{
  "id": "1612.02751",
  "version": "v1",
  "published": "2016-12-08T18:18:29.000Z",
  "updated": "2016-12-08T18:18:29.000Z",
  "title": "Protein-Ligand Scoring with Convolutional Neural Networks",
  "authors": [
    "Matthew Ragoza",
    "Joshua Hochuli",
    "Elisa Idrobo",
    "Jocelyn Sunseri",
    "David Ryan Koes"
  ],
  "categories": [
    "stat.ML",
    "cs.LG",
    "q-bio.BM"
  ],
  "abstract": "Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding and structural data enables the use of deep machine learning techniques for protein-ligand scoring. We describe convolutional neural network (CNN) scoring functions that take as input a comprehensive 3D representation of a protein-ligand interaction. A CNN scoring function automatically learns the key features of protein-ligand interactions that correlate with binding. We train and optimize our CNN scoring functions to discriminate between correct and incorrect binding poses and known binders and non-binders. We find that our CNN scoring function outperforms the AutoDock Vina scoring function when ranking poses both for pose prediction and virtual screening.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-12-08T18:18:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional neural network",
      "protein-ligand scoring",
      "protein-ligand interaction",
      "cnn scoring function automatically learns",
      "structure-based drug design methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}