{"id":31885014,"url":"https://github.com/grimme-lab/confrankplus","last_synced_at":"2026-05-13T23:37:35.726Z","repository":{"id":297408885,"uuid":"986451316","full_name":"grimme-lab/confrankplus","owner":"grimme-lab","description":"ConfRank+: Extending Conformer Ranking to Charged Molecules","archived":false,"fork":false,"pushed_at":"2025-06-05T09:28:44.000Z","size":2584,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-05T10:30:33.059Z","etag":null,"topics":["ase","atomistic-machine-learning","atomistic-modelling","censo","charge-model","chemoinformatics","computational-chemistry","conformer-scoring","conformer-search","crest","energy-prediction","graph-neural-network","machine-learning","organic-chemistry","pairwise-training","pytorch","torchscript"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/grimme-lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-19T16:18:37.000Z","updated_at":"2025-06-05T09:28:47.000Z","dependencies_parsed_at":"2025-06-05T10:34:22.447Z","dependency_job_id":"172a9a87-3d27-4154-8df8-ce0f6eb6c641","html_url":"https://github.com/grimme-lab/confrankplus","commit_stats":null,"previous_names":["grimme-lab/confrankplus"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/grimme-lab/confrankplus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimme-lab%2Fconfrankplus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimme-lab%2Fconfrankplus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimme-lab%2Fconfrankplus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimme-lab%2Fconfrankplus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/grimme-lab","download_url":"https://codeload.github.com/grimme-lab/confrankplus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimme-lab%2Fconfrankplus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279013685,"owners_count":26085390,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-13T02:00:06.723Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ase","atomistic-machine-learning","atomistic-modelling","censo","charge-model","chemoinformatics","computational-chemistry","conformer-scoring","conformer-search","crest","energy-prediction","graph-neural-network","machine-learning","organic-chemistry","pairwise-training","pytorch","torchscript"],"created_at":"2025-10-13T04:19:46.036Z","updated_at":"2025-10-13T04:19:47.267Z","avatar_url":"https://github.com/grimme-lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e\u003cimg src=\"./assets/logo.png\" alt=\"ConfRank+\" width=\"600\"\u003e\u003c/h3\u003e\n\n\u003ch3 align=\"center\"\u003eConfRank+: Extending Conformer Ranking to Charged Molecules\u003c/h3\u003e\n\u003cp align=\"center\"\u003e A High-Throughput Machine Learning Model for Charged Molecular Conformers \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003e\u003ca href=\"https://doi.org/10.26434/chemrxiv-2025-xkwk6\"\u003ePreprint\u003c/a\u003e\u003c/strong\u003e | \n  \u003cstrong\u003e\u003ca href=\"https://zenodo.org/records/15465665\"\u003eDataset\u003c/a\u003e\u003c/strong\u003e | \n  \u003cstrong\u003e\u003ca href=\"https://doi.org/10.1021/acs.jcim.4c01524\"\u003eConfRank 1.0\u003c/a\u003e\u003c/strong\u003e\n\u003c/p\u003e\n\n# Installation\n\nYou can install the python code for running the ConfRankPlus model via pip:\n\n```bash\npip3 install git+https://github.com/grimme-lab/confrankplus.git\n```\n\nIt is **highly recommended** to install `torch_cluster` for significant faster computation of atomistic graphs, e.g., by\nrunning:\n\n```bash\npip install git+https://github.com/rusty1s/pytorch_cluster.git\n```\n\nFor further installation guidelines, see [here](https://github.com/rusty1s/pytorch_cluster/tree/master).\n\n# Inference\n\n## Label xyz files from command line\n\nYou can label (multiple) xyz files (or other formats supported by the `ase.io` module) with the `confrankplus` command\nin your command line:\n\n```bash\n confrankplus --files *.xyz --output_path confrank_output.xyz --total_charge 0  --fidelity r2SCAN-3c --batch_size 20\n``` \n\nThe results will be written to the path specified via `--output_path`. The units of the energies written to the output\npath will be in kcal/mol.