Dynamic language model representations for multi-objective reaction optimisation

• URL: http://arxiv.org/abs/2609.11790v1
• Date: Thu, 10 Sep 2026 16:43:08 GMT
• Title: Dynamic language model representations for multi-objective reaction optimisation
• Abstract summary: We learn the reaction representation dynamically from text.<n>Across nickel- and palladium-catalysed cross-couplings, this approach reaches convergence in fewer experiments than descriptor libraries or one-hot encoding.
• Score: 5.640701143147006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimising chemical reactions across multiple objectives, such as yield, selectivity, and safety, is central to chemical synthesis, and model-driven approaches depend critically on how reaction components are represented. Established featurisations are either chemically uninformative, as with one-hot encodings, or, as with molecular descriptors, do not readily extend across chemically distinct components. For structurally and functionally diverse components, it is therefore unclear what a shared representation should contain. Constructing such a representation is itself a challenging research undertaking that must be revisited for each new reaction system. Here we bypass this step by learning the reaction representation dynamically from text. Textual descriptions of reaction conditions are encoded by a fine-tuned language model trained jointly with Gaussian process surrogates, yielding task-adaptive representations within a multi-objective Bayesian optimisation loop. Across nickel- and palladium-catalysed cross-couplings in both sequential and parallel experimentation regimes, this approach reaches optimisation convergence in fewer experiments than descriptor libraries or one-hot encoding. Applied prospectively to a palladium-catalysed cyanation spanning mixed ligand denticity and heterogeneous additives, and to a three-objective asymmetric hydrogenation across chiral iridium and ruthenium catalyst families, two rounds of high-throughput experimentation (192 reactions, under 3% of each design space) delivered conditions translating directly to gram scale in 94% and 84% isolated yield, the latter at 99.6% enantiomeric excess.

Related papers

• RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction [3.456440183560995]
  We propose reaction contrastive learning foundation (RxnCLF) for reaction representation learning.<n> RxnCLF is built on a condensed reaction graph (CRG) that unifies reactant and product information into a single graph.<n>Pretrained on 1.7 million Pistachio reactions, RxnCLF learns a compact and continuous latent space that captures both reaction-center features and broader side chain contexts.
  arXiv  Detail & Related papers  (2026-08-06T16:51:23Z)
• Reaction-Level Consistency within the Variational Quantum Eigensolver: Homodesmotic Ring Strain Energies of Cyclic Hydrocarbons [12.548381396085253]
  We employ a symmetry guided active space selection protocol to compute ring strain energies of cyclic hydrocarbons using homodesmotic reaction schemes.<n>The protocol enforces symmetry consistency across all reactants and products by selecting active spaces that yield identical symmetry matched fraction (SMF) values.<n>The systematic performance across increasing molecular complexity highlights the effectiveness of combining homodesmotic reaction design with symmetry-consistent VQE calculations.
  arXiv  Detail & Related papers  (2026-03-13T07:32:18Z)
• Rethinking Molecule Synthesizability with Chain-of-Reaction [47.744071119775676]
  We introduce ReaSyn, a generative framework for synthesizable projection.<n>We propose a novel perspective that views synthetic pathways akin to reasoning paths in large language models (LLMs)<n>With the CoR notation, ReaSyn can get dense supervision in every reaction step to explicitly learn chemical reaction rules.
  arXiv  Detail & Related papers  (2025-09-19T15:29:57Z)
• Learning Chemical Reaction Representation with Reactant-Product Alignment [50.28123475356234]
  RAlign is a novel chemical reaction representation learning model for various organic reaction-related tasks.<n>By integrating atomic correspondence between reactants and products, our model discerns the molecular transformations that occur during the reaction.<n>We introduce a reaction-center-aware attention mechanism that enables the model to concentrate on key functional groups.
  arXiv  Detail & Related papers  (2024-11-26T17:41:44Z)
• Measurement-Induced Transmon Ionization [69.65384453064829]
  We develop a comprehensive framework which provides a physical picture of the origin of transmon ionization. This framework identifies the multiphoton resonances responsible for transmon ionization. It also allows one to efficiently compute numerical estimates of the photon number threshold for ionization.
  arXiv  Detail & Related papers  (2024-02-09T18:46:50Z)
• Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model [9.878043289026731]
  Transition state (TS) search is key in chemistry for elucidating reaction mechanisms and exploring reaction networks. Here, we develop an object-aware SE(3) equivariant diffusion model that satisfies all physical symmetries and constraints for generating sets of structures in an elementary reaction. provided reactant and product, this model generates a TS structure in seconds instead of hours required when performing quantum chemistry-based optimizations.
  arXiv  Detail & Related papers  (2023-04-12T22:21:36Z)
• Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation [70.97737157902947]
  There is currently no universal and widely adopted method for robustly representing chemical reactions. Here we exploit graph-based representations of molecular structures to develop and test a hypergraph attention neural network approach. We evaluate this hypergraph representation in three experiments using three independent data sets of chemical reactions.
  arXiv  Detail & Related papers  (2022-01-02T12:33:10Z)
• Self-Improved Retrosynthetic Planning [66.5397931294144]
  Retrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule. Recent search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs) We propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties.
  arXiv  Detail & Related papers  (2021-06-09T08:03:57Z)
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning [107.64562550844146]
  Retrosynthesis is an emerging research area of deep learning. We propose a new approach that reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. For learning the score functions, we also propose a novel contrastive training scheme with hard negative mining.
  arXiv  Detail & Related papers  (2021-05-03T12:47:57Z)
• Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry [4.042350304426974]
  We introduce a predictive workflow for the extension of the reaction scope of chiral catalysts across name reactions. Whole geometry descriptors were encoded from DFT optimized 3D structures of multiple catalyst scaffolds. For the consensus prediction of ensemble models, this global descriptor can be compared with sterimol parameters and noncovalent interaction.
  arXiv  Detail & Related papers  (2021-03-25T20:08:56Z)

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.