The benchmark dataset contains 278 phage proteins which are 144 phage proteins located in host cell (PH proteins) and 134 phage proteins not located in host cell (non-PH proteins). The sequence identity in the dataset is less 30%. Download The 144 PH proteins also divide into 68 phage proteins located in host cell membrane (PHM proteins) and 76 phage proteins located in host cell cytoplasm (PHC proteins). Download |