Graph Contrastive Learning for Multi-omics Data
This work addresses the need for better computational methods to integrate multi-omics data for human disease research, representing an incremental improvement.
The paper tackled the problem of leveraging multi-omics data for disease understanding by introducing a graph contrastive learning framework, which outperformed existing methods in supervised classification tasks.
Advancements in technologies related to working with omics data require novel computation methods to fully leverage information and help develop a better understanding of human diseases. This paper studies the effects of introducing graph contrastive learning to help leverage graph structure and information to produce better representations for downstream classification tasks for multi-omics datasets. We present a learnining framework named Multi-Omics Graph Contrastive Learner(MOGCL) which outperforms several aproaches for integrating multi-omics data for supervised learning tasks. We show that pre-training graph models with a contrastive methodology along with fine-tuning it in a supervised manner is an efficient strategy for multi-omics data classification.