Graph Based Link Prediction between Human Phenotypes and Genes

TL;DR

This paper presents a machine learning framework that predicts links between human phenotypes and genes using graph embeddings and supervised learning, achieving high accuracy in identifying genotype-phenotype associations.

Contribution

It introduces a novel approach combining node2vec embeddings with multiple classifiers, notably LightGBM, for accurate phenotype-gene link prediction.

Findings

LightGBM achieved AUROC 0.904 and AUCPR 0.784.

The framework outperforms other tested algorithms in link prediction accuracy.

High F1 score of 0.87 indicates reliable predictions.

Abstract

Background: The learning of genotype-phenotype associations and history of human disease by doing detailed and precise analysis of phenotypic abnormalities can be defined as deep phenotyping. To understand and detect this interaction between phenotype and genotype is a fundamental step when translating precision medicine to clinical practice. The recent advances in the field of machine learning is efficient to predict these interactions between abnormal human phenotypes and genes. Methods: In this study, we developed a framework to predict links between human phenotype ontology (HPO) and genes. The annotation data from the heterogeneous knowledge resources i.e., orphanet, is used to parse human phenotype-gene associations. To generate the embeddings for the nodes (HPO & genes), an algorithm called node2vec was used. It performs node sampling on this graph based on random walks, then learns features over these sampled nodes to generate embeddings. These embeddings were used to perform the downstream task to predict the presence of the link between these nodes using 5 different supervised machine learning algorithms. Results: The downstream link prediction task shows that the Gradient Boosting Decision Tree based model (LightGBM) achieved an optimal AUROC 0.904 and AUCPR 0.784. In addition, LightGBM achieved an optimal weighted F1 score of 0.87. Compared to the other 4 methods LightGBM is able to find more accurate interaction/link between human phenotype & gene pairs.