hemaClass.org: Online One-By-One Microarray Normalization and Classification of Hematological Cancers for Precision...

Area of Science:

• Bioinformatics
• Genomics
• Cancer Research

Background:

• Omics-based cancer classification systems exist but are complex and cohort-dependent.
• Personalized clinical application of these systems is challenging.
• Existing methods hinder individual patient risk stratification.

Purpose of the Study:

• To develop hemaClass.org, an accessible online tool for personalized cancer classification.
• To enable one-by-one RMA normalization and risk stratification for diffuse large B-cell lymphoma (DLBCL).
• To compare one-by-one classification with traditional cohort-based methods.

Main Methods:

• Developed hemaClass.org, a web application integrating the R-package hemaClass.
• Implemented one-by-one RMA normalization for microarray data.
• Compared classifications from one-by-one and cohort-based methods across four public datasets.

Main Results:

• hemaClass.org provides an easy interface for microarray normalization and DLBCL classification.
• One-by-one classification showed high agreement with cohort-based classifiers when using laboratory-specific reference data.
• The R-package allows for local execution and programmatic use of the developed methods.

Conclusions:

• hemaClass.org and its R-package offer reliable and rapid disease subclass calculation for lymphoma researchers.
• The one-by-one pre-processing method is broadly applicable to microarray data analysis.
• This approach facilitates personalized risk assessment in clinical settings.