{
  "fetched_at": "2026-10-19T19:09:41Z",
  "source_url": "https://www.kaggle.com/competitions/bio322a/data",
  "pages": [
    {
      "name": "data-description",
      "content": "\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>training_data.csv</strong> - the training set</li>\n<li><strong>test_data.csv</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>Id</strong> - molecule identity</li>\n<li><strong>Intensity</strong> - intensity of the odor</li>\n<li><strong>VALENCE.PLEASANTNESS</strong> - how pleasant the odor is</li>\n<li><strong>SWEETORSOUR</strong> - whether the odor is perceived as more sweet than sour</li>\n<li><strong>other columns</strong> - physicochemical features of each of the molecules smelled by the subjects (including atom types, functional groups, and topological and geometrical properties that were computed using Dragon chemoinformatic software)</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<blockquote>In vision and hearing, the wavelength of light and frequency of sound are highly predictive of color and tone. In contrast, it is not currently possible to predict the smell of a molecule from its chemical structure. This stimulus-percept problem has been difficult to solve in olfaction because odors do not vary continuously in stimulus space, and the size and dimensionality of olfactory perceptual space is unknown. Some molecules with very similar chemical structures can be discriminated by humans, and molecules with very different structures sometimes produce nearly identical percepts. Computational efforts developed models to relate chemical structure to odor percept, but many relied on psychophysical data from a single 30-year-old study that used odorants with limited structural and perceptual diversity. (<a href=\"https://science.sciencemag.org/content/355/6327/820.full\">Predicting human olfactory perception from chemical features of odor molecules</a>)\n</blockquote>\n\n<p>In this challenge, you are given access to a database of responses from a subject who had sniffed a large number of molecules and been asked to rate the pleasantness of the smell. You are also given a comprehensive list of the physical and chemical features of the molecules smelled. Your task is to produce algorithms to predict the correspondence between the pleasantness of each smell and a given molecule.</p>\n\n<p>The data set and the task is derived from the publication <a href=\"https://science.sciencemag.org/content/355/6327/820.full\">Predicting human olfactory perception from chemical features of odor molecules</a>.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions are evaluated with the root of the mean squared error (RMSE) over the test data:</p>\n<p>\\[\\mathrm{RMSE} = \\sqrt{\\frac1n\\sum_{i=1}^n (y_i - \\hat y_i)^2}\\]</p>\n<p> where \\\\( y_i \\\\) is the \"VALENCE.PLEASANTNESS\" reported by the subject and \\\\( \\hat y_i \\\\) is your prediction.</p>\n\n<h2>Submission Format</h2>\n<p>Submission files should contain two columns: \"Id\" and \"VALENCE.PLEASANTNESS\" that contain your predictions of the pleasantness of the molecule with the corresponding Id in the <a href=\"https://www.kaggle.com/c/epfl-bio-322a/data\">test_data.csv</a> file.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>\"Id\",\"VALENCE.PLEASANTNESS\"<br>1,0<br>2,11<br>3,91<br>...<br></pre>\n<p>You may want to use the R function `write.csv` to generate this file.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "See instructions on [moodle](https://moodle.epfl.ch/mod/resource/view.php?id=1117079).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}