☆ 4.8 Article

Generative organic electronic molecular design informed by quantum chemistry

CHEMICAL SCIENCE (2023)

Related references

Note: Only part of the references are listed.

Article Chemistry, Multidisciplinary

Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using a Machine Learning Potential

Simon Axelrod et al.

Summary: This article introduces a computational tool for predicting the thermal half-lives of azobenzene derivatives, which are key photoswitches in light-activated drugs. Through machine learning and quantum chemistry data, the authors automated the prediction of thermal half-lives for 19,000 azobenzene derivatives and explored trends and trade-offs between barriers and absorption wavelengths.

NANO LETTERS (2023)

Add to Collection

Article Chemistry, Physical

Exploration and Exploitation Approaches Based on Generative Machine Learning to Identify Potent Small Molecule Inhibitors of α-Synuclein Secondary Nucleation

Robert I. Horne et al.

Summary: The lack of approved disease-modifying drugs for Parkinson's disease is a major concern. Previous clinical trials targeting alpha-synuclein aggregation have faced challenges in identifying effective compounds. In this study, a machine learning approach was used to find small molecules that can reduce the production of oligomeric species through perturbing the kinetics of aggregation.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2023)

Add to Collection

Article Chemistry, Multidisciplinary

Generative Models as an Emerging Paradigm in the Chemical Sciences

Olexandr Isayev et al.

Summary: Traditional computational approaches to chemical species design are limited by the need to compute properties for a large number of candidates. Inverse design methods use generative modeling to optimize chemical structures based on desired properties. This article provides an overview and critical analysis of popular generative algorithms and discusses their potential applications in chemistry.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2023)

Add to Collection

Article Chemistry, Physical

Singlet Fission Driven by Excited-State Intramolecular Proton Transfer (ESIPT+SF): A (TD)DFT Study

Diego Lopez-Carballeira et al.

Summary: Singlet fission is a process that can generate two triplet excitons from one high-energy photon absorption. However, the instability of known singlet fission materials has hindered their practical usage. To overcome this limitation, we propose a novel process combining excited-state intramolecular proton transfer and singlet fission (ESIPT+SF). A computational analysis in this study identifies potential ESIPT+SF materials.

CHEMPHOTOCHEM (2023)

Add to Collection

Article Chemistry, Medicinal

Can Generative-Model-Based Drug Design Become a New Normal in Drug Discovery?

Hongming Chen

Summary: While AI applications in drug discovery are increasing, examples with full DMTA outcomes are still rare. A recent study demonstrated the potential of a generative model in the drug discovery process, showing that ideas generated by AI could be validated through wet-lab works.

JOURNAL OF MEDICINAL CHEMISTRY (2022)

Add to Collection

Article Chemistry, Physical

Actively Searching: Inverse Design of Novel Molecules with Simultaneously Optimized Properties

Nicolae C. Iovanac et al.

Summary: Combining quantum chemistry characterizations with generative machine learning models can accelerate molecular discovery. An active learning approach is used to improve the performance of multi-target generative chemical models by gradually refining the model's understanding of targeted areas of chemical space. This approach does not require modifications to existing generative approaches and can be applied to optimize multiple properties simultaneously.

JOURNAL OF PHYSICAL CHEMISTRY A (2022)

Add to Collection

Article Chemistry, Multidisciplinary

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Tobias Gensch et al.

Summary: The design of molecular catalysts often involves reconciling conflicting property requirements and efficient screening of candidate catalysts. This article introduces a data-driven discovery platform called kraken, which can be used to build predictive models and blueprints for novel catalyst designs. By calculating physicochemical descriptors and utilizing machine learning methods, kraken enables prediction of properties for a large number of new ligands, accelerating ligand selection in catalytic reaction optimization.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Design of Organic Electronic Materials With a Goal-Directed Generative Model Powered by Deep Neural Networks and High-Throughput Molecular Simulations

H. Shaun Kwak et al.

Summary: Generative machine learning methods have gained significant attention in recent years as they can enable more directed design without design bias. Data-driven approaches, on the other hand, have emerged as a new tool to accelerate the development of novel organic electronic materials, particularly for OLED applications.

FRONTIERS IN CHEMISTRY (2022)

Add to Collection

Article Chemistry, Medicinal

LibINVENT: Reaction-based Generative Scaffold Decoration for in Silico Library Design

Vendy Fialkova et al.

Summary: The researchers have proposed a novel drug design tool called LibINVENT, capable of rapidly designing chemical libraries with shared cores and maximizing desirable properties. In addition, users can list specific chemical reactions for library creation, making this tool flexible for lead optimization.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

Add to Collection

Review Chemistry, Applied

Machine Learning for the Discovery, Design, and Engineering of Materials

Chenru Duan et al.

