Machine intelligence for chemical reaction space

Discovering new reactions, optimizing their performance, and extending the synthetically accessible chemical space are critical drivers for major technological advances and more sustainable processes. The current wave of machine intelligence is revolutionizing all data‐rich disciplines. Machine intelligence has emerged as a potential game‐changer for chemical reaction space exploration and the synthesis of novel molecules and materials. Herein, we will address the recent development of data‐driven technologies for chemical reaction tasks, including forward reaction prediction, retrosynthesis, reaction optimization, catalysts design, inference of experimental procedures, and reaction classification. Accurate predictions of chemical reactivity are changing the R&D processes and, at the same time, promoting an accelerated discovery scheme both in academia and across chemical and pharmaceutical industries. This work will help to clarify the key contributions in the fields and the open challenges that remain to be addressed.

• Publication year

  2022

• Venue

  WIREs Computational Molecular Science

• Publication date

  2022-03-07

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1002/wcms.1604
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Biocatalysed synthesis planning using data-driven learning

  2022cited by this paper
• Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity

  2021cited by this paper
• RetroPrime: A Diverse, Plausible and Transformer-based Method for Single-Step Retrosynthesis Predictions

  2021cited by this paper
• Adsorption Enthalpies for Catalysis Modeling through Machine-Learned Descriptors.

  2021cited by this paper
• The Genesis of Molecular Volcano Plots.

  2021cited by this paper
• Bayesian reaction optimization as a tool for chemical synthesis

  2021cited by this paper
• GTA: Graph Truncated Attention for Retrosynthesis

  2021cited by this paper
• Self-Improved Retrosynthetic Planning

  2021influential reference
• Chemist Ex Machina: Advanced Synthesis Planning by Computers.

  2021cited by this paper
• Valid, Plausible, and Diverse Retrosynthesis Using Tied Two-Way Transformers with Latent Variables

  2021cited by this paper
• Reaction coordinates in complex systems-a perspective

  2021cited by this paper
• The Open Reaction Database.

  2021cited by this paper
• Machine learning based energy-free structure predictions of molecules, transition states, and solids

  2021cited by this paper
• Reaction-based machine learning representations for predicting the enantioselectivity of organocatalysts

  2021cited by this paper
• Kernel Methods for Predicting Yields of Chemical Reactions

  2021cited by this paper
• A graph-convolutional neural network for addressing small-scale reaction prediction.

  2021cited by this paper
• Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention

  2021cited by this paper
• Reaction classification and yield prediction using the differential reaction fingerprint DRFP

  2021cited by this paper
• Dreams, False Starts, Dead Ends, and Redemption: A Chronicle of the Evolution of a Chemoinformatic Workflow for the Optimization of Enantioselective Catalysts.

  2021cited by this paper
• Extraction of organic chemistry grammar from unsupervised learning of chemical reactions

  2021influential reference
• When SMILES Smiles, Practicality Judgment and Yield Prediction of Chemical Reaction via Deep Chemical Language Processing

  2021cited by this paper
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Prediction

  2021influential reference
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction

  2021cited by this paper
• RegioSQM20: improved prediction of the regioselectivity of electrophilic aromatic substitutions

  2020cited by this paper
• Unassisted Noise-Reduction of Chemical Reactions Data Sets

  2020cited by this paper
• Substructure-based neural machine translation for retrosynthetic prediction

  2020cited by this paper
• Evaluating and clustering retrosynthesis pathways with learned strategy

  2020cited by this paper
• Direct Optimization across Computer-Generated Reaction Networks Balances Materials Use and Feasibility of Synthesis Plans for Molecule Libraries

  2020cited by this paper
• Machine learning meets mechanistic modelling for accurate prediction of experimental activation energies

  2020cited by this paper
• Machine Learning for Atomic Simulation and Activity Prediction in Heterogeneous Catalysis: Current Status and Future

  2020cited by this paper
• Barking up the right tree: an approach to search over molecule synthesis DAGs

  2020cited by this paper
• ReactionCode: format for reaction searching, analysis, classification, transform, and encoding/decoding

  2020cited by this paper
• DRACON: disconnected graph neural network for atom mapping in chemical reactions.

