Limits...
Protein interaction sentence detection using multiple semantic kernels.

Polajnar T, Damoulas T, Girolami M - J Biomed Semantics (2011)

Bottom Line: We show that combinations of semantic kernels lead to statistically significant improvements in recognition rates and receiver operating characteristic (ROC) scores over the plain Gaussian kernel, when applied to a well-known labelled collection of abstracts.The results from this paper indicate that using semantic information from unlabelled text, and combinations of such information, can be valuable for classification of short texts such as PPI sentences.The method described herein is modular, and can be applied with a variety of feature types, kernels, and semantic models, in order to facilitate full extraction of interacting proteins.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing Science, University of Glasgow, Glasgow, UK. tamara@dcs.gla.ac.uk.

ABSTRACT

Background: Detection of sentences that describe protein-protein interactions (PPIs) in biomedical publications is a challenging and unresolved pattern recognition problem. Many state-of-the-art approaches for this task employ kernel classification methods, in particular support vector machines (SVMs). In this work we propose a novel data integration approach that utilises semantic kernels and a kernel classification method that is a probabilistic analogue to SVMs. Semantic kernels are created from statistical information gathered from large amounts of unlabelled text using lexical semantic models. Several semantic kernels are then fused into an overall composite classification space. In this initial study, we use simple features in order to examine whether the use of combinations of kernels constructed using word-based semantic models can improve PPI sentence detection.

Results: We show that combinations of semantic kernels lead to statistically significant improvements in recognition rates and receiver operating characteristic (ROC) scores over the plain Gaussian kernel, when applied to a well-known labelled collection of abstracts. The proposed kernel composition method also allows us to automatically infer the most discriminative kernels.

Conclusions: The results from this paper indicate that using semantic information from unlabelled text, and combinations of such information, can be valuable for classification of short texts such as PPI sentences. This study, however, is only a first step in evaluation of semantic kernels and probabilistic multiple kernel learning in the context of PPI detection. The method described herein is modular, and can be applied with a variety of feature types, kernels, and semantic models, in order to facilitate full extraction of interacting proteins.

No MeSH data available.


Related in: MedlinePlus

The overview of the method. The training data (X) comes from the labelled corpus (L), while the unlabelled data (UL) is transformed using semantic models (SEM) to produce smoothing matrices (S). The training data is then projected into the semantic subspace (XS) and passed into one or more of the available kernel functions. We use cosine (κc), Gaussian (κg), and polynomial (κp) kernels. We combine the resulting kernels with a weighting βs into a single combined kernel (K).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3116455&req=5

Figure 1: The overview of the method. The training data (X) comes from the labelled corpus (L), while the unlabelled data (UL) is transformed using semantic models (SEM) to produce smoothing matrices (S). The training data is then projected into the semantic subspace (XS) and passed into one or more of the available kernel functions. We use cosine (κc), Gaussian (κg), and polynomial (κp) kernels. We combine the resulting kernels with a weighting βs into a single combined kernel (K).

Mentions: The proposed method combines labelled and unlabelled data (semi-supervised learning), by integrating semantic information from unsupervised lexical semantic models trained on a larger corpus, such as the MEDLINE abstracts contained in the GENIA corpus [41]. It is described graphically in Figure 1.


Protein interaction sentence detection using multiple semantic kernels.

Polajnar T, Damoulas T, Girolami M - J Biomed Semantics (2011)

The overview of the method. The training data (X) comes from the labelled corpus (L), while the unlabelled data (UL) is transformed using semantic models (SEM) to produce smoothing matrices (S). The training data is then projected into the semantic subspace (XS) and passed into one or more of the available kernel functions. We use cosine (κc), Gaussian (κg), and polynomial (κp) kernels. We combine the resulting kernels with a weighting βs into a single combined kernel (K).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3116455&req=5

Figure 1: The overview of the method. The training data (X) comes from the labelled corpus (L), while the unlabelled data (UL) is transformed using semantic models (SEM) to produce smoothing matrices (S). The training data is then projected into the semantic subspace (XS) and passed into one or more of the available kernel functions. We use cosine (κc), Gaussian (κg), and polynomial (κp) kernels. We combine the resulting kernels with a weighting βs into a single combined kernel (K).
Mentions: The proposed method combines labelled and unlabelled data (semi-supervised learning), by integrating semantic information from unsupervised lexical semantic models trained on a larger corpus, such as the MEDLINE abstracts contained in the GENIA corpus [41]. It is described graphically in Figure 1.

Bottom Line: We show that combinations of semantic kernels lead to statistically significant improvements in recognition rates and receiver operating characteristic (ROC) scores over the plain Gaussian kernel, when applied to a well-known labelled collection of abstracts.The results from this paper indicate that using semantic information from unlabelled text, and combinations of such information, can be valuable for classification of short texts such as PPI sentences.The method described herein is modular, and can be applied with a variety of feature types, kernels, and semantic models, in order to facilitate full extraction of interacting proteins.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing Science, University of Glasgow, Glasgow, UK. tamara@dcs.gla.ac.uk.

ABSTRACT

Background: Detection of sentences that describe protein-protein interactions (PPIs) in biomedical publications is a challenging and unresolved pattern recognition problem. Many state-of-the-art approaches for this task employ kernel classification methods, in particular support vector machines (SVMs). In this work we propose a novel data integration approach that utilises semantic kernels and a kernel classification method that is a probabilistic analogue to SVMs. Semantic kernels are created from statistical information gathered from large amounts of unlabelled text using lexical semantic models. Several semantic kernels are then fused into an overall composite classification space. In this initial study, we use simple features in order to examine whether the use of combinations of kernels constructed using word-based semantic models can improve PPI sentence detection.

Results: We show that combinations of semantic kernels lead to statistically significant improvements in recognition rates and receiver operating characteristic (ROC) scores over the plain Gaussian kernel, when applied to a well-known labelled collection of abstracts. The proposed kernel composition method also allows us to automatically infer the most discriminative kernels.

Conclusions: The results from this paper indicate that using semantic information from unlabelled text, and combinations of such information, can be valuable for classification of short texts such as PPI sentences. This study, however, is only a first step in evaluation of semantic kernels and probabilistic multiple kernel learning in the context of PPI detection. The method described herein is modular, and can be applied with a variety of feature types, kernels, and semantic models, in order to facilitate full extraction of interacting proteins.

No MeSH data available.


Related in: MedlinePlus