Summary of Multi-layer Matrix Factorization For Cancer Subtyping Using Full and Partial Multi-omics Dataset, by Yingxuan Ren et al.
Multi-layer matrix factorization for cancer subtyping using full and partial multi-omics dataset
by Yingxuan Ren, Fengtao Ren, Bo Yang
First submitted to arxiv on: 18 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach for cancer subtyping, Multi-Layer Matrix Factorization (MLMF), is introduced, which employs multi-omics data clustering. MLMF processes multi-omics feature matrices through multi-layer linear or nonlinear factorization, decomposing the original data into latent feature representations unique to each omics type. These latent representations are then fused into a consensus form and used for spectral clustering to determine subtypes. The approach can handle missing omics data by incorporating a class indicator matrix, creating a unified framework that can manage both complete and incomplete multi-omics data. MLMF is evaluated on 10 multi-omics cancer datasets, including those with missing values, demonstrating comparable or surpassing performance compared to state-of-the-art approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to identify different types of cancer, called Multi-Layer Matrix Factorization (MLMF), is developed. MLMF looks at many different kinds of data about cancer cells and groups them together based on their similarities. This helps identify the best way to group cancer cells into subtypes. The approach can handle cases where some data is missing by using a special kind of matrix that shows which type of data is important for each subtype. MLMF was tested on many different datasets and showed results that were just as good or even better than other approaches. |
Keywords
* Artificial intelligence * Clustering * Spectral clustering
