Identification of immune feature genes and intercellular profiles in diabetic cardiomyopathy

Table 2 Results of least absolute shrinkage and selection operator and support vector machine recursive feature elimination algorithms for the selection of immune-related feature genes

LASSO		SVM-RFE
Variables	Coefficients	Variables	Accuracy	Kappa
Penk	4.895	Il12a	0.800	0.600
Il12a	0	Angptl4	0.900	0.800
Gcgr	-4.308	Rbp7	0.967	0.933
Rbp7	1.761	Sctr	0.900	0.800
Inha	-1.155	Penk	1.000	1.000
Sctr	0	Gcgr	1.000	1.000
Angptl4	2.382	Inha	1.000	1.000

LASSO: Least absolute shrinkage and selection operator; SVM-RFE: Support vector machine recursive feature elimination; Penk: Proenkephalin; Gcgr: Glucagon receptor; Rbp7: Retinol binding protein 7; Inha: Inhibin subunit alpha.