HPO2GO: prediction of human phenotype ontology term associations for proteins using cross ontology annotation co-occurrences

Abstract

Analysing the relationships between biomolecules and the genetic diseases is a highly active area of research, where the aim is to identify the genes and their products that cause a particular disease due to functional changes originated from mutations. Biological ontologies are frequently employed in these studies, which provides researchers with extensive opportunities for knowledge discovery through computational data analysis. In this study, a novel approach is proposed for the identification of relationships between biomedical entities by automatically mapping phenotypic abnormality defining HPO terms with biomolecular function defining GO terms, where each association indicates the occurrence of the abnormality due to the loss of the biomolecular function expressed by the corresponding GO term. The proposed HPO2GO mappings were extracted by calculating the frequency of the co-annotations of the terms on the same genes/proteins, using already existing curated HPO and GO annotation sets. This was followed by the filtering of the unreliable mappings that could be observed due to chance, by statistical resampling of the co-occurrence similarity distributions. Furthermore, the biological relevance of the finalized mappings were discussed over selected cases, using the literature. The resulting HPO2GO mappings can be employed in different settings to predict and to analyse novel gene/protein—ontology term—disease relations. As an application of the proposed approach, HPO term—protein associations (i.e., HPO2protein) were predicted. In order to test the predictive performance of the method on a quantitative basis, and to compare it with the state-of-the-art, CAFA2 challenge HPO prediction target protein set was employed. The results of the benchmark indicated the potential of the proposed approach, as HPO2GO performance was among the best (Fmax = 0.35). The automated cross ontology mapping approach developed in this work may be extended to other ontologies as well, to identify unexplored relation patterns at the systemic level. The datasets, results and the source code of HPO2GO are available for download at: https://github.com/cansyl/HPO2GO.

DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier

“…To compare our method with other methods, we trained and tested our model using the CAFA2 challenge data, i.e., using the training and testing data as well as the ontologies provided in CAFA2 (see Section 2.1.2). We further evaluated annotations for CAFA2 targets provided by the HPO2GO method (Dogan, 2018). The top performing methods in CAFA2 achieve an Fmax of around 0.36 .…”

“…HPO2GO predicts HPO classes by learning association rules between HPO and GO classes based on their co-occurrence in annotations (Dogan, 2018). The idea is to map every HPO class p to a GO class f and score the mapping with the following formula:…”

“…We overcome this limitation by using the function prediction method DeepGOPlus (Kulmanov and Hoehndorf, 2019) which has been trained on a large number of proteins and can generate accurate functional annotations using only protein sequence. We evaluate our method using the latest phenotype annotations from the HPO (Köhler et al, 2017) and using the evaluation dataset from the Computational Assessment of Function Annotation (CAFA) challenge , and we compare our results with the top performing methods in CAFA 2 (Jiang et al, 2016) and one recent phenotype prediction method, HPO2GO (Dogan, 2018). We demonstrate a significant improvements over the state of the art in each evaluation.…”

“…Several methods have been developed to automatically predict or generate genotype-phenotype associations. To predict phenotype associations, these methods use different sources such as literature (Kahanda et al, 2015;Collier et al, 2015;Singhal et al, 2016), functional annotations (Kulmanov et al, 2018;Kahanda et al, 2015;Dogan, 2018), proteinprotein interactions (Kahanda et al, 2015), expression profiles (Xu et al, 2009;Labuzzetta et al, 2016), genetic variations (Chen et al, 2014;Kahanda et al, 2015), or their combinations (Kahanda et al, 2015). The general idea behind most of these methods is to find genetic similarities, or interactions, and transfer phenotypes between genes based on the assumption that similar or interacting genes are involved in similar or related phenotypes (Gillis and Pavlidis, 2012).…”

Graph analytics for phenome-genome associations inference

“…Moreover, reverse genetic approaches such as phenome-wide association studies (PheWAS) (Bush et al Nat Rev Genet. 2016), as well as large systems genetics infrastructures (Li et al Cell Syst. 2018), have been recently developed.…”