Chemical Science

9 papers9 directions
Chemical Science serves as a venue for research at the intersection of chemistry and artificial intelligence, focusing on the application of machine learning to molecular and materials discovery. The journal publishes work on generative molecular design, including methods to ensure synthesizability and diversity in low-bandgap molecules using techniques like Monte Carlo tree search. It also features research on deep learning-guided pharmacophore modeling for virtual screening and unsupervised learning for drug-likeness scoring. Technical contributions in this venue often address foundational challenges in machine learning for the physical sciences. This includes the development of active learning frameworks for interatomic potentials and strategies to overcome mode collapse in generative models. Research also explores the balance between model sensitivity and robustness in predicting chemical reaction yields, as well as the use of multi-fidelity deep learning for predicting molecular optical properties. The venue facilitates the analysis of experimental data, such as scattering and spectroscopy in materials chemistry, through automated computational methods. Prolific contributors to this field within the journal include researchers such as Seonghwan Seo, Woo Youn Kim, Rafael Gomez-Bombarelli, and Kirsten M.Ø. Jensen. The published works reflect a focus on integrating symmetry constraints and diversity penalties to improve the exploration of chemical space and the robustness of neural search algorithms.

Papers by Year

2026 1
2025 6
2024 1
2023 1

Top Research Directions

Research directions most represented by papers from this venue.

Integrating Environmental Context into Molecular Machine Learning 1
Quantum Transport Simulation with Non-Equilibrium Green's Functions 1
Predicting Activity Cliffs in Chemical Property Landscapes 1
Similarity Penalties for Diverse Optimization and Search 1
Active Learning for Machine Learning Interatomic Potentials 1
Bridging the Synthesizability Gap in Molecular Generation 1
Multi-Algorithm Benchmarking for Domain-Specific Predictive Modeling 1
Overcoming Mode Collapse in Generative Molecular Design 1
Stacked Generalization for Heterogeneous Ensemble Learning 1

Top Authors

AuthorPapers
Rafael Gomez-Bombarelli2
Seonghwan Seo2
Woo Youn Kim2
Chi Cheng1
Igor Rončević1
Jinho Chang1
Juan E. Peralta1
Juno Nam1
Kevin P. Greenman1
Raghavendra Selvan1
Thierry Langer1
William Green1
Zhen Liu1

Papers

TitleYear
PharmacoNet: deep learning-guided pharmacophore modeling for ultra-large-scale virtual screening2026
Base-mediated homologative rearrangement of nitrogen-oxygen bonds of N-methyl-N-oxyamides2025
Correction: Molecular Aharonov–Bohm-type interferometers based on porphyrin nanorings2025
Drug-likeness scoring based on unsupervised learning2025
Machine learning for analysis of experimental scattering and spectroscopy data in materials chemistry2025
Molecular Aharonov–Bohm-type interferometers based on porphyrin nanorings2025
Symmetry-constrained generation of diverse low-bandgap molecules with Monte Carlo tree search2025
Multi-fidelity prediction of molecular optical peaks with deep learning2024
The challenge of balancing model sensitivity and robustness in predicting yields: a benchmarking study of amide coupling reactions2023