Network-constrained regularization and variable selection for analysis of genomic data

By Caiyan Li, Hongzhe Li. Bioinform., 2008

520 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Visualization of genetic disease-phenotype similarities by multiple maps t-SNE with Laplacian regularization (2014, methodology): “The Laplacian regularization has been used for many other objective functions such as linear regression [13] and Gaussian Mixture Model [14].”
Identifying phenotype-associated subpopulations by integrating bulk and single-cell sequencing data (2021, unknown): “Furthermore, the network-based penalty enforces the tightly connected nodes (cells) in the network to have more similar coefficients 50 , making the phenotype-to-cell association results more consistent and interpretable.”
Network-based machine learning and graph theory algorithms for precision oncology (2017, methodology): “The paper 34 proposed a network-constrained linear regression procedure that combines a graph Laplacian constraint with the L 1 -norm sparse linear regression to capture the relations among the regression coef ﬁ cients.”
Network-based support vector machine for classification of microarray samples (2009, methodology): “The simulation setups were similar to those in [18].”
Regularized Learning with Networks of Features (2008, methodology): “The main difference between the Laplacian penalty and the network penalty in equation (1) is that the Laplacian penalizes each edge equally (modulo the edge weights) whereas the network penalty penalizes each feature equally.”