Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules

Review Chemistry, Multidisciplinary

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

Zhengkai Tu et al.

Summary: Predictive chemistry relates to the development of models describing molecular interactions and reactions, with the potential to accelerate the development and discovery of organic reactions and advance synthetic chemistry.

CHEMICAL SCIENCE (2023)

Add to Collection

Article Multidisciplinary Sciences

Inverse design of 3d molecular structures with conditional generative neural networks

Niklas W. A. Gebauer et al.

Summary: The authors propose a conditional generative neural network for the inverse design of 3d molecular structures. This approach allows targeted sampling of novel molecules with specified chemical and structural properties, even in domains with sparse reference calculations.

NATURE COMMUNICATIONS (2022)

Add to Collection

Article Multidisciplinary Sciences

Organic materials repurposing, a data set for theoretical predictions of new applications for existing compounds

Omer H. Omar et al.

Summary: This study presents a data set of 48,182 organic semiconductors prepared through documented synthetic pathways and stable in solid state. The data set contains electronic properties relevant to organic materials research, and provides electronic wavefunctions for further analysis. The unbiased data set offers a great starting point for exploring new applications and gaining novel physical insights into known materials.

SCIENTIFIC DATA (2022)

Add to Collection

Article Chemistry, Physical

Classifying the toxicity of pesticides to honey bees via support vector machines with random walk graph kernels

Ping Yang et al.

Summary: Pesticides play a beneficial role in agriculture but can unintentionally harm bees, necessitating toxicity assessment of candidate pesticides. A support vector machine (SVM) was trained to predict pesticide toxicity to bees using a dataset of 382 molecules, achieving good performance. Different representations of pesticide molecules were compared, with the MACCS-FP-SVM performing on par/marginally better than the L-RWGK-SVM.

JOURNAL OF CHEMICAL PHYSICS (2022)

Add to Collection

Article Chemistry, Physical

Data-driven modeling of S0 → S1 excitation energy in the BODIPY chemical space: High-throughput computation, quantum machine learning, and inverse design

Amit Gupta et al.

Summary: Derivatives of BODIPY are popular fluorophores known for their synthetic feasibility, high quantum yield, and tunable spectroscopic properties. Time-dependent long-range corrected hybrid density functional methods can model the lowest excitation energies with a semi-quantitative precision of +/- 0.3 eV.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Aditya Nandy et al.

Summary: This review focuses on the techniques that enable high-throughput search of transition-metal chemical space, covering the development and limitations of traditional computational chemistry along with leveraging experimental data sources. It discusses how advances in statistical modeling, artificial intelligence, and automation accelerate the discovery of lead compounds and design rules in transition-metal chemistry.

CHEMICAL REVIEWS (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Combining machine learning and high-throughput experimentation to discover photocatalytically active organic molecules

Xiaobo Li et al.

Summary: Organic molecules play a crucial role in photocatalysts, but reliable structure-property design rules are difficult to formulate. By integrating experiment, computation, and machine learning, researchers were able to identify common structural features in molecules with high catalytic activity. The study marks a step towards the machine-learning assisted discovery of molecular organic photocatalysts, with potential applications beyond photocatalytic hydrogen evolution.

CHEMICAL SCIENCE (2021)

Add to Collection

Review Chemistry, Multidisciplinary