Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation

Researchers introduced Fraglingo, an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space, according to an arXiv paper (arXiv:2609.13519v1). Fraglingo predicts an attachment-aware fragment embedding and retrieves the next fragment through latent-space nearest-neighbor search, using a wildcard-anchored readout that represents the growing molecule from its active attachment site. On controlled property-conditional benchmarks, Fraglingo achieved stronger joint property control than comparably trained baselines while maintaining competitive validity, uniqueness, and novelty, and it generalized to fragment libraries up to 4x larger than those used during training without retraining.

arXiv:2609.13519v1 Announce Type: new Abstract: Molecular design is most effective when generation mirrors the edits chemists actually make: extending a scaffold, replacing a substituent, or decorating a scaffold at a specified attachment site while optimizing molecular properties. Fragment-based molecular design naturally supports this workflow, yet existing approaches often separate fragment selection from attachment prediction, first choosing a fragment from a fixed vocabulary and then predicting how it should be connected. This decoupling restricts generation to a closed fragment vocabulary and treats attachment as a separate prediction problem. We introduce Fraglingo, an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space. Fraglingo predicts an attachment-aware fragment embedding and retrieves the next fragment through latent-space nearest-neighbor search. To encode attachment context, we introduce a wildcard-anchored readout that represents the growing molecule from the perspective of its active attachment site, enabling the predicted embedding to capture both the molecular context and the required attachment. Because generation operates in a continuous embedding space rather than over fixed fragment identifiers, new fragments can be added to the inference-time vocabulary without retraining, provided their embeddings can be computed by the trained fragment encoder. This retrieval-based formulation provides a unified generation primitive for molecule generation, scaffold generation, scaffold decoration, and molecular optimization. On controlled property-conditional benchmarks, Fraglingo achieves stronger joint property control than comparably trained baselines while maintaining competitive validity, uniqueness, and novelty. Furthermore, Fraglingo generalizes to fragment libraries up to 4x larger than those used during training without retraining.