Check if the way the negative set of this publication is constructed is interesting for us: doi: 10.1186/s12918-017-0390-8
The basic idea of our method is like this: for anexperimentally-validated PRI of proteinpand RNAr,rishighly possible to interact with any proteinp′similar top.Onthecontrary,ifproteinp′is dissimilar top,thereislow possibility thatp′interactsr. Based on this idea, wepropose the methodFIREto construct reliable negativePRIs. The flowchart of FIRE is shown in Fig. 3. Concretely,for each positive PRI (p,r), we try to find any proteinp′that is as much dissimilar as possible top.If(p′,r)isnotan experimentally-validated PRI, then it is selected as anegative PRI.
Check if the way the negative set of this publication is constructed is interesting for us: doi: 10.1186/s12918-017-0390-8
The basic idea of our method is like this: for anexperimentally-validated PRI of proteinpand RNAr,rishighly possible to interact with any proteinp′similar top.Onthecontrary,ifproteinp′is dissimilar top,thereislow possibility thatp′interactsr. Based on this idea, wepropose the methodFIREto construct reliable negativePRIs. The flowchart of FIRE is shown in Fig. 3. Concretely,for each positive PRI (p,r), we try to find any proteinp′that is as much dissimilar as possible top.If(p′,r)isnotan experimentally-validated PRI, then it is selected as anegative PRI.