arXiv AI
STAMP as a topology-aware molecular language for fragment-level learning and editing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 15
Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation
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.
arXiv AI
Jun 11
Augmenting Molecular Language Models with Local $n$-gram Memory
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.
arXiv Machine Learning
Oct 28
Coder as Editor: Code-driven Interpretable Molecular Editing
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.
arXiv Machine Learning
Jul 3
Probing Chemical Language Models: Effects of Pre-training and Fine-tuning
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.
arXiv Machine Learning
Sep 29
WEECFP-SuRGE: A Position-Aware Substructure Encoding Method for Molecular Property Prediction
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.
arXiv Machine Learning
Jun 9
VQ-Atom: Semantic Discretization of Local Atomic Environments for Molecular Representation Learning
arXiv:2605. 16823v2 Announce Type: replace Abstract: Large language models succeed by combining large-scale pretraining with meaningful discrete tokens.