Back

IE-MOIF: a novel multi-omics early integration framework for biomedical classification and biomarker discovery

ZHANG, W.; MOU, M.; HU, W.; LU, M.; ZHANG, H.; LUO, Y.; XU, H.; ZHANG, H.; TAO, L.; DAI, H.; GAO, J.; ZHU, F.

2023-06-12 genetic and genomic medicine
10.1101/2023.06.07.23291110 medRxiv
Show abstract

In the context of precision medicine, multi-omics data integration provides a comprehensive understanding of underlying biological processes and is critical for disease diagnosis and biomarker discovery. One commonly used integration method is early integration through concatenation of multiple dimensionally reduced omics matrices due to its simplicity and ease of implementation. However, this approach is seriously limited by information loss and lack of latent feature interaction. Herein, a novel multi-omics early integration framework (IE-MOIF) based on information enhancement and image representation learning is thus presented to address the challenges. IE-MOIF employs the self-attention mechanism to capture the intrinsic correlations of omics-features, which make it significantly outperform the existing state-of-the-art methods for multi-omics data integration. Moreover, visualizing the attention embedding and identifying potential biomarkers offer interpretable insights into the prediction results. All source codes and model for IE-MOIF are freely available https://github.com/idrblab/IE-MOIF.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.