MTFuseSyn: A Multi-Task Fusion Framework for Drug Synergy Prediction Integrating Cell Line Multi-Omics Data

With the continuous rise in cancer incidence and mortality, drug resistance has emerged as a critical challenge in cancer therapy. Conventional monotherapy often fails to address tumor cell heterogeneity and multiple drug resistance, resulting in limited efficacy, whereas combination therapy-through the synergistic effects of multiple drugs-can significantly enhance treatment outcomes and delay resistance development. However, accurately predicting drug synergism remains a formidable task due to the complex interplay of factors such as drug molecular features, drug-drug interactions, target proteins, and cell line characteristics, with current methods falling short in integrating these multidimensional data. To address this challenge, we propose a multi-task learning framework-MTFuseSyn-which constructs and integrates multiple tasks, including drug-target interactions and drug-drug interactions. To obtain richer drug features, the framework incorporates a graph aggregation module that leverages an adaptive attention mechanism to automatically identify and focus on key molecular substructures highly correlated with synergistic effects. Additionally, the framework integrates multimodal cell line data to learn richer and context-relevant cellular feature representations, thereby providing robust biological support for prediction. To effectively integrate knowledge across tasks, we design a task fusion attention module to dynamically capture potential associations among multiple tasks. Experimental results on the authoritative DrugCombDB and Oncology-Screen datasets demonstrate that MTFuseSyn significantly outperforms existing methods in both classification and regression tasks, underscoring the importance of multidimensional information fusion in drug synergy prediction. Ablation studies and case analyses further validate the efficacy of the proposed modules.