Autoencoder trained on transcriptomic signals
收藏资源简介：
(A) Microarray normalised gene expression data used in reverse training to define the disease modules: MicroarrayDataForDiseaseGene.zip<br><br>(B) 3 layer deep autoencoder trained on the 20K microarray data samples: MicroarrayDeep512_512_512_AE20K.h5<br>(C) 1 layer shallow autoencoder trained on the 20K microarray data samples: MicroarrayShallow512AE20K.h5<br>(D) 3 layer sparsified deep autoencoder trained on the 20K micro-array data samples: MicroarrayDeep512_512_512_AE_Regularised20K.h5<br>(E) 3 layer denoised deep autoencoder trained on 20K micro-array data samples: MicroarrayDeep512_512_512_AE_Denoised20K.h5<br>(F) 5 layer funnel shaped deep autoencoder trained on 20K microarray data samples: MicroarrayDeep512_256_128_256_512_AE20K.h5<br>(G) 3 layer funnel shaped deep autoencoder trained on 20K microarray data samples: MicroarrayDeep512_128_512_AE20K.h5<br>(H) RNA seq normalised gene expression data used in reverse training to define the disease modules: RNAseqDataForDiseaseGene.zip<br><br>(I) 3 layer deep autoencoder trained on the 50K samples: RNAseqDeep512_512_512_AE50K.h5<br><br>(J) 3 layer deep autoencoder trained on the 20K samples as a first realisation: RNAseqDeep512_512_512_AE20K1.h5<br><br>(K) 3 layer deep autoencoder trained on the 20K samples as a second realisation: RNAseqDeep512_512_512_AE20K2.h5<br><br>(L) 3 layer deep autoencoder trained on the 20K samples as a third realisation: RNAseqDeep512_512_512_AE20K3.h5
