MIA - CNCB-NGDC

MIA is a one-stop platform for multi-omics integrative analysis, committing to clustering and identifying feature genes by supervised and unsupervised learning algorithms. Based on input data from single or multiple omics, it is capable for disease subtyping/classification, feature gene identification, differential analysis between normal and disease samples, tissue/cell clustering, etc.

Clustering & Feature Gene Identification

Input at least one omics dataset. Data file type: .txt; Data separator: Tab;
Rows: genes/features; Columns: samples.

* Omics data1:

(<30 MB allowed) e.g., Transcriptome

For two or three omics types: genes/samples should be arranged consistently
in different datasets.

Omics data2:

(<30 MB allowed) e.g., CNV

Omics data3:

(<30 MB allowed) e.g., DNA methylation

To cluster unlabeled samples, please specify the cluster number (2~10) or select “auto”, which means that an optimal cluster number will be determined automatically.

Cluster number:

For labeled samples, please input label file. Data file type: .txt; Data separator: Tab; First column: sample; Second column: label.

Sample labels:

(<3 MB allowed) Example Label

Try Demo:

(1) Transcriptome + Cluster number: Auto
(2) Transcriptome + DNA methylation + Cluster number: 3
(3) DNA methylation + CNV + Sample labels

MIA Multi-omics Integrative Analysis

Clustering & Feature Gene Identification

Input omics data

Cluster or Input labels

Try Demo:

* Get results: