Accurate prediction of cancer drug response is essential for advancing precision oncology, enabling tailored therapies that account for the molecular heterogeneity of tumors. While deep learning has shown promise in this domain, many existing approaches fail to incorporate physicochemical properties of drug compounds, limiting the biological interpretability and generalizability of learned representations. To address this gap, we present PAM-CDR, a property-aware multi-modal representation learning framework that integrates molecular graphs, fingerprints, and physicochemical descriptors with transcriptomic and genomic profiles of cancer cell lines. PAM-CDR employs a three-stage hierarchical fusion strategy to enable fine-grained representation learning across drug and cell modalities. In the first stage, property-guided attention injects biologically meaningful context to enrich molecular graph and fingerprint features. In the second stage, bidirectional cross-modality interactions capture complementary patterns and enhance multi-omic cellular representations. In the final stage, unified drug and cell line embeddings are integrated to accurately predict drug responses. Benefiting from these designs, PAM-CDR consistently outperforms competitive baselines, achieving an AUC of 0.9161 and an AUPR of 0.9313. Ablation studies confirm the critical contribution of physicochemical priors, while embedding visualizations reveal improved biological coherence in the learned molecular representations. The code is publicly available at https://github.com/catly/PAM-CDR.
Li et al. (Thu,) studied this question.