This is a network of polypharmacy side-effects. Nodes represent drugs and edges represent different types of side effects that are associated with drug pairs. Edges indicate which side effects a patient will likely experience if he takes two drugs together (i.e., a drug combination). Such side effects are known as polypharmacy side-effects, as they are associated with drug pairs (or higher-order drug combinations) and cannot be attributed to either individual drug in the pair (in a drug combination).

Dataset statistics | |
---|---|

Nodes | 645 |

Edges | 63473 |

Nodes in largest SCC | 645 |

Fraction of nodes in largest SCC | 1.000000 |

Edges in largest SCC | 63473 |

Fraction of edges in largest SCC | 1.000000 |

Average clustering coefficient | 0.811445 |

Number of triangles | 11489282 |

Fraction of closed triangles | 0.354259 |

Diameter (longest shortest path) | 3 |

90-percentile effective diameter | 1.864073 |

Average side effects per edge | 73.250689 |

Median side effects per edge | 53 |

Standard deviation of side effects per edge | 66.053302 |

Polypharmacy side-effect information was generated based on national adverse event reporting systems.

- Modeling polypharmacy side effects with graph convolutional networks. Marinka Zitnik, Monica Agrawal, and Jure Leskovec.
*Bioinformatics.*2018.

Presented at ISMB 2018

- Data-driven prediction of drug effects and interactions. Tatonetti, Nicholas P., et al.
*Science Translational Medicine.*2012.

File | Size | Description |
---|---|---|

ChChSe-Decagon_polypharmacy.csv.gz | 232.8MB | Side effects of drug pairs |