  2020cited by this paper
• A machine learning scheme for the catalytic activity of alloys with intrinsic descriptors

  2020cited by this paper
• Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions

  2020cited by this paper
• What can reaction databases teach us about Buchwald–Hartwig cross-couplings?

  2020cited by this paper
• Automatic retrosynthetic route planning using template-free models

  2020cited by this paper
• Retrosynthesis with attention-based NMT model and chemical analysis of “wrong” predictions

  2020cited by this paper
• RetroXpert: Decompose Retrosynthesis Prediction like a Chemist

  2020cited by this paper
• Generating transition states of isomerization reactions with deep learning.

  2020cited by this paper
• Towards efficient discovery of green synthetic pathways with Monte Carlo tree search and reinforcement learning

  2020influential reference
• Iterative Experimental Design Based on Active Machine Learning Reduces the Experimental Burden Associated with Reaction Screening

  2020cited by this paper
• Learning quadrupedal locomotion over challenging terrain

  2020cited by this paper
• Computational planning of the synthesis of complex natural products

  2020cited by this paper
• Optimol : Optimization of Binding Affinities in Chemical Space for Drug Discovery

  2020cited by this paper
• Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates

  2020influential reference
• State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis

  2020influential reference
• CompRet: a comprehensive recommendation framework for chemical synthesis planning with algorithmic enumeration

  2020cited by this paper
• Quantum machine learning using atom-in-molecule-based fragments selected on the fly

  2020influential reference
• AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning

  2020cited by this paper
• Mapping the space of chemical reactions using attention-based neural networks

  2020influential reference
• A machine learning framework for the analysis and prediction of catalytic activity from experimental data

  2020cited by this paper
• Prediction of chemical reaction yields using deep learning

  2020influential reference
• Heck reaction prediction using a transformer model based on a transfer learning strategy.

  2020cited by this paper
• A mobile robotic chemist

  2020cited by this paper
• Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

  2020influential reference
• Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

  2020cited by this paper
• Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

  2020cited by this paper
• Integrating Deep Neural Networks and Symbolic Inference for Organic Reactivity Prediction

  2020cited by this paper
• Predicting glycosylation stereoselectivity using machine learning

  2020cited by this paper
• Data Augmentation and Pretraining for Template-Based Retrosynthetic Prediction in Computer-Aided Synthesis Planning

  2020cited by this paper
• Atom‐to‐atom Mapping: A Benchmarking Study of Popular Mapping Algorithms and Consensus Strategies

  2020cited by this paper
• Data augmentation strategies to improve reaction yield predictions and estimate uncertainty

  2020cited by this paper
• Predicting enzymatic reactions with a molecular transformer

  2020cited by this paper
• Toward the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space.

  2020cited by this paper
• Combining generative artificial intelligence and on-chip synthesis for de novo drug design

  2020cited by this paper
• Retrosynthesis Prediction with Conditional Graph Logic Network

  2020cited by this paper
• Learning Graph Models for Retrosynthesis Prediction

  2020cited by this paper
• Data-Driven Advancement of Homogeneous Nickel Catalyst Activity for Aryl Ether Cleavage

  2020cited by this paper
• Adapting CHMTRN (CHeMistry TRaNslator) for a New Use

  2020cited by this paper
• Thousands of reactants and transition states for competing E2 and S N 2 reactions

  2020cited by this paper
• Accelerated discovery of CO2 electrocatalysts using active machine learning

  2020cited by this paper
• Predicting Regioselectivity in Radical C-H Functionalization of Heterocycles through Machine Learning.

  2020cited by this paper
• 'Ring Breaker': Neural Network Driven Synthesis Prediction of the Ring System Chemical Space.

