MIA - CNCB-NGDC

Based on input data from single or multiple omics, MIA 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
A machine learning framework for accurate sample clustering and feature discovery from multi-omics data.

Clustering & Feature Gene Identification

Input omics data

Cluster or Input labels

Try Demo:

* Get results: