Modeling Protein-Protein Interactions in Biomedical Abstracts with Latent Dirichlet Allocation

A major goal in biomedical text processing is the automatic extraction of protein interaction information from scientific articles or abstracts. We approach this task with a topic-based generative model. Under the model, sentences in biomedical abstracts can be generated by either an ’interaction’ topic if they contain or discuss interacting proteins or a ’background’ topic otherwise. This structure is implemented as a Latent Dirichlet Allocation (LDA) model. The model structure was previously developed as part of work with Mark Craven and Jerry Zhu. During this project, parameter inference equations and algorithms were derived. Future work will consist of implementation and experimental testing.