  2020cited by this paper
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

  2020influential reference
• Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy

  2020influential reference
• The Synthesizability of Molecules Proposed by Generative Models

  2020cited by this paper
• Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

  2020cited by this paper
• A Bayesian algorithm for retrosynthesis

  2020cited by this paper
• Combining retrosynthesis and mixed-integer optimization for minimizing the chemical inventory needed to realize a WHO essential medicines list

  2020cited by this paper
• Deep Learning of Activation Energies

  2020cited by this paper
• A Graph to Graphs Framework for Retrosynthesis Prediction

  2020cited by this paper
• Summit: Benchmarking Machine Learning Methods for Reaction Optimisation

  2020cited by this paper
• Inferring experimental procedures from text-based representations of chemical reactions

  2020cited by this paper
• Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors

  2020cited by this paper
• Predicting chemical reaction outcomes: A grammar ontology‐based transformer framework

  2020cited by this paper
• Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias

  2020cited by this paper
• Reactants, products, and transition states of elementary chemical reactions based on quantum chemistry

  2019cited by this paper
• A retrosynthetic analysis algorithm implementation

  2019cited by this paper
• Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning

  2019cited by this paper
• Predicting Chemical Reaction Barriers with a Machine Learning Model

  2019cited by this paper
• A Model to Search for Synthesizable Molecules

  2019influential reference
• Learning Retrosynthetic Planning through Simulated Experience

  2019cited by this paper
• Automated de novo molecular design by hybrid machine intelligence and rule-driven chemical synthesis

  2019cited by this paper
• Predicting Retrosynthetic Reactions Using Self-Corrected Transformer Neural Networks

  2019cited by this paper
• Analyzing Learned Molecular Representations for Property Prediction

  2019cited by this paper
• Retrosynthesis with Attention-Based NMT Model and Chemical Analysis of the "Wrong" Predictions

  2019cited by this paper
• ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations

  2019cited by this paper
• Learning To Predict Reaction Conditions: Relationships between Solvent, Molecular Structure, and Catalyst

  2019cited by this paper
• A robotic platform for flow synthesis of organic compounds informed by AI planning

  2019influential reference

• Green and Sustainable Approaches for the Synthesis of Imidazo[1,2-a]Pyridines: Advances, Challenges, and Future Perspectives.

  2026cites this paper
• Benchmarking Isomerization Energies for C5$$ {\mathrm{C}}_5 $$ – C7$$ {\mathrm{C}}_7 $$ Hydrocarbons: The ISOC7 Database

  2026cites this paper
• Higher-Level Strategies for Computer-Aided Retrosynthesis

  2026cites this paper
• Toward generalizable predictive models for DNA-encoded libraries.

  2026cites this paper
• Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets

  2025cites this paper
• Artificial Intelligence (AI) in Pharmaceutical Formulation and Dosage Calculations

  2025cites this paper
• Geometry-Driven Attention Model with 3D Molecular Features for Multi-Property Prediction of OLED Materials

  2025cites this paper
• Improving Reaction Yield Prediction with Chemical Atom-Level Reaction Learning

  2025cites this paper
• Learning Multidimensional Electronegativity of Selected Atom Types in Organic Molecules Using Graph Neural Networks

  2025cites this paper
• Freedom Space 3.0: ML-Assisted Selection of Synthetically Accessible Small Molecules

  2025cites this paper
• Materials informatics: A review of AI and machine learning tools, platforms, data repositories, and applications to architectured porous materials

  2025cites this paper
• Transfer Learning for Heterocycle Retrosynthesis

  2025cites this paper
• TempRe: Template generation for single and direct multi-step retrosynthesis

  2025cites this paper
• Accelerated Discovery of Energy Transfer-Catalyzed Dearomative Cycloadditions through a Data-Driven Three-Layer Screening Strategy.

  2025cites this paper
• HiCLR: Knowledge-Induced Hierarchical Contrastive Learning with Retrosynthesis Prediction Yields a Reaction Foundation Model

  2025cites this paper
• Studying Noncovalent Interactions in Molecular Systems with Machine Learning

  2025cites this paper
• ASKCOS: Open-Source, Data-Driven Synthesis Planning.

