Discriminating Neoplastic from Non-Neoplastic Tissues using a microRNA-based Deep Cancer Classifier

Am J Pathol. 2021 Nov 10:S0002-9440(21)00479-X. doi: 10.1016/j.ajpath.2021.10.012. Online ahead of print.ABSTRACTNext-generation sequencing has enabled the collection of large biological datasets, allowing novel molecular-based classification methods to be developed for increased understanding of disease. microRNAs (miRNAs) are small regulatory RNA molecules that can be quantified using next-generation sequencing and are excellent classificatory markers. Here, we adapt a Deep Cancer Classifier (DCC) to differentiate neoplastic from non-neoplastic samples using comprehensive miRNA expression profiles from 1,031 human breast and skin tissue samples. The classifier was fine-tuned and evaluated using 750 neoplastic and 281 non-neoplastic breast and skin tissue samples. Performance of the DCC was compared to two machine learning classifiers: support vector machine and random forests. In addition, performance of feature extraction through the DCC was also compared with a developed feature selection algorithm, cancer specificity. The DCC had the highest performance of AUC and high performance in both sensitivity and specificity, unlike machine learning and feature selection models which often performed well in one metric compared to the other. In particular, deep learning was shown to have noticeable advantages with highly heterogeneous datasets. In addition, our cancer specificity algorithm identified candidate biomarkers for differentiating neoplastic and non-neoplastic tissue sam...
Source: The American Journal of Pathology - Category: Pathology Authors: Source Type: research