A Deep Generative Model for the Inverse Design of Transition Metal Ligands and Complexes

JACS Au, Год журнала: 2025, Номер 5(5), С. 2294 - 2308

Опубликована: Апрель 23, 2025

Deep generative models yielding transition metal complexes (TMCs) remain scarce despite the key role of these compounds in industrial catalytic processes, anticancer therapies, and energy transition. Compared to drug discovery within chemical space organic molecules, TMCs pose further challenges, including encoding bonds higher complexity need optimize multiple properties. In this work, we developed a model for inverse design ligands complexes, based on junction tree variational autoencoder (JT-VAE). After implementing SMILES-based metal-ligand bonds, was trained with tmQMg-L ligand library, allowing generation thousands novel, highly diverse monodentate (κ1) bidentate (κ2) ligands, imines, phosphines, carbenes. Further, generated were labeled two target properties reflecting stability electron density associated homoleptic iridium TMCs: HOMO-LUMO gap (ϵ) charge center (q Ir). This data used implement conditional that from prompt, single- or dual-objective optimizing either both ϵ q Ir interpretation optimization trajectories. The optimizations also had an impact other properties, dissociation energies oxidative addition barriers. A similar implemented condition by solubility steric bulk.

Язык: Английский

---

Integrating Machine Learning and Quantum Circuits for Proton Affinity Predictions

Journal of Chemical Theory and Computation, Год журнала: 2025, Номер unknown

Опубликована: Фев. 17, 2025

A key step in interpreting gas-phase ion mobility coupled with mass spectrometry (IM-MS) data for unknown structure prediction involves identifying the most favorable protonated structure. In gas phase, site of protonation is determined using proton affinity (PA) measurements. Currently, and ab initio computation methods are widely used to evaluate PA; however, both resource-intensive time-consuming. Therefore, there a critical need efficient estimate PA, enabling rapid identification complex organic molecules multiple binding sites. this work, we developed fast accurate method PA by descriptors combination machine learning (ML) models. Using comprehensive set 186 descriptors, our model demonstrated strong predictive performance, an R2 0.96 MAE 2.47 kcal/mol, comparable experimental uncertainty. Furthermore, designed quantum circuits as feature encoders classical neural network. To effectiveness hybrid quantum-classical model, compared its performance traditional ML models reduced derived from full set. correlation analysis showed that quantum-encoded representations have stronger positive target values than original features do. As result, outperformed counterpart achieved consistent same on noiseless simulator real hardware, highlighting potential predictions.

Язык: Английский

---

Toward AI/ML-assisted discovery of transition metal complexes

Annual reports in computational chemistry, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Язык: Английский

---