Synthetic lethal gene combination prediction system based on biological network and machine learning

The invention discloses a synthetic lethal gene combination prediction system based on a biological network and machine learning. The system comprises a data acquisition and preprocessing module, a feature engineering module, a model algorithm design module and a result evaluation module. The data acquisition and preprocessing module comprises three sub-tasks of data acquisition, gene network construction and data preprocessing, and provides a data basis for a subsequent prediction task. The feature engineering module extracts features including gene pair network features and biological features; and after feature extraction, performing corresponding statistical analysis on the features. The model algorithm design module comprises training sample construction and prediction model design. And the result evaluation module is used for verifying the prediction effect of the model by drawing an ROC curve and a PR curve. The synthetic lethal gene combination is researched from the perspective of data mining, and pr