{
  "id": "1509.09292",
  "version": "v1",
  "published": "2015-09-30T18:33:50.000Z",
  "updated": "2015-09-30T18:33:50.000Z",
  "title": "Convolutional Networks on Graphs for Learning Molecular Fingerprints",
  "authors": [
    "David Duvenaud",
    "Dougal Maclaurin",
    "Jorge Aguilera-Iparraguirre",
    "Rafael Gómez-Bombarelli",
    "Timothy Hirzel",
    "Alán Aspuru-Guzik",
    "Ryan P. Adams"
  ],
  "comment": "9 pages, 5 figures. To appear in Neural Information Processing Systems (NIPS)",
  "categories": [
    "cs.LG",
    "cs.NE",
    "stat.ML"
  ],
  "abstract": "Predicting properties of molecules requires functions that take graphs as inputs. Molecular graphs are usually preprocessed using hash-based functions to produce fixed-size fingerprint vectors, which are used as features for making predictions. We introduce a convolutional neural network that operates directly on graphs, allowing end-to-end learning of the feature pipeline. This architecture generalizes standard molecular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-09-30T18:33:50.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "learning molecular fingerprints",
      "convolutional networks",
      "architecture generalizes standard molecular fingerprints",
      "convolutional neural network",
      "produce fixed-size fingerprint vectors"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv150909292D"
    }
  }
}