{"url":"/dataset/multi-labelled-smiles-odors-dataset","name":"Multi-Labelled SMILES Odors dataset","full_name":null,"description_markdown":"This dataset is a multi-labelled SMILES odor dataset with 138 odor descriptors. This dataset was created for replicating the paper: [A principal odor map unifies diverse tasks in olfactory perception](https://www.science.org/doi/full/10.1126/science.ade4401).\r\n\r\nThe complete replication of the paper (dataset curation + model) can be found in the [OpenPOM](https://github.com/BioMachineLearning/openpom) GitHub repository.\r\n\r\nThe dataset contains 4983 molecules, each described by multiple odor labels (e.g. creamy, grassy), was made by combining the [GoodScents](http://www.thegoodscentscompany.com/) and [Leffingwell PMP 2001 datasets](https://zenodo.org/record/4085098#.YqoYk8jMIUE) each containing odorant molecules and corresponding odor descriptors.","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/aryanamitbarsainyan/multi-labelled-smiles-odors-dataset","introduced_date":"2023-09-11","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0: Public Domain","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Molecular Property Prediction","url":"/task/molecular-property-prediction","datasets_with_task":"/datasets/task/molecular-property-prediction"},{"name":"Odor Descriptor Prediction","url":"/task/odor-descriptor-prediction","datasets_with_task":"/datasets/task/odor-descriptor-prediction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Multi-Labelled SMILES Odors dataset"],"data_loaders":[{"repo":"https://github.com/deepchem/deepchem","url":"https://www.kaggle.com/datasets/aryanamitbarsainyan/multi-labelled-smiles-odors-dataset","frameworks":["tf","pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/odor-descriptor-prediction-on-multi-labelled","task":"Odor Descriptor Prediction","dataset_variant":"Multi-Labelled SMILES Odors dataset","rows":1,"metrics":["Avg. ROC-AUC"],"first_row_in_archive_order":{"model":"MPNNPOMModel (OpenPOM)","paper":"/paper/a-principal-odor-map-unifies-diverse-tasks-in","metrics":{"Avg. ROC-AUC":"0.8872"},"code_links":[{"title":"BioMachineLearning/openpom","url":"https://github.com/BioMachineLearning/openpom"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-principal-odor-map-unifies-diverse-tasks-in","title":"A principal odor map unifies diverse tasks in olfactory perception","date":"2023-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}