AnnoPRO is a hybrid deep learning framework constructed to enable protein function annotations, which consisted of three consecutive modules (M1 to M3).These modules included: (M1) the sequence-based multi-scale protein representation realizing the conversion of all protein sequences to feature similarity-based images (ProMAP) and protein similarity-based vectors (ProSIM). Particularly, at feature similarity scale, the similarities among protein features were utilized to transform the ‘unordered’ vector of 1,484 protein features to an ‘ordered’ image-like representation; at protein similarity scale, the pair-wise similarities between any two proteins were used to transform the ‘independent’ vector of 1,484 protein features to a ‘globally-relevant’ vector of 92,120 dimensions. (M2) the dual-path protein encoding based on a pre-training. Using the ProMAP and ProSIM generated for all proteins, a dual-path encoding was constructed based on a seven-channel Convolutional Neural Network (7C-CNN) and Deep Neural Network of five fully-connected layers (5FC-DNN) to pre-train the features of all CAFA4 proteins by integrating their annotation data of GO families. (M3) the functional annotation by a LSTM-based decoding. The protein features pre-trained using the dual-path encoding layer in M2 were concatenated and then fed into a long short-term memory recurrent neural network (LSTM) to enable a multi-label annotation of proteins to 6,109 functional GO families using the hybrid deep learning.