Summary: Machine learning plays a crucial role in high-throughput screening and computational discovery of materials, but challenges remain. It can surpass physics-based models, accelerate them, or integrate with them. The ultimate goal is to realize ML as a widespread tool for practical computational materials design.

ANNUAL REVIEW OF CHEMICAL AND BIOMOLECULAR ENGINEERING (2022)

Add to Collection

Article Biotechnology & Applied Microbiology

Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery

Aditya Nandy et al.

Summary: Machine learning-accelerated discovery requires large amounts of high-fidelity data. However, the challenging nature and high cost of data generation in materials discovery have resulted in scarce and dubious quality data. Data-driven techniques such as using consensus across functionals, developing new theories, and detecting areas where computationally demanding methods are necessary are helping overcome these limitations. When properties cannot be reliably simulated, large experimental data sets can be used to train ML models. Moreover, advancements in natural language processing and automated image analysis enable the learning of structure-property relationships from literature.

CURRENT OPINION IN CHEMICAL ENGINEERING (2022)

Add to Collection

Article Chemistry, Physical

Either Accurate Singlet-Triplet Gaps or Excited-State Structures: Testing and Understanding the Performance of TD-DFT for TADF Emitters

Thomas Froitzheim et al.

Summary: This study examines the performance of TDA-DFT methods in predicting Delta EST values, finding that calculating Delta EST at the ground-state structure is the most effective strategy but it introduces systematic deviations. More rigorous approaches, although more accurate, have larger errors.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2022)

Add to Collection

Article Chemistry, Medicinal

Beyond the Ground State: Predicting Electron Ionization Mass Spectra Using Excited-State Molecular Dynamics

Oliver Fiehn et al.

Summary: In this study, an algorithm is introduced to incorporate excited states into the molecular dynamics prediction of electron ionization mass spectra. The results demonstrate that excited-state molecular dynamics can provide more accurate predictions of experimental spectra compared to calculations using only ground-state occupation.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

Add to Collection

Review Chemistry, Multidisciplinary

Recent advances in triplet-triplet annihilation upconversion and singlet fission, towards solar energy applications

Andrew J. Carrod et al.

Summary: This article introduces two processes for increasing solar light utilization: triplet-triplet annihilation upconversion (TTA-UC) and singlet fission (SF). Although these two fields are often studied separately, they are actually reverse processes of each other. This article consolidates research in both areas, highlighting their similarities and common challenges, and provides recommendations for future work.

ENERGY & ENVIRONMENTAL SCIENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Multi-objective goal-directed optimization of de novo stable organic radicals for aqueous redox flow batteries

Shree S. Sowndarya et al.

Summary: Advances in goal-directed molecular optimization provide hope for finding feasible candidates for challenging molecular design applications. In this study, a new open-source molecular optimization framework based on AlphaZero coupled with machine learning and quantum chemistry simulations was developed to find stable radical compounds that satisfy redox and stability requirements.

NATURE MACHINE INTELLIGENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Improving de novo molecular design with curriculum learning

Jeff Guo et al.

Summary: Guo and colleagues introduce curriculum learning extension to REINVENT, a de novo molecular design framework, which improves training efficiency by providing increasingly difficult problems over epochs.

NATURE MACHINE INTELLIGENCE (2022)

Add to Collection

Review Chemistry, Physical

Singlet fission photovoltaics: Progress and promising pathways

Alexander J. Baldacchino et al.

Summary: Singlet fission is a process in which a high-energy singlet exciton separates into two lower energy triplet excitons, with high quantum efficiency and potential for reducing energy losses in photovoltaic cells. Efforts have been made in the past decade to incorporate singlet fission into solar cells, comparing and categorizing various device structures to identify promising avenues for future research and development.

CHEMICAL PHYSICS REVIEWS (2022)

Add to Collection

Article Chemistry, Physical

Discovery of lead low-potential radical candidates for organic radical polymer batteries with machine-learning-assisted virtual screening

Cheng-Han Li et al.

Summary: In this paper, a virtual screening campaign is conducted to identify lead low potential candidate molecules in the initial space. A trained Gaussian Process regression model is employed to accelerate the screening task, and a set of promising redox-active molecules and two Pareto-optimal molecules are identified.

JOURNAL OF MATERIALS CHEMISTRY A (2022)

Add to Collection

Review Chemistry, Medicinal

Generative Deep Learning for Targeted Compound Design

Tiago Sousa et al.

