An active representation learning method for reaction yield prediction with small-scale data

Communications Chemistry, Journal Year: 2025, Volume and Issue: 8(1)

Published: Feb. 10, 2025

Reaction optimization plays an essential role in chemical research and industrial production. To explore a large reaction system, practical issue is how to reduce the heavy experimental load for finding high-yield conditions. In this paper, we present efficient machine learning tool called "RS-Coreset", where key idea take advantage of deep representation techniques guide interactive procedure representing full space. Our proposed only uses small-scale data, say 2.5% 5% instances, predict yields We validate performance on three public datasets achieve state-of-the-art results. Moreover, apply assist realistic exploration Lewis base-boryl radicals enabled dechlorinative coupling reactions our lab. The can help us effectively even discover several feasible combinations that were overlooked previous articles. Optimization systems crucial production, but represents significant challenge given required find optimal high-yielding Here, authors introduce tool, RS-Coreset, they space, enabling yield prediction with data.

Language: Английский

---

FluoBase: a fluorinated agents database

Journal of Cheminformatics, Journal Year: 2025, Volume and Issue: 17(1)

Published: Feb. 11, 2025

Organofluorine compounds, owing to their unique physicochemical properties, play an increasingly crucial role in fields such as medicine, pesticides, and advanced materials. Fluorinated reagents are indispensable for developing efficient synthetic methods organofluorine compounds serve the cornerstone of chemistry. Equally important fluorinated functional molecules, which contribute specific properties necessary applications pharmaceuticals, agrochemicals, materials science. However, information about these agents' structure, functions is scattered throughout vast literature, making it inconvenient chemists access utilize them effectively. Recognizing need a dedicated organized resource, we present FluoBase—a comprehensive agents database designed streamline key agents. FluoBase aims become premier resource related fluorine chemistry, serving scientific community anyone interested chemistry machine learning property predictions. freely available at https://fluobase.siochemdb.com . Scientific contribution provide on structures, molecules.

Language: Английский

---

Multi‐modal Homogeneous Chemical Reaction Performance Prediction with Graph and Chemical Language Information

Chinese Journal of Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 20, 2025

Comprehensive Summary Accurate prediction for chemical reaction performance offers optimal direction synthetic development. To this end, we present a novel multi‐modal model called MMHRP‐GCL to achieve the of homogeneous yield, enantioselectivity, and activation energy by fusing information from text graph modalities, requiring only 8 simple descriptors Reaction SMILES obtained without high‐cost DFT computation, capable managing reactions involving fluctuating number molecules. Experimental results on 4 datasets show that outperforms at least 7 generalized SOTA methods. Ablation study confirms critical roles complementation as well significance modality alignment atomic features in prediction. Albeit there is still room improvement interpretation relationships, has remarkable ability identify important atoms. A statistically interpretable feature importance test challenging dataset further demonstrates utility potential model. As high‐accuracy, low‐cost, interpretable, general model, provides valuable guidance design forward predictors catalytic reactions.

Language: Английский

---

YieldFCP: Enhancing reaction Yield prediction via Fine-grained Cross-modal Pre-training

Artificial Intelligence Chemistry, Journal Year: 2025, Volume and Issue: 3(1), P. 100085 - 100085

Published: March 1, 2025

Language: Английский

---

Chat-microreactor: A large-language-model-based assistant for designing continuous flow systems

Chemical Engineering Science, Journal Year: 2025, Volume and Issue: unknown, P. 121567 - 121567

Published: March 1, 2025

Language: Английский

---

CrownBind-IA: A machine learning model predicting binding constants between crown ethers and alkali metal ions

Chinese Chemical Letters, Journal Year: 2025, Volume and Issue: unknown, P. 111149 - 111149

Published: March 1, 2025

Language: Английский

---

The Unexploring Optoelectronic Features in Organic Trans-Dimensional Materials of Gridofluorenes at the Nanoscale

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 3888 - 3903

Published: April 10, 2025

Organic grido-architectures offer not only state-of-the-art models for exploring the complex relationships of multicarrier coherence among excitons, charges, photons, electrons, and phonons but also organic high-dimensional nanomaterials flexible electronics intelligence. Herein, we initiate fundamental progress perspective on gridofluorene-based zero-, one-, two-, three-dimensional nanomolecules their optoelectronic features. From future point view, sterically trans-dimensional hierarchically cross-scale effects these covalent frameworks nanostructures are discussed photophysical, electrical, mechanical thermal properties. multiscale systems, with feature synergistically molecule-programmable integration diverse functionalities, open a bright door to electronics, intelligent molecules, devices, even organobots as well artificially robotic chemists (AiRCs).

Language: Английский

---

Facilitating Charge Spatial Separation for Efficient Photocatalytic H₂O₂ Production via Ester‐Oxygen Bridged Organic Anthraquinone and Curved Open‐Ring g‐C₃N₄ Structures

Advanced Functional Materials, Journal Year: 2025, Volume and Issue: unknown

Published: April 21, 2025

Abstract Photocatalytic two‐electron oxygen reduction for hydrogen peroxide (H 2 O ) production represents a cost‐effective and sustainable synthetic approach. Inexpensive carbon nitride (g‐C 3 N 4 features tunable bandgap impressive photocatalytic performance in the 2e − ORR. This study presents design of defect vacancy ring‐opening g‐ that introduces specific C─OH sites at edges ring openings. The is covalently bonded to anthraquinone (AQ) via ester C─O─C═O bridges, resulting CN─O─AQ catalyst characterized by silk‐like, ordered stacked layer structure. incorporation specialized bridge bonds alters charge transport dynamics, establishing rapid diffusion pathways enhance electron migration surface during photoactivated reaction. synergistic effects optimizing (100) crystal plane crystallinity introducing dual O/Cl element doping promote development new light absorption centers lower adsorption energy while creating suitable vacancies. achieved an H yield 626 mmol L −1 , which 14.9 times higher than pure CN (42 ). work elucidates impact modulating both electronic structures on performance, offering valuable insights designing strategies organic conjugated structure catalysts.

Language: Английский

---

Controllable Radical Reactions of 1,3-Dienes with Light

ACS Catalysis, Journal Year: 2025, Volume and Issue: unknown, P. 7749 - 7779

Published: April 25, 2025

Language: Английский

---

High-throughput experimentation and machine learning-promoted synthesis of α-phosphoryloxy ketones via Ru-catalyzed P(O)O-H insertion reactions of sulfoxonium ylides

Science China Chemistry, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 10, 2024

Language: Английский

---