From: Statistical representation models for mutation information within genomic data

Algorithm | Parameter | Value | Data Rep. |
---|---|---|---|

KNN | k | 50 | Binary |

10 | c-score, tf-idf, tf-rf, | ||

bm25-tf-idf, bm25-tf-rf | |||

SVM-poly | Polynomial degree | 3 | binary, tf-idf, bm25-tf-idf |

2 | c-score, tf-rf, bm25-tf-rf | ||

SVM-rbf | Gamma |
10^{−4}
| All |

Cost |
10^{3}
| All | |

SVM-linear | Gamma |
10^{−4}
| All |

Cost |
10^{2}
| All | |

Perceptron | Optimization function | SGD | binary |

Adam | c-score, tf-idf, tf-rf, | ||

bm25-tf-idf, bm25-tf-rf | |||

Activation function | tanh | binary | |

ReLU | c-score, tf-idf, tf-rf, | ||

bm25-tf-idf, bm25-tf-rf | |||

Hidden layer size | 100 | All | |

The maximum number of iterations | 200 | binary | |

300 | c-score, tf-idf, tf-rf, | ||

bm25-tf-idf, bm25-tf-rf | |||

Feed Forward NN | Optimization function | Adam | All |

Activation function | ReLU | All | |

The number of layers | 4 | All | |

Dropout rate | 0.25 | All | |

The number of nodes in the first layer | 8192 | All |