Discovering patterns to extract protein–protein interactions from full texts

Huang, Minlie; Zhu, Xiaoyan; Yu, Hongfang; Payan, Donald G.; Qu, Kun; Li, Ming

doi:10.1093/bioinformatics/bth451

Cited by 182 publications

(112 citation statements)

References 15 publications

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…Since the corpus I data used in our experiments came from [6], it would be interested to see how our system performed compared to the method based on pattern matching proposed in [6]. If simply comparing the respective recall and precision rates, our method is less efficient.…”

Section: Resultsmentioning

confidence: 99%

“…Approaches using pattern matching [4,5,6] rely on a set of predefined patterns or rules to extract proteinprotein interactions. For example, Ono's method [5] manually defines some rules and patterns which are augmented with additional restrictions based on syntactic categories and word forms to give better matching precision.…”

Section: Introductionmentioning

confidence: 99%

“…It achieves high performance with a recall rate of 85% and precision rate of 84% for Saccharomyces cerevisiae (yeast) and Escherichia coli. Another method [6] tries to use dynamic programming to automatically discover patterns which describe protein-protein interactions. Their results give precision of 80.5% and recall of 80.0%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Zhou

Kwoh

2006

Computational Science – ICCS 2006

View full text Add to dashboard Cite

Abstract. In the field of bioinformatics in solving biological problems, the huge amount of knowledge is often locked in textual documents such as scientific publications. Hence there is an increasing focus on extracting information from this vast amount of scientific literature. In this paper, we present an information extraction system which employs a semantic parser using the Hidden Vector State (HVS) model for protein-protein interactions. Unlike other hierarchical parsing models which require fully annotated treebank data for training, the HVS model can be trained using only lightly annotated data whilst simultaneously retaining sufficient ability to capture the hierarchical structure needed to robustly extract task domain semantics. When applied in extracting protein-protein interactions information from medical literature, we found that it performed better than other established statistical methods and achieved 47.9% and 72.8% in recall and precision respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Zhou

Kwoh

2006

Computational Science – ICCS 2006

View full text Add to dashboard Cite

show abstract

“…In terms of the NLP techniques used in the biomedical domain these involve either full parsing [17] or shallow parsing methods [15]. Concerning machine learning techniques, these are used for pattern extraction employing lexical, syntactic and semantic features [8]. Our work is based on shallow parsing methods exploiting the semantic features extracted by the previous stage of our ontology population method (ontology instances and their synonyms).…”

Section: Related Workmentioning

confidence: 99%

Populating an Allergens Ontology Using Natural Language Processing and Machine Learning Techniques

Valarakos

Karkaletsis

Alexopoulou

et al. 2005

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Abstract.Ontologies are becoming increasingly important in the biomedical domain since they enable the re-use and sharing of knowledge in a formal, homogeneous and unambiguous way. In the rapidly growing field of biomedicine, knowledge is usually evolving and therefore an ontology maintenance process is required to keep the ontological knowledge up-to-date. This paper presents our approach for populating a formally defined ontology for the allergen domain exploiting PubMed abstracts on allergens and using natural language processing and machine learning techniques. This approach is composed of two stages: locating initially instances of ontology concepts in the PubMed corpus, and finding at a 2nd stage instances' properties and relations between instances.

show abstract

“…But, the protein interaction data is still accumulated manually in biological databases. Furthermore, scientists sometime continue to publish their discoveries on new protein interactions and modifying previous results in scientific papers without submitting to the public databases [2]. Therefore, a lot of interaction data still exist only in text materials.…”

Section: Introductionmentioning

confidence: 99%

A Tree Kernel-Based Method for Protein-Protein Interaction Mining from Biomedical Literature

Eom

Kim

et al. 2006

Knowledge Discovery in Life Science Literature

View full text Add to dashboard Cite

Abstract.As genomic research advances, the knowledge discovery from a large collection of scientific papers becomes more important for efficient biological and biomedical research. Even though current databases continue to update new protein-protein interactions, valuable information still remains in biomedical literature. Thus data mining techniques are required to extract the information. In this paper, we present a tree kernel-based method to mine protein-protein interactions from biomedical literature. The tree kernel is designed to consider grammatical structures for given sentences. A support vector machine classifier is combined with the tree kernel and trained on predefined interaction corpus and set of interaction patterns. Experimental results show that the proposed method gives promising results by utilizing the structure patterns.

show abstract

Discovering patterns to extract protein–protein interactions from full texts

Abstract: The program is available on request from the authors.

Cited by 182 publications

References 15 publications

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Populating an Allergens Ontology Using Natural Language Processing and Machine Learning Techniques

A Tree Kernel-Based Method for Protein-Protein Interaction Mining from Biomedical Literature

Contact Info

Product

Resources

About