Summary: De novo molecular design is increasingly using generative models from Deep Learning to propose novel compounds with desired properties. Different optimization strategies can guide the generation process towards specific aims, such as biological activities, synthesis processes, or chemical features.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Importance of Engineered and Learned Molecular Representations in Predicting Organic Reactivity, Selectivity, and Chemical Properties

Liliana C. Gallegos et al.

Summary: Machine-readable chemical structure representations are essential for machine learning predictions of molecular properties; the featurization of chemical structures and new encoding methods are active research areas; expert-guided descriptors, learned features, and molecular graphs are used in different prediction tasks to learn complex relationships between structure and targets.

ACCOUNTS OF CHEMICAL RESEARCH (2021)

Add to Collection

Review Biochemistry & Molecular Biology

Generative chemistry: drug discovery with deep learning generative models

Yuemin Bian et al.

Summary: The creativity of deep learning generative models can enhance the efficiency of drug discovery, involving the generation of original texts, images, and videos. The field of generative chemistry utilizes various advanced generative architectures, including recurrent neural networks, variational autoencoders, adversarial autoencoders, and generative adversarial networks, to accelerate compound generation.

JOURNAL OF MOLECULAR MODELING (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems

John A. Keith et al.

Summary: The article discusses the potential impact of machine learning models on chemical sciences and emphasizes the importance of collaboration between expertise in computer science and physical sciences. It provides concise tutorials of computational chemistry and machine learning methods, and demonstrates how they can be used together to provide insightful predictions.

CHEMICAL REVIEWS (2021)

Add to Collection

Article Chemistry, Physical

Software for the frontiers of quantum chemistry: An overview of developments in the Q-Chem 5 package

Evgeny Epifanovsky et al.

Summary: This article summarizes the technical advances in the fifth major release of the Q-Chem quantum chemistry program package, which includes developments since 2015. Q-Chem 5 features a variety of new many-body methods, core-level spectroscopy modeling tools, vibronic spectrum calculation methods, high-performance capabilities, and support for multithreaded parallelism. The software is continuously evolving with the support of an open teamware model and increasingly modular design, backed by a community of over 100 active academic developers.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Article Chemistry, Physical

De Novo Design of Molecules with Low Hole Reorganization Energy Based on a Quarter-Million Molecule DFT Screen

Gabriel Marques et al.

Summary: Three novel design methods utilizing machine learning models were applied to discover new molecules with potentially higher mobilities for printed electronics applications, showing the possibility of developing an extrapolative materials design protocol.

JOURNAL OF PHYSICAL CHEMISTRY A (2021)

Add to Collection

Review Materials Science, Multidisciplinary

High-throughput virtual screening for organic electronics: a comparative study of alternative strategies

Omer H. Omar et al.

Summary: This review provides a comprehensive overview of high-throughput virtual screening for organic electronics materials, covering methodological choices, properties computation, candidate generation, and interesting findings beyond top candidates. The field is dynamic and constantly evolving to adapt to changing landscapes of applications, methodologies, and datasets.

JOURNAL OF MATERIALS CHEMISTRY C (2021)

Add to Collection

Article Chemistry, Physical

A time and resource efficient machine learning assisted design of non-fullerene small molecule acceptors for P3HT-based organic solar cells and green solvent selection

Asif Mahmood et al.

Summary: This study aims to predict the performance of P3HT based organic solar cells through machine learning models, selecting molecular descriptors with positive impact on PCE for better prediction, and providing new insights for material design and candidate selection.

JOURNAL OF MATERIALS CHEMISTRY A (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Unconventional singlet fission materials

Tobias Ullrich et al.

Summary: Singlet fission is a photophysical downconversion pathway that transforms a singlet excitation into two triplet excited states, offering potential applications in solar energy conversion devices and other areas. While the mechanistic understanding of SF has evolved rapidly, the limited number of suitable SF-chromophores poses a challenge, necessitating the search for new SF materials.

CHEMICAL SOCIETY REVIEWS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Inverse design of nanoporous crystalline reticular materials with deep generative models

Zhenpeng Yao et al.

Summary: Reticular frameworks are crystalline porous materials that have desirable properties for various applications, but the diversity of building blocks presents challenges for materials design. An automated nanoporous materials discovery platform powered by a supramolecular variational autoencoder is proposed for generative design of reticular materials, showing high fidelity in capturing structural features and promising optimization capability for gas separation.

NATURE MACHINE INTELLIGENCE (2021)

Add to Collection

Article Materials Science, Multidisciplinary

Evolving the Materials Genome: How Machine Learning Is Fueling the Next Generation of Materials Discovery

Changwon Suh et al.

