mlsanityData to 7 Oct 2026

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

arXiv 2209.10702 ↗First posted 21 Sep 2022physics.chem-ph cs.LG q-bio.BMcited by 80

Not on the map. Why?

Abstract (arXiv)

Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 6 of its 53 references that are in the map. First posted on arXiv 21 Sep 2022.

Builds on

6 of 53 references.

References · 6

  1. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  4. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 179
  5. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
  6. 2021Differentiable sampling of molecular geometries with uncertainty-based adversarial attackscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 20; 2025: 28; 2026: 19.

80 papers.

Sort:

By area:

  1. 2025UMA: A Family of Universal Models for Atomscited by 99
  2. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 92
  3. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 79
  4. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
  5. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 53
  6. 2024Open Materials 2024 (OMat24) Inorganic Materials Dataset and Modelscited by 50
  7. 2023OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentialscited by 44
  8. 2024The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domainscited by 40
  9. 2023From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Predictioncited by 39
  10. 2023Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasetscited by 37
  11. 2023Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic sizecited by 33
  12. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
38 more
  1. 2024The dark side of the forces: assessing non-conservative force models for atomistic machine learningcited by 23
  2. 2025PET-MAD, a lightweight universal interatomic potential for advanced materials modelingcited by 23
  3. 2025Adjoint Schr"odinger Bridge Samplercited by 20
  4. 2025High-performance training and inference for deep equivariant interatomic potentialscited by 17
  5. 2024TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulationscited by 15
  6. 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessianscited by 15
  7. 2023MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modelingcited by 14
  8. 2024Euclidean Fast Attention -- Machine Learning Global Atomic Representations at Linear Costcited by 12
  9. 2025E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Productscited by 12
  10. 2023Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentialscited by 11
  11. 2026Pushing the limits of unconstrained machine-learned interatomic potentialscited by 11
  12. 2025How simple can you go? An off-the-shelf transformer approach to molecular dynamicscited by 10
  13. 2025A universal augmentation framework for long-range electrostatics in machine learning interatomic potentialscited by 9
  14. 2024Nutmeg and SPICE: Models and Data for Biomolecular Machine Learningcited by 7
  15. 2024Learning charges and long-range interactions from energies and forcescited by 7
  16. 2026MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistrycited by 7
  17. 2026A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attentioncited by 7
  18. 2024Zero Shot Molecular Generation via Similarity Kernelscited by 6
  19. 2024FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentialscited by 6
  20. 2025chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulationscited by 6
  21. 2025Transformers Discover Molecular Structure Without Graph Priorscited by 6
  22. 2023CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learningcited by 5
  23. 2025Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibrationcited by 5
  24. 2026Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamicscited by 5
  25. 2023EspalomaCharge: Machine learning-enabled ultra-fast partial charge assignmentcited by 4
  26. 2023Gradual Optimization Learning for Conformational Energy Minimizationcited by 4
  27. 2024Broadening the Scope of Neural Network Potentials through Direct Inclusion of Additional Molecular Attributescited by 3
  28. 2024Grappa -- A Machine Learned Molecular Mechanics Force Fieldcited by 3
  29. 2024On the design space between molecular mechanics and machine learning force fieldscited by 3
  30. 2024Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learningcited by 3
  31. 2026Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fieldscited by 3
  32. 2026Transferable SCF-Acceleration through Solver-Aligned Initialization Learningcited by 3
  33. 2024nabla2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentialscited by 2
  34. 2025Machine-Learning Interatomic Potentials for Long-Range Systemscited by 2
  35. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2
  36. 2026Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPscited by 2
  37. 2024FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproductioncited by 1
  38. 2024ZnTrack -- Data as Codecited by 1

50 most cited of 80 All 80 (JSON)