Identifying Stage II Colorectal Cancer Recurrence Associated Genes by Microarray Meta-Analysis and Building Predictive Models with Machine Learning Algorithms

Table 2

Regression coefficients of the lasso Cox model.

Gene symbol	β	Gene symbol	β
PAOX	−0.02752	FLJ90680	0.011181
SIGLEC7	0.174815	NVL	−0.0407
PHAX	−0.02803	ESM1	0.158185
XCR1	0.073122	GABRR2	0.055987
TM4SF4	0.021224	FAM166A	−0.56059
TRIOBP	0.173985	USP14	−0.03345
MCMBP	−0.10873	JUNB	0.268267
HCFC1R1	0.029341	UBAP2	−0.41623
ADNP2	−0.1739	AP5B1	−0.3134
NUP50	−0.02431	FAM46C	−0.02913
GTF2A2	−0.01368	LDB3	0.146108
BCCIP	−0.03355	JUP	0.260895

Positive regression coefficients indicate that higher gene expression values contributed to higher recurrence risks, while negative coefficients indicate that higher gene expression values contributed to lower recurrence risks.