Thermodynamics-Informed Accurate pKa Prediction and Protonation State Generation in PlayMolecule AI
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912995500621824 |
|---|---|
| author | Pesce, Francesco Farr, Stephen de Fabritiis, Gianni |
| author_facet | Pesce, Francesco Farr, Stephen de Fabritiis, Gianni |
| contents | Accurate prediction of acid dissociation constants (p$K_{\rm a}$) and the determination of dominant protonation states is critical in drug discovery, influencing molecular properties such as solubility, permeability, and protein-ligand binding. We present Acep$K_{\rm a}$, an advanced application integrated into the PlayMolecule AI platform. Acep$K_{\rm a}$ is built upon the theoretically rigorous Uni-p$K_{\rm a}$ framework, which unifies statistical mechanics with representation learning. By modeling the complete protonation ensemble rather than treating p$K_a$ as a scalar regression target, Acep$K_{\rm a}$ ensures thermodynamic consistency across coupled ionization sites. We describe the application's enhanced architecture, which features a retrained Uni-Mol backbone achieving state-of-the-art performance on standard benchmarks. Furthermore, we detail critical engineering advancements. These include AceConfgen, a proprietary GPU-accelerated conformer generator that achieves a ~40x speed-up compared to NVIDIA's nvmolkit, a streamlined inference engine to directly protonate molecules, and a 3D-aware modality for applying protonation states to bound ligand poses. Finally, we discuss the integration of Acep$K_{\rm a}$ into the PlayMolecule AI ecosystem, a modern AI-assisted environment for molecular modelling and drug discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00841 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Thermodynamics-Informed Accurate pKa Prediction and Protonation State Generation in PlayMolecule AI Pesce, Francesco Farr, Stephen de Fabritiis, Gianni Chemical Physics Accurate prediction of acid dissociation constants (p$K_{\rm a}$) and the determination of dominant protonation states is critical in drug discovery, influencing molecular properties such as solubility, permeability, and protein-ligand binding. We present Acep$K_{\rm a}$, an advanced application integrated into the PlayMolecule AI platform. Acep$K_{\rm a}$ is built upon the theoretically rigorous Uni-p$K_{\rm a}$ framework, which unifies statistical mechanics with representation learning. By modeling the complete protonation ensemble rather than treating p$K_a$ as a scalar regression target, Acep$K_{\rm a}$ ensures thermodynamic consistency across coupled ionization sites. We describe the application's enhanced architecture, which features a retrained Uni-Mol backbone achieving state-of-the-art performance on standard benchmarks. Furthermore, we detail critical engineering advancements. These include AceConfgen, a proprietary GPU-accelerated conformer generator that achieves a ~40x speed-up compared to NVIDIA's nvmolkit, a streamlined inference engine to directly protonate molecules, and a 3D-aware modality for applying protonation states to bound ligand poses. Finally, we discuss the integration of Acep$K_{\rm a}$ into the PlayMolecule AI ecosystem, a modern AI-assisted environment for molecular modelling and drug discovery. |
| title | Thermodynamics-Informed Accurate pKa Prediction and Protonation State Generation in PlayMolecule AI |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2604.00841 |