Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Classifying protein-protein interaction articles using word and syntactic features

Figure 1

Overview of the proposed PPI article classification approach. Input articles are first evaluated whether there are gene/protein names in the text. After gene name detection, feature generation is performed in three different ways: word features including multi-words, sub-strings, and MeSH terms; syntactic features involving grammar relations between words; higher-order features obtained by evaluating a combination of different features.

Back to article page