{"url":"/dataset/iso17","name":"ISO17","full_name":"ISO17 - MD Trajectories of C7O2H10 with total energies and atomic forces","description_markdown":"### Description\r\n\r\nThe molecules were randomly drawn from the largest set of isomers in the QM9 dataset [1] which consists of molecules with a fixed composition of atoms (C7O2H10) arranged in different chemically valid structures. It is an extension of the ismoer MD data used in [2].\r\n\r\nThe database was generated from molecular dynamics simulations using the Fritz-Haber Institute ab initio simulation package (FHI-aims)[3]. The simulations were carried out using the standard quantum chemistry computational method density functional theory (DFT) in the generalized gradient approximation (GGA) with the Perdew-Burke-Ernzerhof (PBE) functional[4] and the Tkatchenko-Scheffler (TS) van der Waals correction method [5].\r\n\r\nThe database consist of 129 molecules each containing 5,000 conformational geometries, energies and forces with a resolution of 1 femtosecond in the molecular dynamics trajectories.\r\n\r\n### Format\r\nThe data is stored in ASE sqlite format with the total energy in eV under the key total energy and the atomic_forces under the key atomic_forces in eV/Ang.\r\n\r\nThe following Python snippet iterates over the first 10 entries of the dataset located at path_to_db:\r\n\r\n```python\r\nfrom ase.db import connect\r\n\r\nwith connect(path_to_db) as conn:\r\n   for row in conn.select(limit=10):\r\n       print(row.toatoms())\r\n       print(row['total_energy'])\r\n       print(row.data['atomic_forces'])\r\n```\r\n\r\n### Partitions\r\nThe data is partitioned as used in the SchNet paper [6]:\r\n\r\nreference.db - 80% of steps of 80% of MD trajectories\r\nreference_eq.db - equilibrium conformations of those molecules\r\ntest_within.db - remaining 20% unseen steps of reference trajectories\r\ntest_other.db - remaining 20% unseen MD trajectories\r\ntest_eq.db - equilibrium conformations of test trajectories\r\nIn the paper, we split the reference data (reference.db) into 400k training examples and 4k validation examples. The indices are given in the files train_ids.txt and validation_idx.txt, respectively.\r\n\r\n### Benchmarks\r\nModel\tEnergy (within) [eV]\tForce (within) [eV/A]\tEnergy (other) [eV]\tForce (other) [eV/A]\r\nSchNet [6]\t0.016\t0.043\t0.104\t0.095\r\n\r\n### Download\r\n\r\nAvailable here: data/iso17.tar.gz (799.7 MB)\r\n\r\n### How to cite\r\n\r\nWhen using this dataset, please make sure to cite the following papers:\r\n\r\nK.T. Schütt, P.-J. Kindermans, H.E. Sauceda, S. Chmiela, A. Tkatchenko, K.-R. Müller. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in Neural Information Processing System. 2017.\r\nK.T. Schütt, F. Arbabzadah, S. Chmiela, K.R. Müller, A. Tkatchenko. Quantum-chemical insights from deep tensor neural networks. Nature Communications, 8, 13890. 2017.\r\nR. Ramakrishnan, P. O. Dral, M. Rupp, and O. A. von Lilienfeld. Quantum chemistry structures and properties of 134 kilo molecules. Scientific Data, 1, 2014.\r\nReferences\r\n[1] R. Ramakrishnan, P. O. Dral, M. Rupp, and O. A. von Lilienfeld. Quantum chemistry structures\r\nand properties of 134 kilo molecules. Scientific Data, 1, 2014.\r\n[2] Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R., & Tkatchenko, A. (2017). Quantum-chemical insights from deep tensor neural networks. Nature Communications, 8, 13890.\r\n[3] Blum, V.; Gehrke, R.; Hanke, F.; Havu, P.; Havu, V.; Ren, X.; Reuter, K.; Scheffler, M. Ab Initio Molecular Simulations with Numeric Atom-Centered Orbitals. Comput. Phys. Commun. 2009, 180 (11), 2175–2196.\r\n[4] Perdew, J. P.; Burke, K.; Ernzerhof, M. Generalized Gradient Approximation Made Simple. Phys. Rev. Lett. 1996, 77 (18), 3865–3868.\r\n[5] Tkatchenko, A.; Scheffler, M. Accurate Molecular Van Der Waals Interactions from Ground-State Electron Density and Free-Atom Reference Data. Phys. Rev. Lett. 2009, 102 (7), 73005.\r\n[6] Schütt, K. T., Kindermans, P. J., Sauceda, H. E., Chmiela, S., Tkatchenko, A., & Müller, K. R. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in Neural Information Processing System (accepted). 2017.","description_withheld":null,"homepage":"http://quantum-machine.org/datasets/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["ISO17"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}