Guided diffusion for inverse molecular design

Weiss, Tomer; Mayo Yanes, Eduardo; Chakraborty, Sabyasachi; Cosmo, Luca; Bronstein, Alex M.; Gershoni-Poranne, Renana

doi:10.1038/s43588-023-00532-0

Cited by 15 publications

(6 citation statements)

References 52 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Not only does the position of each atom need to be predicted, but also the conformation of the whole molecule needs optimization to ensure that the generated molecule is physically and chemically valid. In this regard, knowledge-driven algorithms and diffusion models − hold promise as potential aids in the future. By leveraging such tools, deep learning models may emulate the expertise of professionals, yielding generations that are consistent with established scientific principles and logically self-consistent.…”

Section: Perspectivesmentioning

confidence: 99%

Deep Learning-Assisted Spectrum–Structure Correlation: State-of-the-Art and Perspectives

Lu,

Wu,

et al. 2024

Anal. Chem.

View full text Add to dashboard Cite

Spectrum−structure correlation is playing an increasingly crucial role in spectral analysis and has undergone significant development in recent decades. With the advancement of spectrometers, the high-throughput detection triggers the explosive growth of spectral data, and the research extension from small molecules to biomolecules accompanies massive chemical space. Facing the evolving landscape of spectrum−structure correlation, conventional chemometrics becomes ill-equipped, and deep learning assisted chemometrics rapidly emerges as a flourishing approach with superior ability of extracting latent features and making precise predictions. In this review, the molecular and spectral representations and fundamental knowledge of deep learning are first introduced. We then summarize the development of how deep learning assist to establish the correlation between spectrum and molecular structure in the recent 5 years, by empowering spectral prediction (i.e., forward structure−spectrum correlation) and further enabling library matching and de novo molecular generation (i.e., inverse spectrum−structure correlation). Finally, we highlight the most important open issues persisted with corresponding potential solutions. With the fast development of deep learning, it is expected to see ultimate solution of establishing spectrum−structure correlation soon, which would trigger substantial development of various disciplines.

show abstract

Section: Perspectivesmentioning

confidence: 99%

Deep Learning-Assisted Spectrum–Structure Correlation: State-of-the-Art and Perspectives

Lu,

Wu,

et al. 2024

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…While 2D molecular representation models have achieved significant success in learning and extracting features, they neglect the crucial 3D structural information on molecules, ultimately limiting their accuracy. Inspired by advancements in computer vision and graphics within the 3D domain, particularly point cloud processing, , research on 3D representation has emerged in molecular generation − and property prediction . However, in the 3D domain, obtaining accurate geometry information remains a challenge.…”

Section: Introductionmentioning

confidence: 99%

PointGAT: A Quantum Chemical Property Prediction Model Integrating Graph Attention and 3D Geometry

Zhang,

Yuan,

Tian

2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Predicting quantum chemical properties is a fundamental challenge for computational chemistry. While the development of graph neural networks has advanced molecular representation learning and property prediction, their performance could be further enhanced by incorporating three-dimensional (3D) structural geometry into two-dimensional (2D) molecular graph representation. In this study, we introduce the PointGAT model for quantum molecular property prediction, which integrates 3D molecular coordinates with graph-attention modeling. Comparison with other current models in molecular prediction tasks showed that PointGAT could provide higher predictive accuracy in various benchmark data sets from MoleculeNet, including ESOL, FreeSolv, Lipop, HIV, and 6 out of 12 tasks of the QM9 data set. To further examine PointGAT prediction of quantum mechanical (QM) energies, we constructed a C10 data set comprising 11,841 charged and chiral carbocation intermediates with QM energies calculated at the DM21/6-31G*//B3LYP/6-31G* levels. Notably, PointGAT achieved an R 2 value of 0.950 and an MAE of 1.616 kcal/mol, outperforming even the best-performing graph neural network model with a reduction of 0.216 kcal/mol in MAE and an improvement of 0.050 in R 2 . Additional ablation studies indicated that incorporating molecular geometry into the model resulted in markedly higher predictive accuracy, reducing the MAE value from 1.802 to 1.616 kcal/mol. Moreover, visualization of PointGAT atomic attention weights suggested its predictions were interpretable. Findings in this study support the application of PointGAT as a powerful and versatile tool for quantum chemical property prediction that can facilitate high-accuracy modeling for fundamental exploration of chemical space as well as drug design and molecular engineering.

show abstract

“…COMPAS-1 and COMPAS-2 have already been used to provide the first examples of interpretable machine and deep-learning models for PASs 62,63 and to demonstrate the first generative design of PASs with targeted properties. 64 Both datasets, as well as all future installments, are freely available for use, according to the FAIR 65 principles of data sharing. Herein, we report on the third installment, COMPAS-3, which expands the COMPAS database to peri-condensed PBHs (pc-PBHs) in the ground state.…”

Section: Introductionmentioning

confidence: 99%