Please use this identifier to cite or link to this item:
|Title:||Stacked Sparse Autoencoder For Unsupervised Features Learning in PanCancer miRNA Cancer Classification||Authors:||Zenbout, Imene
|Affiliations:||Faculty of Information and Communication Technology (ICT)
Faculty of Information and Communication Technology (ICT)
|Keywords:||Deep learning;Bioinformatics;features learning;Sparse autoencoders;miRNA;PanCancer||Date:||26-May-2020||Publisher:||CEUR Workshop Proceedings||Volume:||2589||Conference:||1st International Conference on Innovative Trends in Computer Science||Abstract:||
The recent progress in cancer diagnosis is genomic data analysis oriented. miRNA is playing an important role as cancer biomarkers to move with cancer diagnosis and therapy towards personalized medicine with the ultimate goal to augment survival rate and disease prevention. The recent explosion in genomic data generation has motivated the use of miRNA to enhance diagnosis, prognosis and treatment. In this work we have explored the integrated Atlas PanCancer miRNA profiles, using deep features learning based on unsupervised Stacked Sparse AutoEncoder (SSAE). The proposed SSAE model learns features representation from the used data. The consistency of the learned features has been tested using classification of samples according to 31 cancer types. The model performance has been compared to state-of-the-art unsupervised features learning models. The obtained results exhibit the competitiveness and promising performance of our model, where an accuracy rate of about 95% has been achieved. Index Terms—Deep learning, Bioi
This work is licensed under a Creative Commons Attribution 4.0 International License.
|Appears in Collections:||Conference Paper|
checked on Jan 29, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.