Deep learning-based multiomics integration model for predicting axillary lymph node metastasis in breast cancer.

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Accurate prediction of breast cancer axillary lymph node metastasis is crucial for treatment planning.
• Integrating diverse omics data holds potential for improving prognostic accuracy.

Purpose of the Study:

• To develop and evaluate a deep learning-based multiomics integration model for predicting axillary lymph node metastasis in breast cancer.

Main Methods:

• Utilized five types of omics data: mRNA, DNA methylation, miRNA, copy number variation, and protein expression.
• Developed a deep neural network incorporating an attention mechanism for adaptive weighting of multiomics features.

Main Results:

• The deep learning model achieved an area under the curve (AUC) of 0.89 (95% CI: 0.863-0.910).
• Demonstrated superior performance compared to other existing methods.

Conclusions:

• The developed deep learning multiomics integration model shows significant promise for predicting breast cancer axillary lymph node metastasis.
• This model represents an effective computational approach for enhancing breast cancer prognosis.