Paper ID: 2402.01809

PhenoLinker: Phenotype-Gene Link Prediction and Explanation using Heterogeneous Graph Neural Networks

Jose L. Mellina Andreu, Luis Bernal, Antonio F. Skarmeta, Mina Ryten, Sara Álvarez, Alejandro Cisterna García, Juan A. Botía

The association of a given human phenotype to a genetic variant remains a critical challenge for biology. We present a novel system called PhenoLinker capable of associating a score to a phenotype-gene relationship by using heterogeneous information networks and a convolutional neural network-based model for graphs, which can provide an explanation for the predictions. This system can aid in the discovery of new associations and in the understanding of the consequences of human genetic variation.

Submitted: Feb 2, 2024