In:
Combinatorial Chemistry & High Throughput Screening, Bentham Science Publishers Ltd., Vol. 22, No. 4 ( 2019-07-24), p. 256-265
Abstract:
Lung cancer is a disease with a dismal prognosis and is the major cause of
cancer deaths in many countries. Nonetheless, rapid technological developments in genome science guarantees more effective prevention and treatment strategies. Materials and Methods: In this study, genes were pair-matched and screened for lung adenocarcinomaspecific
gene relationships. False positives due to fluctuations in single gene expression were avoided and the stability and accuracy of the results was improved. Results: Finally, a deep learning model was constructed with machine learning algorithm to realize the
clinical diagnosis of lung adenocarcinoma in patients. Conclusion: Comparing with the traditional methods which takes ingle gene as a feature, the relative
difference between gene pairs is a higher order feature, leverage high-order features to build the model can avoid instability caused by a single gene mutation, making the prediction results more reliable.
Type of Medium:
Online Resource
ISSN:
1386-2073
DOI:
10.2174/1386207322666190530102245
Language:
English
Publisher:
Bentham Science Publishers Ltd.
Publication Date:
2019
SSG:
15,3
Permalink