CORAZON is an abreviation of CORrelations Analyses Zipper ONline, a bioinformatic tool that uses artificial intelligence to cluster genes according to their expression in tissues and also a tool to normalize databases.

This tool is composed of 3 unsupervised machine learning algorithms: Mean Shift, K-Means and Hierarchical. Unsupervised learning is the machine learning task of inferring a function to describe the hidden structure from unlabeled data. The inductor analyzes the examples provided and tries to determine if some of them can be grouped in any way, forming clusters. All these 3 algorithms was implemented using Euclidean distance a measure of similarity.

CORAZON also includes 8 normalization methodologies: Trimmed Mean of M-values (TMM), Median Ratio Normalization (MRN), Fragments Per Kilobase Million (FPKM), Transcripts Per Kilobase Million (TPM), Counts per million (CPM), base-2 log (log₂), normalization by the sum of the instance's attributes values and normalization by the highest attribute value for each instance. Moreover, a strategy to observe the attributes influence in results was implemented.

Click "Cluster" to start using CORAZON! You can submit a job as a guest, or create a user through the "Sign Up" menu, which will grant you a job table with all your previous results. For more details on the algorithms and normalizations performance, examples and CORAZON schema, check the "Documentation". Contact us if you have any questions or suggestions!

Reference: Ramos, T.A.R., Maracaja-Coutinho, V., Ortega, J.M., do Rêgo, T.G. CORAZON: a web server for data normalization and unsupervised clustering based on expression profiles . BMC Research Notes 13, 338 (2020).