Annual Review of Materials Research (2020)

Add to Collection

Article Chemistry, Medicinal

The Synthesizability of Molecules Proposed by Generative Models

Wenhao Gao et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

Add to Collection

Article Chemistry, Multidisciplinary

AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning

Samuel Genheden et al.

JOURNAL OF CHEMINFORMATICS (2020)

Add to Collection

Article Chemistry, Medicinal

REINVENT 2.0: An AI Tool for De Novo Drug Design

Thomas Blaschke et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

Add to Collection

Article Chemistry, Multidisciplinary

Memory-assisted reinforcement learning for diverse molecular de novo design

Thomas Blaschke et al.

JOURNAL OF CHEMINFORMATICS (2020)

Add to Collection

Review Chemistry, Multidisciplinary

Molecular insights and concepts to engineer singlet fission energy conversion devices

Ruben Casillas et al.

ENERGY & ENVIRONMENTAL SCIENCE (2020)

Add to Collection

Article Chemistry, Physical

Automated exploration of the low-energy chemical space with fast quantum chemical methods

Philipp Pracht et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Singlet fission in spiroconjugated dimers

Maria E. Sandoval-Salinas et al.

JOURNAL OF CHEMICAL PHYSICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Exploiting Excited-State Aromaticity To Design Highly Stable Singlet Fission Materials

Kealan J. Fallon et al.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2019)

Add to Collection

Article Chemistry, Physical

Discovery of blue singlet exciton fission molecules via a high-throughput virtual screening and experimental approach

Collin F. Perkinson et al.

JOURNAL OF CHEMICAL PHYSICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Dataset's chemical diversity limits the generalizability of machine learning predictions

Marta Glavatskikh et al.

JOURNAL OF CHEMINFORMATICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Randomized SMILES strings improve the quality of molecular generative models

Josep Arus-Pous et al.

JOURNAL OF CHEMINFORMATICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Singlet fission molecules among known compounds: finding a few needles in a haystack

Daniele Padula et al.

ENERGY & ENVIRONMENTAL SCIENCE (2019)

Add to Collection

Article Chemistry, Multidisciplinary

A graph-based genetic algorithm and generative model/Monte Carlo tree search for the exploration of chemical space

Jan H. Jensen

CHEMICAL SCIENCE (2019)

Add to Collection

Review Chemistry, Multidisciplinary

Theoretical Modeling of Singlet Fission

David Casanova

CHEMICAL REVIEWS (2018)

Add to Collection

Article Chemistry, Medicinal

SCScore: Synthetic Complexity Learned from a Reaction Corpus

Connor W. Coley et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2018)

Add to Collection

Article Chemistry, Physical

Coupled double triplet state in singlet fission

Hyungjun Kim et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Theoretical design of conjugated diradicaloids as singlet fission sensitizers: quinones and methylene derivatives

Diego Lopez-Carballeira et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2017)

Add to Collection

Article Chemistry, Multidisciplinary

Molecular de-novo design through deep reinforcement learning

Marcus Olivecrona et al.

JOURNAL OF CHEMINFORMATICS (2017)

Add to Collection

Article Chemistry, Physical

Substituent Effects on the Absorption and Fluorescence Properties of Anthracene

Salsabil Abou-Hatab et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2017)

Add to Collection

Article Chemistry, Physical

Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach

Rafael Gomez-Bombarelli et al.

NATURE MATERIALS (2016)

Add to Collection

Article Chemistry, Medicinal

ZINC 15-Ligand Discovery for Everyone

Teague Sterling et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2015)

Add to Collection

Article Chemistry, Physical

Electronic Relaxation in Benzaldehyde Evaluated via TD-DFT and Localized Diabatization: Intersystem Crossings, Conical Intersections, and Phosphorescence

Qi Ou et al.

JOURNAL OF PHYSICAL CHEMISTRY C (2013)

Add to Collection

Article Chemistry, Multidisciplinary

Quantifying the chemical beauty of drugs

G. Richard Bickerton et al.

NATURE CHEMISTRY (2012)

Add to Collection

Article Chemistry, Multidisciplinary

Open Babel: An open chemical toolbox

Noel M. O'Boyle et al.

JOURNAL OF CHEMINFORMATICS (2011)

Add to Collection

Review Chemistry, Multidisciplinary

Singlet Fission

Millicent B. Smith et al.

CHEMICAL REVIEWS (2010)

Add to Collection

Article Chemistry, Multidisciplinary

Singlet fission for dye-sensitized solar cells: Can a suitable sensitizer be found?

Irina Paci et al.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.