A novel deep mining model for effective knowledge discovery from omics data
作者：
Highlights：
• A novel deep mining model is proposed for knowledge discovery from omics data.
• The proposed model is based on a Stacked Sparse Compressed Auto-Encoder.
• A new weight interpretation method is introduced to deconstruct deep learning models.
• Key determinants underlying the latent representations were discovered robustly.
• The cancer markers demonstrate computational and biological relevance.
摘要
•A novel deep mining model is proposed for knowledge discovery from omics data.•The proposed model is based on a Stacked Sparse Compressed Auto-Encoder.•A new weight interpretation method is introduced to deconstruct deep learning models.•Key determinants underlying the latent representations were discovered robustly.•The cancer markers demonstrate computational and biological relevance.
论文关键词：Knowledge discovery,Data mining,AI,Deep learning,Omics data analysis,Predictive modelling,Precision medicine
论文评审过程：Received 28 September 2019, Revised 23 January 2020, Accepted 17 February 2020, Available online 24 February 2020, Version of Record 29 February 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101821
