IPFMC: an iterative pathway fusion approach for enhanced multi-omics clustering

Paper: Haoyang Zhang, Sha Liu, Bingxin Li, Xionghui Zhou, IPFMC: an iterative pathway fusion approach for enhanced multi-omics clustering in cancer research, Briefings in Bioinformatics, Volume 25, Issue 6, November 2024, bbae541, https://doi.org/10.1093/bib/bbae541

Function: IPFMC improves clustering of multi-omics data in cancer research. IPFMC enhances clustering performance by iteratively selecting key pathways to represent samples, thus improving cancer subtype classification. It also emphasizes biological interpretability by identifying significant pathways and genes that clarify cancer mechanisms. By integrating information from different omics through similarity network fusion, IPFMC outperforms existing methods across various cancer datasets, demonstrating its potential in precision medicine.de structure, which can perform representation learning.

https://github.com/BioLemon/IPFMC

DeepCentroid: Deep Cascade Centroid Classifier

Function: A precision medical research method based on deep cascade centroid classifier is an integrated learning method with cascade structure, which can perform representation learning.
It can be applied to early diagnosis, prognosis and drug sensitivity prediction of cancer.

https://github.com/xiexiexiekuan/DeepCentroid

Ensemble Classifier based on gene synergistic network

Paper: Lu Bo, Xiong-Hui Zhou*. Ensemble Classifier based on gene synergistic network improves breast cancer outcome prediction. IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2019; 207-210.

Function: Using gene expression data and matched clinical data od cancer patients, construct gene synergistic networks.

https://github.com/lubo1220/Ensemble-Classifier-based-on-gene-synergistic-network.git

Coming soon.