Fig. 1From: A context-free encoding scheme of protein sequences for predicting antigenicity of diverse influenza A virusesA pipeline for machine learning projects and illustration for CFreeEnS. a Encoding a non-numeric dataset into equal-length numeric vectors is necessary for both traditional machine learning models and deep neural networks. b CFreeEnS encodes m aligned protein sequence pairs of length l with k substitution matrices, resulting in a numeric feature matrix X with dimension m×k×lBack to article page