Skip to main content

Table 1 Feature space mapping from three distinct proteins P i , P j , P k .

From: Prediction of heterotrimeric protein complexes by two-phase learning using neighboring kernels

(F1)

max { ( p , q ) E | p , q { i , j , k } } w p q

(F2)

min { ( p , q ) E | p , q { i , j , k } } w p q

(F3)

max { ( p , r ) E | p { i , j , k } , r { i , j , k } } w p r

(F4)

min { ( p , r ) E | p { i , j , k } , r { i , j , k } } w p r

(F5)

max { ( p , r ) , ( q , r ) E | p , q { i , j , k } , p q , r { i , j , k } } min { w p r , w q r }

(F6)

max{# domains of P i , # domains of P j , # domains of P k }

(F7)

min{# domains of P i , # domains of P j , # domains of P k }