  2025cites this paper
• Enhancing chemical reaction search through contrastive representation learning and human-in-the-loop

  2025cites this paper
• Large language models as uncertainty-calibrated optimizers for experimental discovery

  2025cites this paper
• Generate what you can make: achieving in-house synthesizability with readily available resources in de novo drug design

  2025cites this paper
• YieldFCP: Enhancing reaction Yield prediction via Fine-grained Cross-modal Pre-training

  2025cites this paper
• Multi-objective synthesis planning by means of Monte Carlo Tree search

  2025cites this paper
• Electron flow matching for generative reaction mechanism prediction

  2025cites this paper
• Chemical space as a unifying theme for chemistry

  2025cites this paper
• CLAIRE: a contrastive learning-based predictor for EC number of chemical reactions

  2025cites this paper
• Database Construction for the Virtual Screening of the Ruthenium-Catalyzed Hydrogenation of Ketones.

  2025cites this paper
• Adaptive experimentation and optimization in organic chemistry

  2025cites this paper
• Accelerating the Development of Sustainable Catalytic Processes through Data Science

  2025cites this paper
• Teaching Language Models Mechanistic Explainability Through Arrow-Pushing

  2025cites this paper
• Teaching Computer-Assisted Retrosynthesis Reaction Prediction with Open-Source Software

  2025cites this paper
• The consolidation of open-source computer-assisted chemical synthesis data into a comprehensive database

  2025cites this paper
• Computational synthesis design for controlled degradation and revalorization

  2024cites this paper
• Scientific Deep Machine Learning Concepts for the Prediction of Concentration Profiles and Chemical Reaction Kinetics: Consideration of Reaction Conditions.

  2024cites this paper
• Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

  2024cites this paper
• A genetic optimization strategy with generality in asymmetric organocatalysis as a primary target

  2024cites this paper
• Exploring Chemical Space Using Ab Initio Hyperreactor Dynamics

  2024cites this paper
• Prediction of chemical reaction yields with large-scale multi-view pre-training

  2024cites this paper
• Assessing the Extrapolation Capability of Template-Free Retrosynthesis Models

  2024cites this paper
• Exploring Chemical Reaction Space with Machine Learning Models: Representation and Feature Perspective

  2024cites this paper
• Expanding Chemical Representation with k-mers and Fragment-based Fingerprints for Molecular Fingerprinting

  2024cites this paper
• Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge.

  2024cites this paper
• Standardizing Substrate Selection: A Strategy toward Unbiased Evaluation of Reaction Generality

  2024cites this paper
• ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining

  2024influential citation
• BARTReact: SELFIES-Driven Precision in Reaction Modeling

  2024cites this paper
• Reaction-Agnostic Featurization of Bidentate Ligands for Bayesian Ridge Regression of Enantioselectivity

  2024cites this paper
• Deep Kernel learning for reaction outcome prediction and optimization

  2024cites this paper
• Finding Relevant Retrosynthetic Disconnections for Stereocontrolled Reactions

  2024cites this paper
• Estimating the synthetic accessibility of molecules with building block and reaction-aware SAScore

  2024cites this paper
• From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

  2024cites this paper
• Top 20 Influential AI-Based Technologies in Chemistry

  2024cites this paper
• Reaction Networks Resemble Low-Dimensional Regular Lattices.

  2024cites this paper
• Cost-informed Bayesian reaction optimization

  2024cites this paper
• In Context Learning and Reasoning for Symbolic Regression with Large Language Models

  2024cites this paper
• GLAS: an open-source easily expandable Git-based scheduling architecture for integral lab automation

  2024cites this paper
• Recent Advancements in the Application of Artificial Intelligence in Drug Molecular Generation and Synthesis Planning

  2024cites this paper
• Chemist-aligned retrosynthesis by ensembling diverse inductive bias models

  2024cites this paper
• Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planning

  2023influential citation
• ChemCrow: Augmenting large-language models with chemistry tools

  2023cites this paper
• Open data and algorithms for open science in AI-driven molecular informatics.

