Fraglingo is an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space. It predicts attachment-aware fragment embeddings using a wildcard-anchored readout that captures the growing molecule’s active attachment site, then retrieves the next fragment via latent-space nearest-neighbor search. This approach allows new fragments to be added at inference time without retraining and achieves stronger joint property control on benchmarks while maintaining high validity, uniqueness, and novelty.
By Thao Nguyen, Jeonghwan Kim, Zhenhailong Wang, Heng Ji
arXiv:2606. 12113v1 Announce Type: cross Abstract: Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies.
By Xinni Zhang, Zijing Liu, He Cao, Yu Li, Irwin King
The paper introduces MECo, a framework that translates molecular editing intentions into executable code, bridging the gap between reasoning and execution in drug discovery. MECo generates human‑interpretable editing intentions from a molecule and design objective, then converts those intentions into precise structural edits. The method achieves over 98% accuracy on realistic edits and improves downstream benchmark consistency by 38–86 percentage points, outperforming SMILES‑based baselines while maintaining structural similarity.
By Wenyu Zhu, Chengzhu Li, Xiaohe Tian, Yifan Wang, Yinjun Jia, Jianhui Wang, Bowen Gao, Haichuan Tan, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan
arXiv:2607. 02140v1 Announce Type: new Abstract: Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode.
By Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee
WEECFP-SuRGE introduces a position‑aware substructure encoding method that combines tokenized hierarchical Morgan fingerprints with graph‑distance‑dependent rotations applied at the input and within transformer self‑attention. The approach captures local chemistry, long‑range interactions, and molecular topology without requiring external pretraining or 3‑D conformer generation. Benchmarks on MoleculeNet and the Therapeutic Data Commons ADMET datasets show competitive performance, and a reconstruction procedure correctly identifies constitutional isomers for 92.6% of a 4,200‑molecule library.
By Robert Epps
arXiv:2605. 16823v2 Announce Type: replace Abstract: Large language models succeed by combining large-scale pretraining with meaningful discrete tokens.
By Takayuki Kimura
arXiv:2607. 03007v1 Announce Type: cross Abstract: Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding.
By Wenda Wang, Jinjia Feng, Zhewei Wei
Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of structurally distinct replacement molecules represe...
arXiv:2610.19920v1 Announce Type: new
Abstract: Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of st...
By Yanyi Su, Chenyan Wang, Yulei Gong, Yeyun Chen, Xiaohui Yang, Jun Cheng
arXiv:2606. 03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which molecular representation to use.
By Arun Raja, Garrett M. Morris, Kian Ming A. Chai
The paper reports a large-scale, compute-controlled study of Chemical Language Models (CLMs) involving over 30,000 experiments across different molecular representations, tokenizations, model sizes, datasets, and architectures. It finds clear scaling trends in pretraining loss but shows that these improvements do not translate into proportional gains in goal-directed molecular design, with chemical syntax saturating early while semantic properties develop more slowly. The authors release a new suite of models, NovoMolGen, that achieves state-of-the-art results in drug discovery tasks, highlighting a disconnect between representation learning and downstream design and calling for new pretraining paradigms that target chemical semantics.
By Roshan Balaji, Kamran Chitsaz, Quentin Fournier, Nirav Pravinbhai Bhatt, Sarath Chandar
arXiv:2510.07289v2 Announce Type: replace
Abstract: Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated s...
By Xingtong Yu, Chang Zhou, Xinming Zhang, Yuan Fang