Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Sep 10;12:682841. doi: 10.3389/fgene.2021.682841

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2021 Jung, Kim, Rhee, Lim and Kim.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

The workflow of the MONTI framework. (A) Each omics data (gene expression, methylation, miRNA expression) is pre-processed as a two-dimensional gene-centric matrix comprised of genes and samples. (B) The omics matrices are then stacked to form a three-dimensional tensor structure (genes, samples, omics) all sharing the same genes and samples. (C) Using the PARAFAC approach, the tensor is decomposed into two-dimensional gene, patient and omics components. Here, the components share the rank features. (D) The patient component is used to select subtype-specific features using subtype-specific L1 classifiers. The selected subtype-specific features are used to build a subtype classifier model using MLP (Multi-layer perceptron). Genes associated to the subtype-specific features are then selected for biological function analysis.