MolSight is proposed, a graph-aware vision-language model framework designed to enhance the understanding of molecular images by VLMs and significantly outperforms existing VLMs, molecular LLMs, and task-specific models across multiple chemical visual understanding tasks, achieving a new level of molecular image reasoning in complex chemical scenarios.
Abstract
Using molecular large language models (LLMs) as a unified framework for understanding molecular structures and functions is emerging as a new trend in tasks such as molecular design and drug discovery. However, these models struggle to fully capture the visual representation of molecular structures, limiting their potential. While existing molecular vision-language models (VLMs) show promise, they still face challenges in structural alignment and lack the necessary topological modeling for accurate molecular understanding. To address this, we propose MolSight, a graph-aware vision-language model framework designed to enhance the understanding of molecular images by VLMs. MolSight integrates a Molecular Topology Module to inject chemical-bond adjacency information into vision tokens, and a Molecular Grounding Module to align visual features with chemical symbolic semantics. Our experiments demonstrate that MolSight significantly outperforms existing VLMs, molecular LLMs, and task-specific models across multiple chemical visual understanding tasks, achieving a new level of molecular image reasoning in complex chemical scenarios.
Molecular embedding models can serve as foundational infrastructure for computational chemistry and drug discovery, where reusable vector representations support property prediction, virtual screening, and retrieval. Most molecular encoders are specialist models built around a single molecular view, producing unconditional vectors with no language interface for varying the representation. We ask whether multimodal large language models (MLLMs), which natively process images, text, and symbolic inputs, can instead serve as \emph{general molecular embedding models} that produce embeddings conditioned on both a molecular profile and a natural-language semantic context. We introduce \textbf{MolEmb}, a lightweight framework that adapts MLLMs by aligning molecular profiles with textual descriptions in a shared embedding space using a bidirectional contrastive objective. The resulting embedding model is competitive on molecular property prediction and supports cross-modal molecule--text retrieval in the same space. We further introduce \textbf{MolCAR}, a diagnostic benchmark for context-aware retrieval, and find that context-aware molecular embedding is primarily a data property of the supervision. These results suggest that MLLMs are not merely chemistry assistants or generators, but a viable and extensible route to general molecular embedding models.
Xinjian Zhao, Xiangru Jian, Yaoyao Xu et al.· 0 citations
Large language models (LLMs) are rapidly becoming interactive scientific assistants. Most existing pipelines rely on specialized molecular encoders and alignment modules, while overlooking the importance of chemical hierarchy and traceable evidence for reliable reasoning and explanation. Thus, we propose MolGlass, a data-centric paradigm for visual molecular understanding in vision-language models (VLMs) that injects chemical priors directly into the visual input through chemical-aware visual augmentations, without modifying model architectures or training molecule-specific encoders. MolGlass enriches depictions with human-interpretable cues such as scaffolds, BRICS-like fragments, and functional groups, with a 2.5D visual encoding strategy that strengthens stereochemical symbols in 2D diagrams to mitigate the gap between 2D and 3D reasoning. Moreover, MolGlass includes a three-stage curriculum (Perceive-Reason-Converse) that progressively trains models from grounding MolGlass conventions to evidence-based reasoning and finally to multi-turn, assistant-style molecular consultation. Across molecular understanding and property prediction tasks, extensive experiments show that MolGlass improves transfer and zero-shot performance and enables visually grounded explanations by tracing model decisions to human-identifiable regions. Our code is available at: https://github.com/RunqingXuCn/MolGlass.
Runqing Xu, Xiaotang Wang, Chunfeng Gao et al.· Proceedings of the 32nd ACM...· 0 citations
HME is presented, a framework that combines multiple views of molecules to improve molecular understanding and design and enables bidirectional navigation of the chemical-linguistic space, achieving consistent improvements across molecular comprehension and design tasks over strong baselines.
Liuzhenghao Lv, Hao Li, Yu Wang et al.· Nature Communications· 0 citations
Learning effective molecular representations is crucial for accurate property prediction in AI-aided drug discovery. However, most existing molecular pre-training methods are still primarily based on 2D topological graphs, limiting their ability to exploit 3D geometric information. Moreover, methods that do incorporate 3D geometry often do not distinguish between the roles of atom-centered and bond-centered representations. To address these limitations, we propose GDGraph, a geometryenhanced dual-view framework for molecular representation learning. GDGraph models molecular geometry from two complementary structural perspectives: an atom view for capturing global spatial dependencies and a bond view for modeling local geometric patterns. To support this dual-view design, we introduce a multi-scale geometric feature encoding scheme and a view-specific geometry-aware learning strategy, enabling each view to focus on the geometric dependencies it is best suited to capture. Extensive experiments demonstrate that GDGraph achieves strong and stable performance on molecular property prediction benchmarks, and effectively predicts geometrysensitive quantum chemical properties on the QM9 dataset.
Yu Liu, Jonathan D. Hirst, Jianfeng Ren et al.· Annual International Compute...· 0 citations
Local chemical perception and property reasoning are both essential for understanding how molecular structure determines properties. Current LLM-based chemical reasoning methods either receive SMILES/molecular images together with descriptions of local motifs, or reason directly from molecular images. Neither approach enables the model to focus on chemically meaningful regions before reasoning. To address this gap, we propose Visual Latent Structural Reasoning (VLSR), an end-to-end framework that jointly learns localization and reasoning from molecular images. Central to our approach is a localize-then-reason strategy. VLSR first learns to locate chemically meaningful regions in a molecular image. It then reasons about their property effects in a compact latent workspace before producing the final answer. Under the same inference setup, this design achieves 9.6X higher throughput than a comparable textual-reasoning baseline.
Structure-based generative models (SBGMs) hold great promises for accelerating drug discovery by enabling target-aware molecular design. However, existing approaches face fundamental challenges: three-dimensional graph-based models can explicitly incorporate protein structural information but often generate chemically implausible molecules due to limited training data, while chemical language models (CLMs) produce chemically plausible molecules but struggle to effectively leverage three-dimensional structural information for structure-conditioned generation and hard to incorporate lead optimization functionality due to the nature of SMILES string. Here, we present StructureSAFE, a structure-aware chemical language model that resolves this trade-off by integrating protein structural and evolutionary encoders with the SAFE molecular representation via pretraining and finetuning training scheme, enabling both de novo hit identification and a comprehensive suite of lead optimization subtasks within a unified framework. Comprehensive benchmarking on the MolGenBench dataset demonstrates that StructureSAFE achieves state-of-the-art (SOTA) performance across multiple metrics, with particularly pronounced improvements in chemical plausibility relative to graph-based models lacking pretraining. Evaluation on a rigorously constructed held-out test set further confirms its ability to generate drug-like, synthetically accessible molecules with competitive predicted binding affinities for previously unseen targets on both hit identification and lead optimization setting. In silico case studies across four therapeutically relevant targets validate its capacity to generate chemically plausible molecules that recapitulate key binding interactions of known high-affinity ligands while proposing novel interactions for potential better affinity and exploring previously unknown regions of chemical space. Taking together, StructureSAFE represents a versatile and practical tool to provide high-quality candidate molecules for augmenting medicinal chemistry workflows in both hit identification and lead optimization campaigns.
Bo Yang, Ke Xu, Chijian Xiang et al.· bioRxiv· 0 citations