English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

miRNA and gene expression profiles have been proved useful for classifyingcancer samples. Efficient classifiers have been recently sought and developed.A number of attempts to classify cancer samples using miRNA/gene expressionprofiles are known in literature. However, the use of semi-supervised learningmodels have been used recently in bioinformatics, to exploit the huge corpusesof publicly available sets. Using both labeled and unlabeled sets to trainsample classifiers, have not been previously considered when gene and miRNAexpression sets are used. Moreover, there is a motivation to integrate bothmiRNA and gene expression for a semi-supervised cancer classification as thatprovides more information on the characteristics of cancer samples. In thispaper, two semi-supervised machine learning approaches, namely self-learningand co-training, are adapted to enhance the quality of cancer sampleclassification. These approaches exploit the huge public corpuses to enrich thetraining data. In self-learning, miRNA and gene based classifiers are enhancedindependently. While in co-training, both miRNA and gene expression profilesare used simultaneously to provide different views of cancer samples. To ourknowledge, it is the first attempt to apply these learning approaches to cancerclassification. The approaches were evaluated using breast cancer,hepatocellular carcinoma (HCC) and lung cancer expression sets. Results show upto 20% improvement in F1-measure over Random Forests and SVM classifiers.Co-Training also outperforms Low Density Separation (LDS) approach by around25% improvement in F1-measure in breast cancer.

miRNA and Gene Expression based Cancer Classification using Self- Learning and Co-Training Approaches