TY  - JOUR
AU  - Fiosina, Jelena
AU  - Fiosins, Maksims
AU  - Bonn, Stefan
TI  - Explainable Deep Learning for Augmentation of Small RNA Expression Profiles.342
JO  - Journal of computational biology
VL  - 27
IS  - 2
SN  - 1557-8666
CY  - Larchmont, NY
PB  - Liebert
M1  - DZNE-2020-01198
SP  - 234 - 247
PY  - 2019
AB  - The lack of well-structured metadata annotations complicates the reusability and interpretation of the growing amount of publicly available RNA expression data. The machine learning-based prediction of metadata (data augmentation) can considerably improve the quality of expression data annotation. In this study, we systematically benchmark deep learning (DL) and random forest (RF)-based metadata augmentation of tissue, age, and sex using small RNA (sRNA) expression profiles. We use 4243 annotated sRNA-Seq samples from the sRNA expression atlas database to train and test the augmentation performance. In general, the DL machine learner outperforms the RF method in almost all tested cases. The average cross-validated prediction accuracy of the DL algorithm for tissues is 96.5
LB  - PUB:(DE-HGF)16
C6  - pmid:31855058
C2  - pmc:PMC7047095
DO  - DOI:10.1089/cmb.2019.0320
UR  - https://pub.dzne.de/record/151616
ER  -