SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Eastman, Peter; Behara, Pavan Kumar; Dotson, David; Galvelis, Raimondas; Herr, John E.; Horton, Joshua; Mao, Yuezhi; Chodera, John D.; Pritchard, Benjamin P.; Wang, Yuanqing; Fabritiis, Gianni De; Markland, Thomas E.

doi:10.1038/s41597-022-01882-6

Cited by 67 publications

(86 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This chemical space is incomplete, as many drug molecules contain phosphorus, sulfur, and halogen atoms, and some contain metal ions. − The ANI-2x model was extended to include S, F, and Cl, but the full data set, including the important reference energies and forces at the ωB97X/6-31G* level, to our knowledge, has not yet become publicly available. Currently, there are a number of recent data sets that include compounds that contain phosphorus, sulfur, and halogens at various levels of theory − as well as metal ions . Among them, only the SPICE data set includes forces at the ωB97M-D3BJ/def2-TZVPPD level and currently includes over 420K phosphorus, 520K sulfur, 750K halogen, and 8K metal-containing structures.…”

Section: Resultsmentioning

confidence: 99%

“…Currently, there are a number of recent data sets that include compounds that contain phosphorus, sulfur, and halogens at various levels of theory − as well as metal ions . Among them, only the SPICE data set includes forces at the ωB97M-D3BJ/def2-TZVPPD level and currently includes over 420K phosphorus, 520K sulfur, 750K halogen, and 8K metal-containing structures.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

QDπ: A Quantum Deep Potential Interaction Model for Drug Discovery

Zeng

Tao

Giese

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

We report QDπ-v1.0 for modeling the internal energy of drug molecules containing H, C, N, and O atoms. The QDπ model is in the form of a quantum mechanical/machine learning potential correction (QM/Δ-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 ωB97X/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 QDπ 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 QDπ 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 QDπ highly attractive as a potential force field model for drug discovery.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

QDπ: A Quantum Deep Potential Interaction Model for Drug Discovery

Zeng

Tao

Giese

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…To curate a dataset representing the chemical space of interest for biophysical modeling of biomolecules and drug-like small molecules, we use the SPICE [12] dataset, enumerating reasonable protonation and tautomeric states with the OpenEye Toolkit. We generated AM1-BCC ELF10 charges for each of these molecules using the OpenEye Toolkit, and trained EspalomaCharge (Figure 1) to reproduce the partial atomic charges with a squared loss function.…”

Section: The Spice Dataset Covers Biochemically and Biophysically Int...mentioning

confidence: 99%

“…In this paper, we use the continuous embedding atom representation scheme from Espaloma in conjunction with analytical constrained charge assignment inspired by charge equilibration to come up with an ultra-fast machine learning surrogate for partial charge assignment (EspalomaCharge). We train Espalo-maCharge on an expanded set of protonation states and tautomers of representative biomolecules and druglike molecules (the SPICE dataset [12]) to assign high-quality AM1-BCC ELF10 charges [26]. The resulting EspalomaCharge model accurately reproduces AM1-BCC ELF10 charges to an error well within the discrepancy between AmberTools sqm and OpenEye oequacpac implementations on average 2,000 times faster than AmberTools on the SPICE dataset, can utilize either CPU or GPU, and scales as ( ) with number of atoms, allowing even entire proteins to be assigned AM1-BCC equivalent charges.…”

mentioning

confidence: 99%

EspalomaCharge: Machine learning-enabled ultra-fast partial charge assignment

Wang¹,

Pulido²,

Takaba³

et al. 2023

Preprint

View full text Add to dashboard Cite

Atomic partial charges are crucial parameters in molecular dynamics (MD) simulation, dictating the electrostatic contributions to intermolecular energies, and thereby the potential energy landscape. Traditionally, the assignment of partial charges has relied on surrogates of ab initio semiempirical quantum chemical methods such as AM1-BCC, and is expensive for large systems or large numbers of molecules. We propose a hybrid physical / graph neural network-based approximation to the widely popular AM1-BCC charge model that is orders of magnitude faster while maintaining accuracy comparable to differences in AM1-BCC implementations. Our hybrid approach couples a graph neural network to a streamlined charge equilibration approach in order to predict molecule-specific atomic electronegativity and hardness parameters, followed by analytical determination of optimal charge-equilibrated parameters that preserves total molecular charge. This hybrid approach scales linearly with the number of atoms, enabling, for the first time, the use of fully consistent charge models for small molecules and biopolymers for the construction of nextgeneration self-consistent biomolecular force fields. Implemented in the free and open source package espaloma_charge, this approach provides drop-in replacements for both AmberTools antechamber and the Open Force Field Toolkit charging workflows, in addition to stand-alone charge generation interfaces. Source code is available at https://github.com/choderalab/espaloma_charge. Molecular mechanics (MM) force fields abstract atoms as point charge-carrying particles, with their electrostatic energy ( ) calculated by some Coulomb's law [10](or some modified form), where is Coulomb constant (energy * distance 2 / charge 2 ) and the interatomic distance. In fixed-charge molecular mechanics force fields, the partial charges are treated as constant, static parameters, agnostic of instantaneous geometry. As such, partial charge assignment-the manner in which partial charges are assigned to each atom in a given system based on their chemical environmentsplays a crucial role in molecular dynamics (MD) simulation, determining the electrostatic energy ( ) at every step and shaping the energy landscape.

show abstract

“…In order to produce quantitative results and stable dynamics in this context, next iterations of the FENNIX model will need to explicitly handle charged systems, which will require a more thorough dataset. The recently introduced SPICE dataset [81] could be a good complement to the ones already used in this work as it provides reference data for many charged molecules and focuses on biological systems (however at the lower qual- ity DFT level). Furthermore, it will require finer description of molecular interactions through the inclusion of more advanced energy terms (such as multipolar electrostatics and polarization).…”

Section: Perspective: Gas-phase Simulation Of a Proteinmentioning

confidence: 99%

Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects

Plé¹,

Lagardère²,

Piquemal³

2023

Preprint

View full text Add to dashboard Cite

We introduce FENNIX (Force-Field-Enhanced Neural Network InteraXions), a hybrid approach between machine-learning and force-fields. We leverage state-of-the-art equivariant neural networks to predict local energy contributions and multiple atom-in-molecule properties that are then used as geometry-dependent parameters for physically-motivated energy terms which account for long-range electrostatics and dispersion. Using high-accuracy ab initio data (small organic molecules/dimers), we trained a first version of the model. Exhibiting accurate gas-phase energy predictions, FENNIX is transferable to the condensed phase. It is able to produce stable Molecular Dynamics simulations, including nuclear quantum effects, for water predicting accurate liquid properties. The extrapolating power of the hybrid physically-driven machine learning FENNIX approach is exemplified by computing: i) the solvated alanine dipeptide free energy landscape; ii) the reactive dissociation of small molecules.

show abstract

SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Cited by 67 publications

References 47 publications

QDπ: A Quantum Deep Potential Interaction Model for Drug Discovery

QDπ: A Quantum Deep Potential Interaction Model for Drug Discovery

EspalomaCharge: Machine learning-enabled ultra-fast partial charge assignment

Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects

Contact Info

Product

Resources

About