Bayesian inference of protein–protein interactions from biological literature

Chowdhary, Rajesh; Zhang, Jinfeng; Liu, Jun S.

doi:10.1093/bioinformatics/btp245

Cited by 67 publications

(70 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The relation verbs of protein interaction are extracted and summarized from the work of Chowdhary et al (2009) as seed words. The total seed words retrieved from Chowdhary contain 293 words.…”

Section: Relation Lexicon Learningmentioning

confidence: 99%

Interaction Relation Ontology Learning

Wang

Zhang

et al. 2014

Journal of Computational Biology

View full text Add to dashboard Cite

Ontology is widely used in semantic computing and reasoning, and various biomedicine ontologies have become institutionalized to make the heterogeneous knowledge computationally amenable. Relation words, especially verbs, play an important role when describing the interaction between biological entities in molecular function, biological process, and cellular component; however, comprehensive research and analysis are still lacking. In this article, we propose an automatic method to build interaction relation ontology by investigating relation verbs, analyzing the syntactic relation of PubMed abstracts to perform relation vocabulary expansion, and integrating WordNet into our method to construct the hierarchy of relation vocabulary. Five attributes are populated automatically for each word in interaction relation ontology. As a result, the interaction relation ontology is constructed; it contains a total of 963 words and covers the most relation words used in existing methods of proteins interaction relation.

show abstract

Section: Relation Lexicon Learningmentioning

confidence: 99%

Interaction Relation Ontology Learning

Wang

Zhang

et al. 2014

Journal of Computational Biology

View full text Add to dashboard Cite

show abstract

“…Protein-protein interactive words library contains 191 words organized by reference [8]. Firstly, filter out the sentences that include protein-protein interactive words and at least two proteins related to liver cancer from the literature of liver cancer.…”

Section: Build the Interaction Network Between The Corresponding Pmentioning

confidence: 99%

Liver Cancer Related Gene Analysis Based on Literature Mining

Li¹,

Zou²,

Wang³

2013

IJBBB

View full text Add to dashboard Cite

Abstract-To identify liver cancer related genes and understand their interactions, we introduce a method based on literature mining. The genes are extracted with the disease-gene association classifier based on Bayesian network, and then the interaction network between the corresponding proteins is built. This paper has extracted 464 genes which are related to the liver cancer, and found genes such as p53, VEGF, TNF, AKT are hub proteins, which play important roles in the network. The KEGG pathway analysis shows that 19 enriched pathways may participate in liver carcinogenesis. Network analysis and pathway analysis implies the complexity of the occurrence, progression and prognosis of liver cancer.Index Terms-Bayesian classifier, genes and pathways analysis, liver cancer, literature mining. I. INTRODUCTIONIn the past ten years, with the development of the biomedical science technology, the number of the biomedical literature has been growing exponentially. How to extract the needed knowledge and to obtain new knowledge quickly and efficiently from massive articles has become a very important research area. The interaction between diseases and related proteins is one of the main research directions which mean a lot to disease prevention, diagnosis, therapy and designing biomedical experiment and so on [1].Liver cancer is one of the most common malignant tumors in China. It is reported that the number of people who die of liver cancer is about 110,000 every year and is 55% of the global patients. What's worse, the early symptoms of liver cancer are not apparent and the condition of patients deteriorates quickly. On average, patients can only live about 6 months after the cancer was diagnosed. Therefore, with all these mentioned above, research on liver cancer is necessary.So far, the existing study has been focusing on the interaction between individual protein and liver cancer. The present problem is how to integrate the experiment information gained and researched to help analyze molecular interactions, pathways and their influence on the occurrence, progression as well as prognosis of liver cancer.A method of identifying disease-gene associations based on literature mining which was applied in prostate cancer has genes related to diseases as prior knowledge, and the extracted genes must appear with at least one of seed genes in the same sentence, which leads to the limit of that method. Manuscript received January 24, 2013; revised March 24, 2013. Engineering, Soochow University, P. R. China (e-mail: liuxuan1220@ yahoo.cn, zouwei_198107@163.com, jjwang@suda.edu.cn).In order to solve this problem, we try to extract genes related to liver cancer without priors from the massive literatures and automatically build the interaction network between the corresponding proteins. II. METHODS A. Search for Literatures on Liver CancerBy searching the key words and free words of liver cancer in MeSH database of NCBI and collecting aliases of liver cancer from the reference [2] to conclude 14 aliases of liver cancer, such ...

show abstract

“…They are comprised of two protein names and a relational word that describes the interaction between two proteins. In order to identify these candidate interactions we make use of a protein name dictionary and an interaction word dictionary, compiled in an earlier study [6]. The protein name dictionary consists of 68,970 protein names acquired from BioGrid.…”

Section: Dictionariesmentioning

confidence: 99%

“…These rules may be manually defined, automatically learned, or a combination of the two [6]. Early methods used simple, manually defined rules such as co-occurrence [27,16,3,30,22].…”

Section: Introductionmentioning

confidence: 99%

Mixture of logistic models and an ensemble approach for protein-protein interaction extraction

Bell

Zhang

Niu

2011

Proceedings of the 2nd ACM Conference on Bioinformatics, Computational Biology and Biomedicine

Self Cite

View full text Add to dashboard Cite

Automatic extraction of protein-protein interaction (PPI) information from scientific literature is important for building PPI databases, studying biological networks and discovering new biological knowledge through automatic hypothesis generation. In this paper, we present a new method for PPI extraction based on a mixture of logistic models. The method automatically clusters interaction words (words that describe the interactions of protein pairs) into groups with similar grammatical properties. Logistic models are fitted for each cluster of interaction words. Directionality of interactions is an essential piece of information for many protein interactions and important for building directed biological networks. Most of current PPI extraction methods do not extract the directional information of interactions. This is in part due to the lack of specific corpora with directionality information annotated. We introduce a new corpus, PICAD, for evaluating PPI extraction tools that includes directional annotation. The corpus is available at http://stat.fsu.edu/∼jinfeng/resources/PICAD.txt. In addition, we propose an ensemble approach using logistic regression, Bayesian Networks, and SVM for identifying PPIs. We show that using an ensemble of classifiers allows us to capture different features in the text and report an F-measure of 75.7% using our new corpus.

show abstract

Bayesian inference of protein–protein interactions from biological literature

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 67 publications

References 30 publications

Interaction Relation Ontology Learning

Interaction Relation Ontology Learning

Liver Cancer Related Gene Analysis Based on Literature Mining

Mixture of logistic models and an ensemble approach for protein-protein interaction extraction

Contact Info

Product

Resources

About