\n\nFurthermore, in the directory `evaluate` there are example scripts for running inference on the test datasets of our\npaper.\n\n## ASE Calculator\n\nIn addition to the `confrankplus` command line interface, we provide an ASE calculator.\n\nExample:\n\n```python\nimport numpy as np\n\nnp.random.seed(0)\nfrom ase.collections import s22\nfrom ConfRankPlus.inference.calculator import ConfRankPlusCalculator\n\n# load the ConfRankPlus calculator with r2SCAN-3c fidelity\ncalculator = ConfRankPlusCalculator.load_default(fidelity=\"r2SCAN-3c\",\n                                                 compute_forces=False)\n\nmolecule = s22['Adenine-thymine_Watson-Crick_complex']\nmolecule.set_calculator(calculator)\n# energy before displacements:\nenergy_1 = molecule.get_potential_energy()\n# Apply random displacements:\ndisplacements = np.random.uniform(-0.01, 0.01, molecule.positions.shape)  # in Angstrom\nmolecule.set_positions(molecule.get_positions() + displacements)\n# energy after displacement:\nenergy_2 = molecule.get_potential_energy()\n\n# ASE uses eV as unit for energy:\nprint(f\"The energy difference is {energy_2 - energy_1:.2E} eV.\")\n```\n\nNote: our model has not been tested for geometry optimization or MD simulations.\n\n# Loading datasets\n\nYou can load the datasets from [Zenodo](https://zenodo.org/records/15465665) as follows:\n\n```python\nfrom ConfRankPlus.data.dataset import HDF5Dataset\n\nfilepath = ...  # path to .h5 file \ndataset = HDF5Dataset.from_hdf5(filepath=filepath, precision=64)\n```\n\n`dataset` will be an instance of the `InMemoryDataset` class from PyTorch Geometric. \n\n# Citation\n\nWhen using or referring to ConfRankPlus, please cite it as follows:\n\n```\n@misc{ConfRankPlus25, \nauthor={Oerder, Rick and H{\\\"o}lzer , Christian and Hamaekers, Jan}, \ntitle={ConfRank+: Extending Conformer Ranking to Charged Molecules},\nyear={2025},\ndoi={10.26434/chemrxiv-2025-xkwk6}, \nnote={ChemRxiv Preprint}}\n```\n\nand\n\n```\n@article{ConfRank24,\nauthor = {H{\\\"o}lzer, Christian and Oerder, Rick and Grimme, Stefan and Hamaekers, Jan},\ntitle = {ConfRank: Improving GFN-FF Conformer Ranking with Pairwise Training},\njournal = {Journal of Chemical Information and Modeling},\nvolume = {64},\nnumber = {23},\npages = {8909-8925},\nyear = {2024},\ndoi = {10.1021/acs.jcim.4c01524},\nnote ={PMID: 39565928},\nURL = {https://doi.org/10.1021/acs.jcim.4c01524},\neprint = {https://doi.org/10.1021/acs.jcim.4c01524}}\n```\n\n\n# License\n \u003cp xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dct=\"http://purl.org/dc/terms/\"\u003e\u003cspan property=\"dct:title\"\u003eThe content of this repository is licensed under \u003ca href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/?ref=chooser-v1\" target=\"_blank\" rel=\"license noopener noreferrer\" style=\"display:inline-block;\"\u003eCC BY-NC-SA 4.0\u003cimg style=\"height:22px!important;margin-left:3px;vertical-align:text-bottom;\" src=\"https://mirrors.creativecommons.org/presskit/icons/cc.svg?ref=chooser-v1\"\u003e\u003cimg style=\"height:22px!important;margin-left:3px;vertical-align:text-bottom;\" src=\"https://mirrors.creativecommons.org/presskit/icons/by.svg?ref=chooser-v1\"\u003e\u003cimg style=\"height:22px!important;margin-left:3px;vertical-align:text-bottom;\" src=\"https://mirrors.creativecommons.org/presskit/icons/nc.svg?ref=chooser-v1\"\u003e\u003cimg style=\"height:22px!important;margin-left:3px;vertical-align:text-bottom;\" src=\"https://mirrors.creativecommons.org/presskit/icons/sa.svg?ref=chooser-v1\"\u003e\u003c/a\u003e\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrimme-lab%2Fconfrankplus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgrimme-lab%2Fconfrankplus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrimme-lab%2Fconfrankplus/lists"}