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.
Abstract
Chemical language models are powerful tools for navigating chemical space, but their reliance on linear representations such as molecular strings creates a semantic gap, hindering their ability to bridge natural language with the full complexity of molecular structures. Here we show that chemical language models can gain a comprehensive, multi-modal understanding of molecules through heterogeneous molecular encoding, which integrates one-dimensional sequences, two-dimensional topology, three-dimensional geometry, and statistically derived molecular fragments. We further introduce a query-based module that converts heterogeneous structural information into a unified representation compatible with language models, together with a chain-of-fragment mechanism that guides molecular generation through a hierarchical chemical blueprinting process. To support research in this area, we constructed a million-scale dataset for multi-objective molecular design. Experimentally, the framework enables bidirectional navigation of the chemical-linguistic space, achieving consistent improvements across molecular comprehension and design tasks over strong baselines. Molecular AI models often struggle to connect chemical structures with language. This study presents HME, a framework that combines multiple views of molecules to improve molecular understanding and design.
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.
Wenda Wang, Yihan Tong, Yuwei Hu et al.· 0 citations
Automated exploration of chemical space through machine learning has become a central strategy in modern drug discovery, where the ability to learn transferable molecular representations directly impacts predictive modeling performance. Recent advances in chemical language models have primarily relied on atom-level string encodings such as SMILES or SELFIES, treating molecules as sequences of individual atoms or characters. However, medicinal chemistry reasoning is often fragment-centric, emphasizing scaffolds, functional groups, and modular substructures rather than isolated atoms. In this study, we introduce FragBERTa, a molecular fragment-aware transformer-based representation language model pretrained using masked language modeling on Sequential Attachment-based Fragment Embedding (SAFE) representations. SAFE decomposes molecules into chemically meaningful fragments while preserving attachment information, enabling the model to learn fragment-level structural patterns within a sequence framework. FragBERTa is pretrained on 11 million unique SAFE sequences extracted from multiple public chemical databases and subsequently finetuned on diverse MoleculeNet benchmarks covering both regression (ESOL, FreeSolv, Lipophilicity, PDBbind) and classification (BACE, BBBP, HIV, Tox21, SIDER) tasks under both random and scaffold splits. Our evaluation shows that FragBERTa achieves competitive performance across tasks, often matching or surpassing prior models. In regression, it demonstrates strong gains in lipophilicity and the best scaffold-split performance on protein-ligand binding affinity within our comparison. In classification, FragBERTa attains the strongest reported random-split ROC-AUC results on BACE, HIV, and Tox21 and the strongest reported scaffold-split ROC-AUC performance on BBBP among the compared baselines, and delivers robust performance across bioactivity, permeability, and toxicity benchmarks, indicating that fragment-based representations effectively capture biologically driven and interaction-sensitive endpoints. Collectively, these findings suggest that fragment-based string representations offer advantages over atom-level representations such as SMILES and SELFIES for scaffold-sensitive and interaction-driven tasks, highlighting the value of fragment-level inductive bias for future molecular foundation models in drug discovery.
Transformer models have revolutionized natural language processing (NLP), and text-based molecular representations like SMILES have successfully extended these architectures to chemistry. However, domain-adaptive pre-training often causes models to overfit to chemical syntax, catastrophically forgetting their foundational semantic capabilities. To address this challenge, we introduce CheMatE, a chemistry-oriented embedding model that jointly captures molecular structure and domain-specific natural language within the same representation space. Built on a ModernBERT backbone, CheMatE learns bi-semantic representations through a two-stage training procedure: continued masked language modeling (MLM) followed by a Matryoshka contrastive learning stage via Multiple Negative Ranking Loss (MNRL). First, we train the model using MLM on a novel, large-scale corpus of SMILES-annotated, long-context scientific documents that were constructed and curated from FineWeb and ChemPile (comprising 10.4B and 11.5B tokens, respectively). Subsequently, the model undergoes contrastive learning using a synthetic dataset of SMILES-text pairs algorithmically derived from our original training corpus. This design exposes the model to SMILES-enriched scientific literature, enabling bi-semantic understanding. We evaluate CheMatE across a range of downstream tasks covering molecular property prediction and scientific language understanding. Our results demonstrate that coupling our custom-curated datasets with this sequential training strategy yields robust, highly transferable representations. By effectively unifying structural and contextual signals within a single text-based framework, CheMatE achieves competitive performance across both specialized chemistry models and general-purpose language model baselines.
David Ming Segura, Jeremy Goumaz, Joshua W. Sin et al.· 0 citations
This paper proposes UniEdit, a Unified Graph-based Mixture-of-Experts (MoE) Molecular Editing model that offers a robust alternative to LLMs and incorporates a Mixture-of-Experts architecture that dynamically routes tasks to specialized components.
Jiajun Yu, Zhihao Wu, Yizhen Zheng et al.· Proceedings of the 32nd ACM...· 0 citations
Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular LLMs represent a molecule through several modalities, notably a 1D SMILES sequence or a 2D molecular graph. Both encode molecular information implicitly, so the contribution of individual substructures remains opaque. Retrieval and augmentation methods add context, but from external sources. However, the cues chemists reason over are the internal substructures that drive a property up or down. We propose MR-MoL, a multi-granular rationale-guided molecular LLM that supplies this evidence directly. A fine-tuned GNN scores each substructure through masking, and the most influential ones are serialized as a ranked, direction-tagged rationale that the LLM reads alongside the SMILES sequence and molecular graph. The rationale spans three levels of granularity: Murcko scaffolds with their side chains, BRICS fragments, and functional groups. This is, to our knowledge, the first method to expose GNN-derived attributions to an LLM as evidence for property prediction. On eight MoleculeNet tasks, MR-MoL achieves the best overall results among generalist models and narrows the gap to specialist models tuned for each task. Five diagnostics further confirm that the model reads the rationale rather than merely benefiting from its presence. Its direction, rank, and substructure each shape the prediction, and its attributions reproduce known structure-property relationships.
Junwoo Park, Minyoung Shin, C. Lee et al.· 0 citations
MolLingua, a token-centric, dual-modal framework designed for native molecular understanding, uses a dual-branch Residual Vector Quantization engine to discretize heterogeneous, high-dimensional spatial 2D and 3D features into compact code sequences rather than relying solely on continuous projections.
Haoyang Liu, Xikang Feng, Fei Guo et al.· IEEE journal of biomedical a...· 0 citations