Pith. sign in

REVIEW 11 cited by

Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.05708 v1 pith:YTU3JDZ5 submitted 2023-05-09 cs.LG q-bio.QM

classification cs.LGq-bio.QM
keywords modelschemicallanguagedirectlystructuresdimensionsfilesprotein
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language models are powerful tools for molecular design. Currently, the dominant paradigm is to parse molecular graphs into linear string representations that can easily be trained on. This approach has been very successful, however, it is limited to chemical structures that can be completely represented by a graph -- like organic molecules -- while materials and biomolecular structures like protein binding sites require a more complete representation that includes the relative positioning of their atoms in space. In this work, we show how language models, without any architecture modifications, trained using next-token prediction -- can generate novel and valid structures in three dimensions from various substantially different distributions of chemical structures. In particular, we demonstrate that language models trained directly on sequences derived directly from chemical file formats like XYZ files, Crystallographic Information files (CIFs), or Protein Data Bank files (PDBs) can directly generate molecules, crystals, and protein binding sites in three dimensions. Furthermore, despite being trained on chemical file sequences -- language models still achieve performance comparable to state-of-the-art models that use graph and graph-derived string representations, as well as other domain-specific 3D generative models. In doing so, we demonstrate that it is not necessary to use simplified molecular representations to train chemical language models -- that they are powerful generative models capable of directly exploring chemical space in three dimensions for very different structures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How Well Can Frontier Large Language Models Generate Structures? High Quality Prediction of Molecular Geometries with Help from Fine-Tuning

    physics.chem-ph 2026-07 conditional novelty 7.0 of 10

    A fine-tuned LLM trained on Z-matrix representations generates accurate 3D molecular geometries and conformer ensembles, matching or beating the specialized DMCG model on GEOM benchmarks.

  2. Reaction-Network-Level Discovery of Ammonia Synthesis Catalysts via Ten-Million-Scale Generative Exploration

    physics.chem-ph 2026-06 unverdicted novelty 7.0 of 10

    Ten-million-scale generative Transformers with ML potentials map compatibility across N*, NH*, NNH*, and HNNH* to discover 279 ammonia synthesis catalyst candidates, recovering Fe/Ru motifs and identifying new familie...

  3. Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

    cs.LG 2026-07 conditional novelty 6.0 of 10

    General-purpose LLMs can satisfy simple local 3D constraints such as anchor fragments and pharmacophores, but their unoptimized poses dock much worse than those from specialized diffusion models.

  4. Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning

    physics.comp-ph 2026-07 conditional novelty 6.0 of 10

    A plain causal transformer that tokenizes atom positions in local frames generates 3D molecules directly; RL against an xTB relaxation reward lifts topology-preserving valid yield from ~50% to ~95%.

  5. AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org

    cs.AI 2025-12 reject novelty 6.0 of 10

    An open-source agentic materials-design platform shows tool access can help or hurt accuracy depending on the property, but its headline memorization-resistant test results are not presented.

  6. InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames

    cs.LG 2025-10 conditional novelty 6.0 of 10

    An autoregressive transformer with inertial-frame tokenization and geometric rotary positional encoding reports state-of-the-art validity and stability on QM9, GEOM-Drugs, and B3LYP, plus strong functional-group-condi...

  7. CrystalICL: Enabling In-Context Learning for Crystal Generation

    cs.LG 2025-08 conditional novelty 6.0 of 10

    CrystalICL is a few-shot crystal generation model combining space-group tokenization with multi-task instruction tuning.

  8. Kinetic Langevin Diffusion for Crystalline Materials Generation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    KLDM runs the diffusion process for crystal coordinates in Euclidean velocity space via left-trivialized kinetic Langevin dynamics on a torus, and reports competitive or state-of-the-art performance on CSP and DNG benchmarks.

  9. 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery

    cs.CE 2025-02 conditional novelty 6.0 of 10

    A dual-channel transformer that reads and writes 3D coordinates as continuous numbers alongside chemical tokens achieves state-of-the-art docking and pocket-aware molecule generation.

  10. TopoMAS: Large Language Model Driven Topological Materials Multiagent System

    cond-mat.mtrl-sci 2025-07 conditional novelty 4.0 of 10

    TopoMAS is a multi-agent LLM framework that automates retrieval, generation, and first-principles validation for topological materials, reporting 94.55% accuracy with a lightweight Qwen2.5-72B model.

  11. A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools

    cs.LG 2025-06 unverdicted novelty 4.0 of 10

    This survey organizes foundation models, LLM agents, datasets, and tools in materials science into six task areas.

Pith tools