Normalization of Large Scale Transcriptome Data Using Heuristic Methods. Normalization of Large Scale Transcriptome Data Using Heuristic Methods

We introduce AI method for addressing batch effect of genetic data The method does not rely on any assumptions regarding the distribution and the behavior of data elements. Hence, it does not introduce any new biases in the process of correcting for batch effect. It strictly maintains the integrity of measurements within the original batches. Overall design: The human peripheral mononuclear blood cells (PBMC) samples from multiple sclerosis patients treated in Multiple Sclerosis Center, Sheba Medical Center, Israel were processed on Affymetrix HU-133A-2 microarrays (Santa Clara, CA) according to manufacturer protocol between 2006 and 2014 . A total 216 samples from 216 distinct individuals, combined from 24 batches associated with working sets consisting of more than seven samples of each were analyzed.