4.7 Article

QDp: A Quantum Deep Potential Interaction Model for Drug Discovery

Journal

Publisher

AMER CHEMICAL SOC
DOI: 10.1021/acs.jctc.2c01172

Keywords

-

Ask authors/readers for more resources

We introduce the QD7 pi-v1.0 model for accurately modeling the internal energy of drug molecules. This model combines a quantum mechanical/machine learning potential correction with a high-level deep-learning potential. It outperforms other semiempirical and machine learning potentials in handling electrostatic interactions and charge/protonation state changes. The QD pi model is highly accurate in various molecular interactions and shows excellent performance in relative protonation/deprotonation energies and tautomers.
We report QD7 pi-v1.0 for modeling the internal energy of drug molecules containing H, C, N, and O atoms. The QD7 pi model is in the form of a quantum mechanical/machine learning potential correction (QM/delta-MLP) that uses a fast third order self-consistent density-functional tight-binding (DFTB3/ 3OB) model that is corrected to a quantitatively high-level of accuracy through a deep-learning potential (DeepPot-SE). The model has the advantage that it is able to properly treat electrostatic interactions and handle changes in charge/protonation states. The model is trained against reference data computed at the omega B97X/6-31G* level (as in the ANI-1x data set) and compared to several other approximate semiempirical and machine learning potentials (ANI-1x, ANI-2x, DFTB3, MNDO/d, AM1, PM6, GFN1-xTB, and GFN2-xTB). The QD pi model is demonstrated to be accurate for a wide range of intra-and intermolecular interactions (despite its intended use as an internal energy model) and has shown to perform exceptionally well for relative protonation/deprotonation energies and tautomers. An example application to model reactions involved in RNA strand cleavage catalyzed by protein and nucleic acid enzymes illustrates QD pi has average errors less than 0.5 kcal/mol, whereas the other models compared have errors over an order of magnitude greater. Taken together, this makes QD pi highly attractive as a potential force field model for drug discovery.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available