CEPICS: A Comparison and Evaluation Platform for Integration Methods in Cancer Subtyping

Area of Science:

• Computational biology
• Bioinformatics
• Cancer research

Background:

• Cancer subtypes enhance understanding and treatment precision.
• Multi-omics data offers multi-level cancer characterization.
• Lack of gold standards hinders evaluation of multi-omics integration methods for cancer subtyping.

Purpose of the Study:

• To develop a scalable platform, CEPICS, for comprehensive evaluation and comparison of multi-omics data integration methods in cancer subtyping.
• To provide a guideline for users to select optimal integration methods.
• To enable robust cancer subtype prediction.

Main Methods:

• CEPICS integrates up to five state-of-the-art methods for cancer subtyping.
• It evaluates methods using clustering performance metrics and clinical survival analysis.
• Users can upload their own subtyping results for comparison.

Main Results:

• CEPICS provides subtyping results for a user-specified maximum number of subtypes (k-max).
• It generates evaluation reports comparing different integration methods.
• The platform facilitates robust cancer subtype prediction by analyzing results from various methods.

Conclusions:

• CEPICS offers a standardized approach for evaluating multi-omics integration methods in cancer subtyping.
• The platform aids researchers in selecting appropriate methods for their specific needs.
• CEPICS contributes to advancing precision oncology through improved cancer subtyping.