A structural equation modeling approach for the identification of gene expression adaptation in breast cancer patients at grade specific level
Rahul V. Veettil, Eitan Rubin and Norm O'Rourke
Ben -Gurion University of the Negev
We used classical machine learning approach information gain and structural equation modeling to prioratize and find structural relationship between breast cancer genes, recurrence events and recurrence free survival using AMOS software in a large breast cancer cohort.
We identified signature genes and recurrence events which are predictive of recurrence free survival. The model was able to find unique genes that can differentiate between the grades. The identified genes for grade 1 are NEUROD2,IFNA14, SMCP, A1CF, CNTNAP1, APBB3, and G6PC2. For Grade 2, we identified CYP11B1, ARHGEF38, CHRNB3, and NTNG1. Whereas, grade 3 included NTNG1, ALS2CL, A1CF, and P2RY4 genes. We also found 2 genes A1CF and NTNG1 partcipating in grade 1& 3 and grade 2&3, respectively.