PhenoPro: a novel toolkit for assisting in the diagnosis of Mendelian disease

Li, Zixiu; Zhang, Feng; Wang, Yukai; Qiu, Yue; Wu, Yang; Lu, Yulan; Yang, Lin; Qu, William J; Wang, Huijun; Zhou, Wenhao; Tian, Weidong

doi:10.1093/bioinformatics/btz100

Cited by 28 publications

(23 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many other HPO-driven variant prioritization tools exist [34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51][52], all primarily tested only on (different) simulated datasets with limited software performance comparison. Further work should include a systematic and exhaustive software performance comparison on both simulated and real patient large datasets.…”

Section: Discussionmentioning

confidence: 99%

“…In order to overcome these difficulties, another generation of (freely available) tools have been developed that incorporate a rare disease patient's phenotype into the interpretation of their sequencing data. These include eXtasy [34], BiERapp [35], Phen-Gen [36], Exomiser [37], Phevor [38], PhenoVar [39], PhenIX [40], OVA [41], Phenolyzer [42], wANNOVAR [43], OMIM Explorer [44], QueryOR [45], GenIO [46], DeepPVP [47], MutationDistiller [48], Phrank [49], Xrare [50], PhenoPro [51], and Phenoxome [52]. Such phenotype-driven prioritization tools leverage existing genotype to phenotype information from various databases in order to prioritize candidate variants in those genes that are likely to be more relevant to the patient's phenotype.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Phenotype-Driven Tool for Rare Mendelian Variant Prioritization: Benchmarking Exomiser on Real Patient Whole-Exome Data

Cipriani

Pontikos

Arno

et al. 2020

Genes

View full text Add to dashboard Cite

Next-generation sequencing has revolutionized rare disease diagnostics, but many patients remain without a molecular diagnosis, particularly because many candidate variants usually survive despite strict filtering. Exomiser was launched in 2014 as a Java tool that performs an integrative analysis of patients’ sequencing data and their phenotypes encoded with Human Phenotype Ontology (HPO) terms. It prioritizes variants by leveraging information on variant frequency, predicted pathogenicity, and gene-phenotype associations derived from human diseases, model organisms, and protein–protein interactions. Early published releases of Exomiser were able to prioritize disease-causative variants as top candidates in up to 97% of simulated whole-exomes. The size of the tested real patient datasets published so far are very limited. Here, we present the latest Exomiser version 12.0.1 with many new features. We assessed the performance using a set of 134 whole-exomes from patients with a range of rare retinal diseases and known molecular diagnosis. Using default settings, Exomiser ranked the correct diagnosed variants as the top candidate in 74% of the dataset and top 5 in 94%; not using the patients’ HPO profiles (i.e., variant-only analysis) decreased the performance to 3% and 27%, respectively. In conclusion, Exomiser is an effective support tool for rare Mendelian phenotype-driven variant prioritization.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Improved Phenotype-Driven Tool for Rare Mendelian Variant Prioritization: Benchmarking Exomiser on Real Patient Whole-Exome Data

Cipriani

Pontikos

Arno

et al. 2020

Genes

View full text Add to dashboard Cite

show abstract

“…If studies simulate genomic analysis, then additionally a published disease-associated variant would be spiked into an otherwise normal VCF file. [29][30][31][32] However, this kind of simulation can be criticized because randomly chosen terms are unlikely to resemble terms that would be chosen in a real clinical encounter. In a real clinical encounter, the clinician may or may not be able to describe phenotypic abnormalities with the greatest possible detail.…”

