(a-b) The LASSO algorithm was used for hyperparameter tuning and identification of the important predictive features.

(a-b) The LASSO algorithm was used for hyperparameter tuning and identification of the important predictive features.

<p>(c) The top genes chosen by the LASSO model as important features.</p>

Saved in:

Bibliographic Details
Main Author:	Devi Soorya Narayana Sasikumar (22331743) (author)
Other Authors:	Vino Sundararajan (14514034) (author)
Published:	2025
Subjects:	Biochemistry Cell Biology Genetics Molecular Biology Immunology Cancer Infectious Diseases Biological Sciences not elsewhere classified Information Systems not elsewhere classified relevant modules relevant lipid peroxide accumulation least absolute shrinkage immune infiltrating cells future studies focusing functional annotation analysis involving symmetric joints support vector machine related genes associated differentially expressed genes using r software sat1 contribute significantly protein interaction network gene expression omnibus xlink "> nampt xlink "> pathways involving three machine machine learning hub genes genes showed common genes 314 genes 17 genes wgcna ). underlying mechanisms transcriptomic dataset therapeutic targets therapeutic potential systemic involvement svm ), substantial association selection operator roc curve rf ), potential biomarkers nomogram plots level contributions learning algorithms larger cohorts influencing immunity inflammatory diseases gene ontology chronic presentation biological functions
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	<p>(c) The top genes chosen by the LASSO model as important features.</p>

Cannot write session to /tmp/vufind_sessions/sess_3ur4pi429h9ifa45uje7cue5dd