Multiple kernel learning in protein–protein interaction extraction from biomedical literature

Yang, Zhihao; Tang, Nan; Zhang, Xiao; Lin, Hongfei; Li, Yanpeng; Yang, Zhiwei

doi:10.1016/j.artmed.2010.12.002

Cited by 42 publications

(41 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We proposed a weighted multiple kernel learning-based approach to extracting PPIs from biomedical literature [22]. The approach combines several appropriately weighed kernels, namely feature-based, convolution tree, and graph kernels, whereby the kernel with better performance is assigned higher weight.…”

Section: Ppi Extractormentioning

confidence: 99%

PPIExtractor: A protein-protein interaction Extractor for biomédical literature

Yang

Zhao

et al. 2012

2012 IEEE International Conference on Bioinformatics and Biomedicine

Self Cite

View full text Add to dashboard Cite

Knowledge about protein-protein interactions (PPIs) unveils the molecular mechanisms of biological processes. In this paper, we present a PPI extraction system, termed PPIExtractor, which automatically extracts PPIs from biomedical text and visualizes them. Given a Medline record dataset, PPIExtractor first applies Feature Coupling Generalization (FCG) to tag protein names, next uses the extended semantic similarity-based method to normalize them, then combines feature-based, convolution tree and graph kernels to extract PPIs, and finally visualizes the PPI network. Experimental evaluations show that PPIExtractor can achieve stateof-the-art performance on a DIP subset with respect to comparable evaluations. PPIExtractor is freely available for academic purposes at: http://202.118.75.18:8080/PPIExtractor/.

show abstract

Section: Ppi Extractormentioning

confidence: 99%

PPIExtractor: A protein-protein interaction Extractor for biomédical literature

Yang

Zhao

et al. 2012

2012 IEEE International Conference on Bioinformatics and Biomedicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Current methods for PPIE fall into three main categories: word co-occurrence, pattern matching and statistical machine learning [1], [2]. Compared with other methods, machine learning methods are more robust.…”

Section: Introductionmentioning

confidence: 99%

“…So far there have been many attempts to develop machine learning techniques to extract protein-protein interaction pairs. These techniques include feature vectors-based, kernel-based [1] and combination methods [2]. For example, Zhang [1] presented a weighted multiple kernels learning-based approach, which included feature-based, tree, graph and POS path kernels and achieved 64.41% F-score on AIMed, 65.84% F- score on BioInfer, 74.38% F-score on HPRD50, 75.73% Fscore on IEPA and 83.01% F-score on LLL.…”

Section: Introductionmentioning

confidence: 99%

“…These techniques include feature vectors-based, kernel-based [1] and combination methods [2]. For example, Zhang [1] presented a weighted multiple kernels learning-based approach, which included feature-based, tree, graph and POS path kernels and achieved 64.41% F-score on AIMed, 65.84% F- score on BioInfer, 74.38% F-score on HPRD50, 75.73% Fscore on IEPA and 83.01% F-score on LLL. Li [2] combined feature-based kernel, tree kernel with semantic kernel which obtained an F-score of 69.40% on AIMed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Active Transfer Learning Framework for Protein-Protein Interaction Extraction

Zheng

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY Protein-Protein Interaction Extraction (PPIE) from biomedical literatures is an important task in biomedical text mining and has achieved great success on public datasets. However, in real-world applications, the existing PPI extraction methods are limited to label effort. Therefore, transfer learning method is applied to reduce the cost of manual labeling. Current transfer learning methods suffer from negative transfer and lower performance. To tackle this problem, an improved TrAdaBoost algorithm is proposed, that is, relative distribution is introduced to initialize the weights of TrAdaBoost to overcome the negative transfer caused by domain differences. To make further improvement on the performance of transfer learning, an approach combining active learning with the improved TrAdaBoost is presented. The experimental results on publicly available PPI corpora show that our method outperforms TrAdaBoost and SVM when the labeled data is insufficient,and on document classification corpora, it also illustrates that the proposed approaches can achieve better performance than TrAdaBoost and TPTSVM in final, which verifies the effectiveness of our methods.

show abstract

“…Miwa et al (2009) proposed a method that combines bag-of-words (BOW) kernel, subset tree kernel, and graph kernel, based on several syntactic parsers, in order to retrieve the widest possible range of important information from a given sentence. Yang et al (2011) combined the following kernels: feature-based kernel, tree kernel, APG kernel and partof-speech path kernel. The combination of multiple kernels can retrieve the widest range of important information in a given sentence and achieves better performance.…”

Section: Introductionmentioning

confidence: 99%

A protein-protein interaction extraction approach based on deep neural network

Zhao

Yang

Lin

et al. 2016

IJDMB

Self Cite

View full text Add to dashboard Cite

Protein-Protein Interactions (PPIs) information extraction from biomedical literature helps unveil the molecular mechanisms of biological processes. Machine learning methods have been the most popular ones in PPI extraction area. However, these methods are still feature engineering-based, which means that their performances are also heavily dependent on the appropriate feature selection which is still a skill-dependent task. This paper presents a deep neural network-based approach which can learn complex and abstract features automatically from unlabelled data by unsupervised representation learning methods. This approach first employs the training algorithm of auto-encoders to initialise the parameters of a deep multilayer neural network. Then the gradient descent method using back propagation is applied to train this deep multilayer neural network model. Experimental results on five public PPI corpora show that our method can achieve better performance than can a multilayer neural network: on two 'toughest handling' corpora AImed and BioInfer, the former outperforms the latter with the improvements of 3.10 and 2.89 percentage units in F-score, respectively. In addition, the performance comparison with APG also verifies the effectiveness of our method.Keywords: deep learning; biomedical text mining; interaction extraction; neural network.Reference to this paper should be made as follows: Zhao, Z., Yang, Z., Lin, H., Wang, J. and Gao, S. (2016) 'A protein-protein interaction extraction approach based on deep neural network', Int.

show abstract

Multiple kernel learning in protein–protein interaction extraction from biomedical literature

Cited by 42 publications

References 18 publications

PPIExtractor: A protein-protein interaction Extractor for biomédical literature

PPIExtractor: A protein-protein interaction Extractor for biomédical literature

An Active Transfer Learning Framework for Protein-Protein Interaction Extraction

A protein-protein interaction extraction approach based on deep neural network

Contact Info

Product

Resources

About

Multiple kernel learning in protein–protein interaction extraction from biomedical literature

Cited by 42 publications

References 18 publications

PPIExtractor: A protein-protein interaction Extractor for biom&#x00E9;dical literature

PPIExtractor: A protein-protein interaction Extractor for biom&#x00E9;dical literature

An Active Transfer Learning Framework for Protein-Protein Interaction Extraction

A protein-protein interaction extraction approach based on deep neural network

Contact Info

Product

Resources

About

PPIExtractor: A protein-protein interaction Extractor for biomédical literature

PPIExtractor: A protein-protein interaction Extractor for biomédical literature