Predicting plant protein subcellular multi-localization by Chou's PseAAC formulation based multi-label homolog knowledge transfer learning

► We define a multi-label confusion matrix. ► We use probabilistic outputs to adapt MK-TLM to multi-label learning scenario. ► We propose two multi-labeling performance measures: LHRNT-LHR. ► We conduct multi-labeling estimation in optimistic, moderate and pessimistic cases.