Leffingwell Odor Dataset
Bibliographic record
Abstract
<p><strong>NOTE: It's easier to download this dataset from <a href="https://github.com/pyrfume/pyrfume">pyrfume</a>. Here's how:</strong></p>\n\n<pre><code># First install pyrfume in your Python environment. This can be done easily with pip.\n# pip install pyrfume\n\nimport pyrfume\nmolecules = pyrfume.load_data('leffingwell/molecules.csv', remote=True)\nbehavior = pyrfume.load_data('leffingwell/behavior.csv', remote=True)\n# e.g. to count the number of molecules with each descriptor\nbehavior.sum().sort_values(ascending=False).astype(int) \n\n</code></pre>\n\n<p>Predicting properties of molecules is an area of growing research in machine learning, particularly as models for learning from graph-valued inputs improve in sophistication and robustness. A molecular property prediction problem that has received comparatively little attention during this surge in research activity is building Structure-Odor Relationships (SOR) models (as opposed to Quantitative Structure-Activity Relationships, a term from medicinal chemistry). This is a 70+ year-old problem straddling chemistry, physics, neuroscience, and machine learning.</p>\n\n<p>To spur development on the SOR problem, we curated and cleaned a dataset of 3523 molecules associated with expert-labeled odor descriptors from the <em>Leffingwell PMP 2001</em> database.  We provide featurizations of all molecules in the dataset using bit-based and count-based fingerprints, Mordred molecular descriptors, and the embeddings from our trained GNN model (Sanchez-Lengeling et al., 2019). This dataset is comprised of two files: </p>\n\n<ol>\n\t<li><strong>leffingwell_data.csv</strong>: this contains molecular structures, and what they smell like, along with train, test, and cross-validation splits. More detail on the file structure is found in leffingwell_readme.pdf.</li>\n\t<li><strong>leffingwell_embeddings.npz</strong>: this contains several featurizations of the molecules in the dataset.</li>\n\t<li><strong>leffingwell_readme.pdf</strong>: a more detailed description of the data and its provenance, including expected performance metrics.</li>\n\t<li><strong>LICENSE</strong>: a copy of the CC-BY-NC license language.</li>\n</ol>\n\n<p>The dataset, and all associated features, is freely available for research use under the <a href="https://creativecommons.org/licenses/by-nc/4.0/">CC-BY-NC</a> license.</p>\n\n<p>If you use the data in a publication, please cite:</p>\n\n<pre>@article{sanchez2019machine,\n title={Machine learning for scent: Learning generalizable perceptual representations of small molecules},\n author={Sanchez-Lengeling, Benjamin and Wei, Jennifer N and Lee, Brian K and Gerkin, Richard C and Aspuru-Guzik, Al{\\'a}n and Wiltschko, Alexander B},\n journal={arXiv preprint arXiv:1910.10685},\n year={2019}\n}</pre>
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.048 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".