 alpha reductase type 3 (SRD5A3) cause rare inherited congenital disorder of glycosylation known as SRD5A3-CDG (MIM# 612379). To date, 43 affected individuals have been reported. Despite the development of various dysmorphic features in significant number of patients, facial recognition entity has not yet been established for SRD5A3-CDG. Herein, we reported a novel SRD5A3 missense pathogenic variant c.460 T > C p.(Ser154Pro). The 3D structural modeling of the SRD5A3 protein revealed additional transmembrane α-helices and predicted that the p.(Ser154Pro) variant is located in a potential active site and is capable of reducing its catalytic efficiency. Based on phenotypes of our patients and all published SRD5A3-CDG cases, we identified the most common clinical features as well as some recurrent dysmorphic features such as arched eyebrows, wide eyes, shallow nasal bridge, short nose, and large mouth. Based on facial digital 2D images, we successfully designed and validated a SRD5A3-CDG computer based dysmorphic facial analysis, which achieved 92.5% accuracy. The current work integrates genotypic, 3D structural modeling and phenotypic characteristics of CDG-SRD5A3 cases with the successful development of computer tool for accurate facial recognition of CDG-SRD5A3 complex cases to assist in the diagnosis of this particular disorder globally.

Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study

Background

Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls.

Objective

The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images.

Methods

Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists.

Results

We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; P<.001).

Conclusions

DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.

The case for open science: rare diseases

The premise of Open Science is that research and medical management will progress faster if data and knowledge are openly shared. The value of Open Science is nowhere more important and appreciated than in the rare disease (RD) community. Research into RDs has been limited by insufficient patient data and resources, a paucity of trained disease experts, and lack of therapeutics, leading to long delays in diagnosis and treatment. These issues can be ameliorated by following the principles and practices of sharing that are intrinsic to Open Science. Here, we describe how the RD community has adopted the core pillars of Open Science, adding new initiatives to promote care and research for RD patients and, ultimately, for all of medicine. We also present recommendations that can advance Open Science more globally.

The phenotype-driven computational analysis yields clinical diagnosis for patients with atypical manifestations of known intellectual disability syndromes

BACKGROUND

Due to extensive clinical and genetic heterogeneity of intellectual disability (ID) syndromes, the process of diagnosis is very challenging even for expert clinicians. Despite recent advancements in molecular diagnostics methodologies, a significant fraction of ID patients remains without a clinical diagnosis.

METHODS, RESULTS, AND CONCLUSIONS

Here, in a prospective study on a cohort of 21 families (trios) with a child presenting with ID of unknown etiology, we executed phenotype-driven bioinformatic analysis method, PhenIX, utilizing targeted next-generation sequencing (NGS) data and Human Phenotype Ontology (HPO)-encoded phenotype data. This approach resulted in clinical diagnosis for eight individuals presenting with atypical manifestations of Rubinstein-Taybi syndrome 2 (MIM 613684), Spastic Paraplegia 50 (MIM 612936), Wiedemann-Steiner syndrome (MIM 605130), Cornelia de Lange syndrome 2 (MIM 300590), Cerebral creatine deficiency syndrome 1 (MIM 300352), Glass Syndrome (MIM 612313), Mental retardation, autosomal dominant 31 (MIM 616158), and Bosch-Boonstra-Schaaf optic atrophy syndrome (MIM 615722).

Shared facial phenotype of patients with mucolipidosis type IV: A clinical observation reaffirmed by next generation phenotyping

BACKGROUND

Mucolipidosis type IV (ML-IV) is a rare autosomal-recessive lysosomal storage disease, caused by mutations in MCOLN1. ML-IV manifests with developmental delay, esotropia and corneal clouding. While the clinical phenotype is well-described, the diagnosis of ML-IV is often challenging and elusive.

OBJECTIVE

Our experience with ML-IV patients brought to the clinical observation that they share common and identifiable facial features, not yet described in the literature to date. Here, we utilized a computerized facial analysis tool to establish this association.

METHODS

Using the DeepGestalt algorithm, 50 two-dimensional facial images of ten ML-IV patients were analyzed, and compared to unaffected controls (n = 98) and to individuals affected with other genetic disorders (n = 99). Results were expressed in terms of the area-under-the-curve (AUC) of the receiver-operating-characteristic curve (ROC).

RESULTS

When compared to unaffected cases and to cases diagnosed with syndromes other than ML-IV, the ML-IV cohort showed an AUC of 0.822 (p value < 0.01) and an AUC of 0.885 (p value < 0.001), respectively.

CONCLUSIONS

We describe recognizable facial features typical in patients with ML-IV. Reaffirmed by the DeepGestalt technology, the described common facial phenotype adds to the tools currently available for clinicians and may thus assist in reaching an earlier diagnosis of this rare and underdiagnosed disorder.

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.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

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.

Differentiation of MISSLA and Fanconi anaemia by computer-aided image analysis and presentation of two novel MISSLA siblings

Variants in DONSON were recently identified as the cause of microcephaly, short stature, and limb abnormalities syndrome (MISSLA). The clinical spectra of MISSLA and Fanconi anaemia (FA) strongly overlap. For that reason, some MISSLA patients have been clinically diagnosed with FA. Here, we present the clinical data of siblings with MISSLA featuring a novel DONSON variant and summarize the current literature on MISSLA. Additionally, we perform computer-aided image analysis using the DeepGestalt technology to test how distinct the facial features of MISSLA and FA patients are. We show that MISSLA has a specific facial gestalt. Notably, we find that also FA patients feature facial characteristics recognizable by computer-aided image analysis. We conclude that computer-assisted image analysis improves diagnostic precision in both MISSLA and FA.