Momentum Contrast-Enhanced Multimodal Representation Learning for Drug Synergy Prediction.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 42467001.
- Also identified by DOI 10.1093/bioinformatics/btag530.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Accurate prediction of synergistic drug combinations can accelerate anticancer combination discovery. Existing methods inadequately model higher-order drug-drug-cell-line interactions and drug-disease associations and remain sensitive to sparse and noisy multi-omics data, limiting generalization to unseen cell lines and drug combinations. We present MoCo-MultiSynergy, a multimodal framework that combines modality-specific momentum contrastive learning with heterogeneous hypergraph modeling. The hypergraph represents synergistic drug-drug-cell-line triplets and drug-disease associations, while gated residual propagation refines node representations. Momentum Contrast modules regularize encoded drug and cell-line representations using latent feature masking and Gaussian perturbation. On the O'Neil and NCI-ALMANAC datasets, MoCo-MultiSynergy achieves the highest AUROC and AUPRC across the evaluated settings, with the largest gains when generalizing to unseen cell lines and drug combinations. Source code is available at https://github.com/27167199/MoCo-MultiSynergy.