Large scale genotype‐ and phenotype‐driven machine learning in Von Hippel‐Lindau disease

Abstract

Von Hippel‐Lindau (VHL) disease is a hereditary cancer syndrome where individuals are predisposed to tumor development in the brain, adrenal gland, kidney, and other organs. It is caused by pathogenic variants in the VHL tumor suppressor gene. Standardized disease information has been difficult to collect due to the rarity and diversity of VHL patients. Over 4100 unique articles published until October 2019 were screened for germline genotype–phenotype data. Patient data were translated into standardized descriptions using Human Genome Variation Society gene variant nomenclature and Human Phenotype Ontology terms and has been manually curated into an open‐access knowledgebase called Clinical Interpretation of Variants in Cancer. In total, 634 unique VHL variants, 2882 patients, and 1991 families from 427 papers were captured. We identified relationship trends between phenotype and genotype data using classic statistical methods and spectral clustering unsupervised learning. Our analyses reveal earlier onset of pheochromocytoma/paraganglioma and retinal angiomas, phenotype co‐occurrences and genotype–phenotype correlations including hotspots. It confirms existing VHL associations and can be used to identify new patterns and associations in VHL disease. Our database serves as an aggregate knowledge translation tool to facilitate sharing information about the pathogenicity of VHL variants.

Developing a disease-specific annotation protocol for VHL gene curation using Hypothes.is

“…Out of the 430 papers that were extracted, 86% (371/430) have been annotated thus far. Based on previous work by our team ( 30 ), we estimated 566 unique variants within these 430 papers; however, we expect this number will fluctuate by the end of the project. Within these 371 papers, there were 458 unique variants.…”

“…The annotated papers were selected through a literature search ( 30 ) on Ovid MEDLINE and EMBASE databases using the terms ‘(Von Hippel–Lindau) AND (genetics OR gene mutations)’ and ‘(Von Hippel–Lindau) and (databases)’. These terms were searched for in the title, abstract and index terms of manuscripts published up to October 2019.…”

CIViCdb 2022: evolution of an open-access cancer variant interpretation knowledgebase

“…CIViC entered into collaborations with outside groups, notably the ClinGen Somatic Cancer CDWG, and in response developed Organizations to enable group tracking of curation conducted within a formal expert panel setting. Evidence Types for functional, oncogenic, and predisposing data were added, extending the data model to cover published guidelines ( 16 , 18 ) and supporting the collaborator-led incorporation of a large VHL variant dataset into CIViC ( 17 , 22 ). Further collaborative work resulted in the integration of CIViC into the broader community of variant interpretation resources and the development of the curation enhancement tool, CIViCmine.…”

“…Specific examples of community-driven features are described below. Results of our first Hackathon and Curation Jamboree led to the development of a new Evidence Type (Predisposing Evidence) described elsewhere ( 17 , 19 ) and a fruitful collaboration with VHL experts for descriptive integration of variant and case-level data related to cancer predisposition syndromes ( Supplemental Figure S7 ) ( 22 ). To achieve this, Human Phenotype Ontology (HPO) ( 23 ) terms were added as a new field to EIDs.…”

Molecular uropathology and cancer genetics for the urologist: key findings for classification and diagnosis

“…In renal cell carcinoma (RCC), involved pathways differ by tumor type. In clear cell RCC (ccRCC), the most common genetic aberrations involve chromosome 3p25-26, inducing an inactivation of the tumor suppressor Von Hippel-Lindau (VHL) gene [36,37]. Sporadic ccRCCs show VHL inactivation in 56-91% due to loss of heterozygosity, mutation, deletion or hypermethylation.…”