Sep 2026· 2026 International Conference on Secure IoT and Cybersecurity (ICOSICS)· pp. 2091-2098· 0 citations· 23 references
TL;DR
ChemGraphy, a multimodal drug discovery platform that unifies structural molecular encoding, literature retrieval, and language-model generation within a cross-attention fusion framework, is introduced and a token-removal study finds a significant inverse association between retained attention and perturbation impact, so attention is not treated as a causal explanation.
Abstract
We introduce ChemGraphy, a multimodal drug discovery platform that unifies structural molecular encoding, literature retrieval, and language-model generation within a cross-attention fusion framework. The system accepts natural-language queries, identifies molecular entities, retrieves evidence from a ChEMBL-derived corpus, encodes molecular graphs using a six-layer Graphormer-based graph neural network (GNN), and supplies the resulting representations to an instruction-tuned language model. Its central architectural component, CrossAttentionFusion (CAF), projects 768-dimensional molecu-lar representations, 384-dimensional query representations, and retrieved-context vectors into a shared 512-dimensional space and integrates them using eight-head cross-attention followed by self-attention refinement. On four MoleculeNet benchmarks, the graph encoder provides molecular-property signals across solubility, hydration free energy, lipophilicity, and beta-secretase classification. On BACE, the reported CAF ablation reaches a ROC-AUC of 0.8324 ± 0.0466, compared with 0.7557 ± 0.0174 for naive feature concatenation under the same ablation protocol. Additional controlled experiments evaluate CAF retrieval depth, hidden dimension, scaffold-based generalization, attention perturbation, and external ADMET benchmarks. Retrieval depth is relatively stable on BACE and improves ESOL performance up to $k=5$; scaffold splitting produces lower performance than random splitting, exposing a measurable scaffold-shift gap. A token-removal study finds a significant inverse association between retained attention and perturbation impact, so attention is not treated as a causal explanation. External evaluation on TDC BBB and HIA benchmarks provides independent screening evidence while retaining the limitations of the descriptor-based ADMET module.
Graph neural networks (GNNs) are among the standard tools for molecular property prediction, but the atom-level explanations of their predictions are hard for medicinal chemists to act on. We propose a change of input representation rather than a new model: molecules are encoded as fragment-level graphs from BRICS deco...
Rafael Lopes Almeida, Ina Pöhner School Of Pharmacy, University of Eastern Finland et al.· 0 citations
Screen Tables and Substrate Scopes are information-dense figures widely used in synthetic chemistry literature, yet automated extraction of structured reaction data from them remains challenging. We introduce RxnExBench, a multimodal benchmark for fine-grained reaction-level evaluation. Built from high-impact chemistry...
Jia-Xing Sun, Jun-Yuan Gao, Rui-Kang Zhang et al.· Conference on Empirical Meth...· 0 citations
Accurate medication recommendation is central to clinical decision-making, directly determining therapeutic efficacy and patient safety. However, existing methods suffer from two key limitations: drugs are often abstracted as discrete tokens, ignoring their molecular structures and pharmacological mechanisms, and the c...
Jun-Ke Wang, Hong-Shun Ling, Li Zhang et al.· 0 citations
MoTIF-X, a motif-centered framework that uses graph-grounded chemical motifs as shared anchors for multimodal integration and interpretation, is introduced, achieving the best average classification performance across the evaluated benchmarks and generalizing to an external drug-cold-start dataset without additional fi...
Lin-Qing Mo, Jia-Yu Zhou, Bin Chen· arXiv.org· 0 citations
This work proposes Molrep-SCF, a multimodal self-supervised pretraining framework for molecular representation learning using SMILES sequences, 2D molecular graphs, and 3D geometric structures that consistently outperforms existing multi-modal frameworks on molecular property prediction and other tasks.
Meng Ma, Qing-Qing Cao, Fang Liu et al.· Frontiers in Pharmacology· 0 citations
LARK is introduced, a unified framework for learning atom–molecule–reaction knowledge from chemical transformations that learns chemically informative representations of substructures involved in molecular transformations and establishes chemical transformations as a source of structured supervision for representation...
Jian-Bo Qiao, Yu-Hang Liu, Jun-Ru Jin et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.