Evaluation of linguistic features useful in extraction of interactions from PubMed; Application to annotating known, high-throughput and predicted interactions in I2D

By Yun Niu, D. Otasek, Igor Jurisica. 2009

86 citations recorded by the source corpus.

Motivation: Identification and characterization of protein–protein interactions (PPIs) is one of the key aims in biological research. While previous research in text mining has made substantial progress in automatic PPI detection from literature, the need to improve the precision and recall of the process remains. More accurate PPI detection will also improve the ability to extract experimental data related to PPIs and provide multiple evidence for each interaction. Results: We developed an interaction detection method and explored the usefulness of various features in automatically identifying PPIs in text. The results show that our approach outperforms other systems using the AImed dataset. In the tests where our system achieves better precision with reduced recall, we discuss possible approaches for improvement. In addition to test datasets, we evaluated the performance on interactions from five human-curated databases—BIND, DIP, HPRD, IntAct and MINT—where our system consistently identified evidence for ∼60% of interactions when both proteins appear in at least one sentence in the PubMed abstract. We then applied the system to extract articles from PubMed to annotate known, high-throughput and interologous interactions in I2D. Availability: The data and software are available at: http://www.cs.utoronto.ca/∼juris/data/BI09/. Contact: yniu@uhnres.utoronto.ca; juris@ai.utoronto.ca Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

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

In Molecular Biology

Citations in the corpus

The MIntAct project—IntAct as a common curation platform for 11 molecular interaction databases (2013, neutral): “Other databases such as I2D (Interologous Interaction Database) (20), which curates interaction protein interaction data relevant to the development of cancer and InnateDB (21), capturing both protein and gene interactions relevant to the process of innate immunity, choose to select appropriate reco”
Machine learning applications in cancer prognosis and prediction (2014, methodology): “The dataset used through this study consists of gene expression pro ﬁ les found in the GEO repository [62] as well as of PPIs derived from the I2D database [63].”
Pi-Pi contacts are an overlooked protein feature relevant to phase separation (2018, result): “By comparing score pairs from protein interactions taken from the I2D metadatabase (Niu et al., 2010), we confirm that high-scoring proteins and low-scoring proteins are both over two-fold more likely to interact with proteins of similar score, relative to expectations (Figure 6A).”