Home
/
Analysis
/
Joint Analysis
Functional Enrichment
Clustering Analysis
Download
/
Help
Clustering Analysis
Step1: Method Selection
Step2: Dataset Input
Step3: Result Browse
Introduction
Clustering analysis is a technique in unsupervised learning that groups data points into clusters (subsets) based on similarity, aiming for intra-cluster homogeneity and inter-cluster heterogeneity.
Clustering analysis modules currently contain seven algorithms to choose from: PCA, PCoA, t-SNE, UMAP, K-Means, Hierarchical K-Means and Fuzzy Clustering (Mfuzz).
Method Selection
PCA
PCoA
t-SNE ( Perplexity:
)
UMAP
K-Means
Hierarchical K-Means
Fuzzy Clustering ( Cluster Number:
)
Figures of Cases
Previous
Next
Next Step
Data Input
*
Upload Matrix File:
Case File:
matrix.txt
Upload Group Information File:
Case File:
groupinfo.txt
Matrix file is required. In a matrix, each column is a sample, and each row is a feature. For details, refer to the case file.
Group information file is optional. If uploaded, the clustering results of the PCA/PCoA/t-SNE/UMAP algorithm will take a different color scheme according to the group.
Fuzzy clustering (Mfuzz) is a clustering analysis based on time series. Therefore, the sample order in the matrix file should be time-sorted.
Last Step
Submit
copyright 2025-present@The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital
