Phen2Disease: A Phenotype-driven Semantic Similarity-based Integrated Model for Disease and Gene Prioritization

Abstract

By utilizing the Human Phenotype Ontology (HPO), recent approaches to prioritizing disease-causing genes for patients become popular. However, these approaches do not comprehensively use information about phenotypes of diseases and patients. We present a new method called Phen2Disease that calculates similarity scores between two phenotype sets of patients and diseases by which to prioritize diseases and genes. Specifically, we calculate three scores of information content-based similarities using the phenotypes, and their combination as the respective benchmarks, and integrate them as a final score. Comprehensive experiments were conducted on six real data cohorts with 2051 cases and two simulated data cohorts with 1000 cases. Compared with the three state-of-the-art methods, if we only use phenotype information and HPO knowledge base, Phen2Disease outperformed all of them, particularly in cohorts with the less average numbers of HPO terms. We have found that patients with higher information content scores had more specific information so their predictions would be more accurate. In addition, Phen2Disease has high interpretability with ranked diseases and patient HPO terms provided.

Integrative omics approaches to advance rare disease diagnostics

“…2,3 HPO is a comprehensive, standardised vocabulary of phenotypic abnormalities that can be used to describe human diseases and their corresponding signs and symptoms. The popularity of HPO facilitated the development of a number of gene prioritisation algorithms based on the similarity analysis of patient phenotypes to clinical symptoms described for known disease genes [4][5][6][7] (Table S1). These methods provide a framework for systematic reanalysis of genetic data.…”

Enhancing phenotype recognition in clinical notes using large language models: PhenoBCBERT and PhenoGPT

“… 1 , 4 , 5 For example, a number of computational methods have been developed to facilitate phenotype-based prioritization of disease variants and genes, 6 , 7 , 8 , 9 , 10 , 11 , 12 and some methods also enable the prediction of Mendelian diseases directly from phenotype information. 13 , 14 , 15 To facilitate computational phenotype analysis, the Human Phenotype Ontology (HPO) was established, which provides a standardized vocabulary to describe phenotypic abnormalities in human diseases. 16 The current release of HPO (June 2022) covers 13,000 terms and over 156,000 annotations on hereditary diseases.…”