Uncovering protein interaction in abstracts and text using a novel linear model and word proximity networks

• Autores: Abi-Haidar, Alaa; Kaur, Jasleen; Maguitman, Ana Gabriela; Radivojac, Pedrag; Rechtsteiner, Andreas; Verspoor, Karin; Wang, Zhiping; Rocha, Luis
• Año de publicación: 2008
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: Support Vector Machine; Singular Value Decomposition; Word Pair; Singular Value Decomposition Method; Proximity Network
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

Background: We participated in three of the protein-protein interaction subtasks of the Second BioCreative Challenge: classification of abstracts relevant for protein-protein interaction (interaction article subtask [IAS]), discovery of protein pairs (interaction pair subtask [IPS]), and identification of text passages characterizing protein interaction (interaction sentences subtask [ISS]) in full-text documents. We approached the abstract classification task with a novel, lightweight linear model inspired by spam detection techniques, as well as an uncertainty-based integration scheme. We also used a support vector machine and singular value decomposition on the same features for comparison purposes. Our approach to the full-text subtasks (protein pair and passage identification) includes a feature expansion method based on word proximity networks. Results: Our approach to the abstract classification task (IAS) was among the top submissions for this task in terms of measures of performance used in the challenge evaluation (accuracy, F-score, and area under the receiver operating characteristic curve). We also report on a web tool that we produced using our approach: the Protein Interaction Abstract Relevance Evaluator (PIARE). Our approach to the full-text tasks resulted in one of the highest recall rates as well as mean reciprocal rank of correct passages. Conclusion: Our approach to abstract classification shows that a simple linear model, using relatively few features, can generalize and uncover the conceptual nature of protein-protein interactions from the bibliome. Because the novel approach is based on a rather lightweight linear model, it can easily be ported and applied to similar problems. In full-text problems, the expansion of word features with word proximity networks is shown to be useful, although the need for some improvements is discussed.
Fil: Abi-Haidar, Alaa. Indiana University; Estados Unidos. Fundação Luso-Americana para o Desenvolvimento; Portugal
Fil: Kaur, Jasleen. Indiana University; Estados Unidos
Fil: Maguitman, Ana Gabriela. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación; Argentina
Fil: Radivojac, Pedrag. Indiana University; Estados Unidos
Fil: Rechtsteiner, Andreas. Indiana University; Estados Unidos
Fil: Verspoor, Karin. Los Alamos National High Magnetic Field Laboratory; Estados Unidos
Fil: Wang, Zhiping. Indiana University; Estados Unidos
Fil: Rocha, Luis. Fundação Luso-Americana para o Desenvolvimento; Portugal. Indiana University; Estados Unidos