  2023cites this paper
• Artificial intelligence in multi-objective drug design.

  2023cites this paper
• Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons

  2023cites this paper
• Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges.

  2023cites this paper
• An explainability framework for deep learning on chemical reactions exemplified by enzyme-catalysed reaction classification

  2023cites this paper
• Qmugs 1.1: Quantum Mechanical Properties of Organic Compounds Commonly Encountered in Reactivity Datasets

  2023cites this paper
• RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction

  2023cites this paper
• A Customized Bayesian Algorithm to Optimize Enzyme-Catalyzed Reactions

  2023cites this paper
• Exploring the synergistic effects of hybrid grid partitioning and rough set method for fuzzy rule generation in dataset classification

  2023cites this paper
• Augmenting large language models with chemistry tools

  2023cites this paper
• SELFIES RxNet: Empowering Reaction Synthesis Through Symbolic Notations and AI

  2023cites this paper
• Bayesian Optimization of Catalysis With In-Context Learning

  2023cites this paper
• Computer‐assisted synthetic planning considering reaction kinetics based on transition state automated generation method

  2023cites this paper
• LinChemIn: SynGraph—a data model and a toolkit to analyze and compare synthetic routes

  2023cites this paper
• AiZynthTrain: Robust, Reproducible, and Extensible Pipelines for Training Synthesis Prediction Models

  2023cites this paper
• Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis

  2023cites this paper
• Machine learning approach for predicting the yield of pyrroles and dipyrromethanes condensation reactions with aldehydes

  2023cites this paper
• Gas–solid reactor optimization based on EMMS-DPM simulation and machine learning

  2023cites this paper
• Re-evaluating Retrosynthesis Algorithms with Syntheseus

  2023cites this paper
• Transformers and Large Language Models for Chemistry and Drug Discovery

  2023cites this paper
• Recent Applications of Machine Learning in Molecular Property and Chemical Reaction Outcome Predictions.

  2023cites this paper
• Scope of machine learning in materials research—A review

  2023cites this paper
• 3DReact: Geometric Deep Learning for Chemical Reactions

  2023cites this paper
• Holistic chemical evaluation reveals pitfalls in reaction prediction models

  2023cites this paper
• Revolutionizing the structural design and determination of covalent-organic frameworks: principles, methods, and techniques.

  2023cites this paper
• When Yield Prediction Does Not Yield Prediction: An Overview of the Current Challenges

  2023cites this paper
• Mining Large-Scale Knowledge Graphs for Chemical Reaction Fingerprints

  2023cites this paper
• In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science.

  2023cites this paper
• Language models in molecular discovery

  2023cites this paper
• Multistep retrosynthesis combining a disconnection aware triple transformer loop with a route penalty score guided tree search

  2023cites this paper
• Quantum Neural Network for Time Series Forecasting: Harnessing Quantum Computing's Potential in Predictive Modeling

  2023cites this paper
• A deep learning framework for accurate reaction prediction and its application on high-throughput experimentation data

  2023cites this paper
• AI-driven Hypernetwork of Organic Chemistry: Network Statistics and Applications in Reaction Classification

  2022cites this paper
• Supervised Training of Conditional Monge Maps

  2022cites this paper
• Bayesian optimisation for additive screening and yield improvements in chemical reactions – beyond one-hot encodings

  2022cites this paper
• Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction

  2022cites this paper
• Is GPT-3 all you need for machine learning for chemistry?

  2022cites this paper
• Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

  2022cites this paper
• AI-driven hypergraph network of organic chemistry: network statistics and applications in reaction classification

  2022cites this paper
• Differential top-k learning for template-based single-step retrosynthesis

  year unknowncites this paper
• Exploring Organic Syntheses through Natural Language

  year unknowncites this paper
• R EFRAMING LLM F INETUNING THROUGH B AYESIAN O PTIMIZATION L ENSES

  year unknowncites this paper