Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 623-631
DOI: 10.1609/aaai.v40i1.37027 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Mengran Li und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Understanding how chemical perturbations propagate through biological systems is essential for robust molecular property prediction. While most existing methods focus on chemical structures alone, recent advances highlight the crucial role of cellular responses such as morphology and gene expression in shaping drug effects. However, current cell-aware approaches face two key limitations: (1) modality incompleteness in external biological data, and (2) insufficient modeling of hierarchical dependencies across molecular, cellular, and genomic levels. We propose CHMR (Cell-aware Hierarchical Multi-Modal Representations), a robust framework that jointly models local-global dependencies between molecules and cellular responses and captures latent biological hierarchies via a novel tree-structured vector quantization module. Evaluated on public benchmarks spanning 696 tasks, CHMR outperforms state-of-the-art baselines, yielding average improvements of 3.6% on classification and 17.2% on regression tasks. These results demonstrate the advantage of hierarchy-aware, multi-modal learning for reliable and biologically grounded molecular representations, offering a generalizable framework for integrative biomedical modeling.
Zitieren
APA
Li, M., Zang, Z., Xing, W., Chen, J., Zhang, R., Luo, J., & Li, S. Z. (2026). Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 623-631. https://doi.org/10.1609/aaai.v40i1.37027
Vancouver
Li M, Zang Z, Xing W, Chen J, Zhang R, Luo J, et al. Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):623-631. doi:10.1609/aaai.v40i1.37027
BibTeX
@article{Li2026,
author = {Li, Mengran and Zang, Zelin and Xing, Wenbin and Chen, Junzhou and Zhang, Ronghui and Luo, Jiebo and Li, Stan Z.},
title = {Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {1},
pages = {623--631},
doi = {10.1609/aaai.v40i1.37027}
}
EUVIMED