PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine

By Ian M. Donaldson, Joel D. Martin, Berry de Bruijn, Cheryl Wolting, V. Lay, Brigitte Tuekam, Shudong Zhang, B. Baskin, Gary D. Bader, K. Michalickova and 2 more. BMC Bioinformatics, 2003

362 citations recorded by the source corpus.

BackgroundThe majority of experimentally verified molecular interaction and biological pathway data are present in the unstructured text of biomedical journal articles where they are inaccessible to computational methods. The Biomolecular interaction network database (BIND) seeks to capture these data in a machine-readable format. We hypothesized that the formidable task-size of backfilling the database could be reduced by using Support Vector Machine technology to first locate interaction information in the literature. We present an information extraction system that was designed to locate protein-protein interaction data in the literature and present these data to curators and the public for review and entry into BIND.ResultsCross-validation estimated the support vector machine's test-set precision, accuracy and recall for classifying abstracts describing interaction information was 92%, 90% and 92% respectively. We estimated that the system would be able to recall up to 60% of all non-high throughput interactions present in another yeast-protein interaction database. Finally, this system was applied to a real-world curation problem and its use was found to reduce the task duration by 70% thus saving 176 days.ConclusionsMachine learning methods are useful as tools to direct interaction and pathway database back-filling; however, this potential can only be realized if these techniques are coupled with human review and entry into a factual database such as BIND. The PreBIND system described here is available to the public at http://bind.ca. Current capabilities allow searching for human, mouse and yeast protein-interaction information.

Subfields: Computational Theory and Mathematics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/5de350b446853b61da1ccd5c89d291f987ef4a8b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

A survey of current work in biomedical text mining (2005, methodology): “used an SVM trained on the words in MEDLINE abstracts to distinguish abstracts containing information on protein-protein interactions, prior to curating this information into their BIND database [36].”
Overview of the protein-protein interaction annotation extraction task of BioCreative II (2008, methodology): “In order to improve the efficiency of locating curation relevant articles by the Biomolecular Interaction Network Database (BIND) curators, an extraction system called PreBIND based on support vector machine (SVM) classifiers to detect interaction-relevant articles, has been developed [10].”
The Biomolecular Interaction Network Database and related tools 2005 update (2004, background): “PreBIND (16) is currently a separate information system with interactions derived from text mining of MEDLINE abstracts (17).”
Textpresso: An Ontology-Based Information Retrieval and Extraction System for Biological Literature (2004, background): “Other machine learning approaches have classiﬁed abstracts and sentences for relevant interactions, but have not extracted information (Marcotte et al. 2001; Donaldson et al. 2003).”
Mining the Biomedical Literature in the Genomic Era: An Overview (2003, positive): “Most recently, Donaldson et al. (2003) introduced their PreBind/Textomy system, in which they combine information retrieval with information extraction to assist in recovering protein–protein interactions from the literature.”
Biomedical language processing: what's beyond PubMed? (2006, background): “This work is surveyed in Cohen and Hunter (2004) .”
Extracting interactions between proteins from the literature (2008, neutral): “[8] constructed PreBIND and Textomy—an information extraction system”
Evaluation of linguistic features useful in extraction of interactions from PubMed; Application to annotating known, high-throughput and predicted interactions in I2D (2009, methodology): “Results: We developed an interaction detection method and explored the usefulness of various features in automatically identifying PPIs in text.”
Text-mining and information-retrieval services for molecular biology (2005, methodology): “PreBIND Classifier of protein interaction documents http://bind.ca/ [ 44 ]”
Content-rich biological network constructed by mining PubMed abstracts (2004, background): “Others assign relationships based on similarities in the texts of abstracts [5-7].”
STRING: known and predicted protein–protein associations, integrated and transferred across organisms (2004, background): “Another important source of protein association information is the published literature (18,19).”