Section: Lirical Achieves State Of Art Performance and Is Robust To Pmentioning

confidence: 99%

Interpretable Clinical Genomics with a Likelihood Ratio Paradigm

Robinson

Ravanmehr

Jacobsen

et al. 2020

Preprint

View full text Add to dashboard Cite

Human Phenotype Ontology (HPO)-based analysis has become standard for genomic diagnostics of rare diseases. Current algorithms use a variety of semantic and statistical approaches to prioritize the typically long lists of genes with candidate pathogenic variants. These algorithms do not provide robust estimates of the strength of the predictions beyond the placement in a ranked list, nor do they provide measures of how much any individual phenotypic observation has contributed to the prioritization result. However, given that the overall success rate of genomic diagnostics is only around 25-50% or less in many cohorts, a good ranking cannot be taken to imply that the gene or disease at rank one is necessarily a good candidate. Likelihood ratios (LR) are statistics for summarizing diagnostic accuracy, providing a measure of how much more (or less) a patient with a disease has a particular test result compared to patients without the disease. Here, we present an approach to genomic diagnostics that exploits the LR framework to provide an estimate of (1) the posttest probability of candidate diagnoses; (2) the LR for each observed HPO phenotype, and (3) the predicted pathogenicity of observed genotypes. LIkelihood Ratio Interpretation of Clinical AbnormaLities (LIRICAL) placed the correct diagnosis within the first three ranks in 92.9% of 384 cases reports comprising 262 Mendelian diseases, with the correct diagnosis having a mean posttest probability of 67.3%. Simulations show that LIRICAL is robust to many typically encountered forms of genomic and phenomic noise. In summary, LIRICAL provides accurate, clinically interpretable results for phenotype-driven genomic diagnostics.

show abstract

“…Here we described and benchmarked a Bayesian, AI-based gene prioritization tool for scalable diagnosis of rare genetic diseases by CNLP and WES or WGS. [31] [19,27,28,64,65]GEM improved upon prior, similar tools [19,27,28,64,65] by incorporating OMIM, HPO and ClinVar knowledge explicitly, automatically controlling for confounding factors, such as sex and ancestry, compatibility with CNLP-derived phenotypes, SVs and singleton probands, and by directly nominating diplotypes and disorders, rather than variants. [19,27,28,64,65] In the cohorts examined, GEM had maximal recall of 99%, requiring review of an average of 3 candidate genes, and less than one half of the associated disorders nominated by other widely used variant prioritization methods per case.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence enables comprehensive genome interpretation and nomination of candidate diagnoses for rare genetic diseases.

Vega

Chowdhury

Moore

et al. 2021

Preprint

View full text Add to dashboard Cite

Clinical interpretation of genetic variants in the context of the patient's phenotype is becoming the largest component of cost and time expenditure for genome-based diagnosis of rare genetic diseases. Artificial intelligence (AI) holds promise to greatly simplify and speed interpretation by comprehensively evaluating genetic variants for pathogenicity in the context of the growing knowledge of genetic disease. We assess the diagnostic performance of GEM, a new, AI-based, clinical decision support tool, compared with expert manual interpretation. We benchmarked GEM in a retrospective cohort of 119 probands, mostly NICU infants, diagnosed with rare genetic diseases, who received whole genome sequencing (WGS) at Rady Children's Hospital. We also performed a replication study in a separate cohort of 60 cases diagnosed at five additional academic medical centers. For comparison, we also analyzed these cases with commonly used variant prioritization tools (Phevor, Exomiser, and VAAST). Included in the comparisons were WGS and whole exome sequencing (WES) as trios, duos, and singletons. Variants underpinning diagnoses spanned diverse modes of inheritance and types, including structural variants (SVs). Patient phenotypes were extracted either manually or by automated clinical natural language processing (CNLP) from clinical notes. Finally, 14 previously unsolved cases were re-analyzed. GEM ranked >90% of causal genes among the top or second candidate, using manually curated or CNLP derived phenotypes, and prioritized a median of 3 genes for review per case. Ranking of trios and duos was unchanged when analyzed as singletons. In 17 of 20 cases with diagnostic SVs, GEM identified the causal SVs as the top or second candidate irrespective of whether SV calls where provided or inferred ab initio by GEM when absent. Analysis of 14 previously unsolved cases provided novel findings in one, candidates ultimately not advanced in 3, and no new findings in 10, demonstrating the utility of GEM for reanalysis. GEM enables automated diagnostic interpretation of WES and WGS for all types of variants, including SVs, nominating a very short list of candidate genes and disorders for final review and reporting. In combination with deep phenotyping by CNLP, GEM enables substantial automation of genetic disease diagnosis, potentially decreasing the cost and speeding case review.

show abstract

PhenoPro: a novel toolkit for assisting in the diagnosis of Mendelian disease

Cited by 28 publications

References 38 publications

An Improved Phenotype-Driven Tool for Rare Mendelian Variant Prioritization: Benchmarking Exomiser on Real Patient Whole-Exome Data

An Improved Phenotype-Driven Tool for Rare Mendelian Variant Prioritization: Benchmarking Exomiser on Real Patient Whole-Exome Data

Interpretable Clinical Genomics with a Likelihood Ratio Paradigm

Artificial intelligence enables comprehensive genome interpretation and nomination of candidate diagnoses for rare genetic diseases.

Contact Info

Product

Resources

About