Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining

• URL: http://arxiv.org/abs/2606.17445v1
• Date: Tue, 16 Jun 2026 03:00:52 GMT
• Title: Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining
• Abstract summary: We present a conditional catalyst generative model based on the Generative Pretrained Transformer architecture.<n>The model achieved 98% structural validity, 95% optimization validity, and high categorical condition fidelity.<n>Results show that large-scale autoregressive pre-training, combined with explicit property conditioning, provides a practical route toward controllable catalyst generation.
• Score: 0.20391237204597365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone. Although machine learning-based high-throughput screening has accelerated catalyst discovery, its efficiency inevitably declines as the search space grows, motivating the development of generative models that can directly construct catalysts with target properties. Here, we present a conditional catalyst generative model based on the Generative Pretrained Transformer architecture with a numerical embedding layer that enables the generation of catalyst structures conditioned on both categorical and continuous properties within a single autoregressive framework. The model was pretrained on 133 million catalyst structures and subsequently fine-tuned on approximately 460,000 optimized structures with associated categorical properties and binding energies for conditional generation. The resulting model achieved 98% structural validity, 95% optimization validity, and high categorical condition fidelity, with a 93 % joint match rate for adsorbate type and composition. For binding energy conditioning, the match rate of approximately 20% represents a four-fold improvement over the baseline training distribution, and the generated distributions shift systematically toward the target values, enabling a 1.5 to 4-fold improvement in screening efficiency for reaction-targeted catalyst discovery without additional fine-tuning. These results show that large-scale autoregressive pre-training, combined with explicit property conditioning, provides a practical route toward controllable catalyst generation and accelerated catalysts discovery.

Related papers

• Catalyst Diffusion Transformer: Generative Inverse Design of Heterogeneous Catalysts [0.18665975431697432]
  Catalyst Diffusion Transformer (CatDiT) is a unified framework for inverse catalyst design.<n>CatDiT generates valid and novel structures ranging from intermetallic alloys to oxide surfaces.
  arXiv  Detail & Related papers  (2026-07-27T11:11:33Z)
• CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery [1.9682121767943492]
  CatRetriever is a contrastive representation learning model that aligns slab and bulk crystal representations in a shared latent space.<n>From a slab query, CatRetriever accurately retrieves plausible parent bulk candidates with R@1 > 91% and R@3 > 98% on both the in-distribution and holdout evaluation sets.
  arXiv  Detail & Related papers  (2026-07-13T15:38:41Z)
• CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials [61.546562658308005]
  We propose QE-Catalytic-V2, a unified graph--text multimodal large language model for catalytic materials.<n>It integrates property prediction and inverse design within the same model and shared representation space.<n>Under this unified framework, QE-Catalytic-V2 can not only perform reliable property prediction but also generate and screen physically feasible CIF candidates.
  arXiv  Detail & Related papers  (2026-05-17T04:31:46Z)
• SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers [50.18388227899971]
  We present SaDiT, a novel framework that accelerates protein backbone generation by integrating SaProt Tokenization with a Diffusion Transformer (DiT) architecture.<n>Experiments demonstrate that SaDiT outperforms state-of-the-art models, including RFDiffusion and Proteina, in both computational speed and structural viability.
  arXiv  Detail & Related papers  (2026-02-06T13:50:13Z)
• Accelerating High-Throughput Catalyst Screening by Direct Generation of Equilibrium Adsorption Structures [0.0]
  We present DBCata, a deep generative model that integrates a periodic Brownian-bridge framework with an equivariant graph neural network to establish a low-dimensional transition manifold between unrelaxed and DFT-relaxed structures.<n>Upon training, DBCata effectively generates high-fidelity, interatomic distance mean absolute error (DMAE) of 0.035 text on the Catalysis-Hub dataset.<n>The corresponding DFT accuracy can be improved within 0.1 eV in 94% of instances by identifying and refining anomalous predictions.
  arXiv  Detail & Related papers  (2025-12-17T09:26:58Z)
• Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study [73.49945279707323]
  Electrocatalysts play a key role in hydrogen energy storage (HES), allowing the energy to be stored as hydrogen.<n>We introduce Catalyst GFlowNet, a generative model that leverages machine learning-based predictors of formation and energy to design crystal surfaces that act as efficient catalysts.<n>We demonstrate the performance of the model through a proof-of-concept application to the hydrogen evolution reaction, a key reaction in HES, for which we successfully identified platinum as the most efficient known catalyst.
  arXiv  Detail & Related papers  (2025-10-02T15:49:39Z)
• Fitness aligned structural modeling enables scalable virtual screening with AuroBind [56.720030595081845]
  We present AuroBind, a scalable virtual screening framework that fine-tunes a custom atomic-level structural model on million-scale chemogenomic data.<n>AuroBind integrates direct preference optimization, self-distillation from high-confidence complexes, and a teacher-student acceleration strategy.<n>In a prospective screen across ten disease-relevant targets, AuroBind achieved experimental hit rates of 7-69%, with top compounds reaching sub-nanomolar to picomolar potency.
  arXiv  Detail & Related papers  (2025-08-04T07:34:48Z)
• Generative Language Model for Catalyst Discovery [0.0]
  We introduce the Catalyst Generative Pretrained Transformer (CatGPT), trained to generate string representations of inorganic catalyst structures from a vast chemical space. CatGPT not only demonstrates high performance in generating valid and accurate catalyst structures but also serves as a foundation model for generating desired types of catalysts.
  arXiv  Detail & Related papers  (2024-07-19T05:34:08Z)
• Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning [17.00084254889438]
  High-performance catalysts are crucial for sustainable energy conversion and human health. The discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and composition spaces.
  arXiv  Detail & Related papers  (2024-04-18T18:11:06Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• Turning hazardous volatile matter compounds into fuel by catalytic steam reforming: An evolutionary machine learning approach [2.1026063307327045]
  This study is the first to develop a machine-learning-based research framework for modeling, understanding, and optimizing the catalytic steam reforming of volatile matter compounds. Toluene catalytic steam reforming is used as a case study to show how chemical/textural analyses can be used to obtain input features for machine learning models.
  arXiv  Detail & Related papers  (2023-07-25T16:29:07Z)
• Catalysis distillation neural network for the few shot open catalyst challenge [1.1878820609988694]
  This paper introduces Few-Shot Open Catalyst Challenge 2023, a competition aimed at advancing the application of machine learning for predicting reactions. We propose a machine learning approach based on a framework called Catalysis Distillation Graph Neural Network (CDGNN) Our results demonstrate that CDGNN effectively learns embeddings from catalytic structures, enabling the capture of structure-adsorption relationships.
  arXiv  Detail & Related papers  (2023-05-31T04:23:56Z)
• PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design [102.9593507372373]
  Catalyst materials play a crucial role in the electrochemical reactions involved in industrial processes. Machine learning holds the potential to efficiently model materials properties from large amounts of data. We propose task-specific innovations applicable to most architectures, enhancing both computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-11-22T05:24:30Z)
• Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based Single-Atom Alloy Catalysts for CO2 Reduction Reaction [61.9212585617803]
  Graph neural networks (GNNs) have drawn more and more attention from material scientists. We develop a multi-task (MT) architecture based on DimeNet++ and mixture density networks to improve the performance of such task.
  arXiv  Detail & Related papers  (2022-09-15T13:52:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.