Fig. 3From: Multi-scaled self-attention for drug–target interaction prediction based on multi-granularity representationResults of DeepDTA [6] model on the KIBA dataset with different multi-granularity representations as inputs. These multi-granularity representations are encoded by BPE algorithm with different threshold T. Here, \(T_d\) is the threshold T for drug segmentation and \(T_p\) is the threshold T for protein segmentationBack to article page