Limits...
Mining semantic networks of bioinformatics e-resources from the literature.

Afzal H, Eales J, Stevens R, Nenadic G - J Biomed Semantics (2011)

Bottom Line: These efforts rely on manual curation, making it difficult to cope with the huge influx of various electronic resources that have been provided by the bioinformatics community.Since such representations are typically sparse (on average 13.77 features per resource), we used lexical kernel metrics to identify semantically related resources via descriptor smoothing.Resources are then clustered or linked into semantic networks, providing the users (bioinformaticians, curators and service/tool crawlers) with a possibility to explore algorithms, tools, services and datasets based on their relatedness.

View Article: PubMed Central - HTML - PubMed

Affiliation: College of Telecommunication Engineering, National University of Sciences and Technology, Islamabad, Pakistan. Hammad.Afzal@deri.org.

ABSTRACT

Background: There have been a number of recent efforts (e.g. BioCatalogue, BioMoby) to systematically catalogue bioinformatics tools, services and datasets. These efforts rely on manual curation, making it difficult to cope with the huge influx of various electronic resources that have been provided by the bioinformatics community. We present a text mining approach that utilises the literature to automatically extract descriptions and semantically profile bioinformatics resources to make them available for resource discovery and exploration through semantic networks that contain related resources.

Results: The method identifies the mentions of resources in the literature and assigns a set of co-occurring terminological entities (descriptors) to represent them. We have processed 2,691 full-text bioinformatics articles and extracted profiles of 12,452 resources containing associated descriptors with binary and tf*idf weights. Since such representations are typically sparse (on average 13.77 features per resource), we used lexical kernel metrics to identify semantically related resources via descriptor smoothing. Resources are then clustered or linked into semantic networks, providing the users (bioinformaticians, curators and service/tool crawlers) with a possibility to explore algorithms, tools, services and datasets based on their relatedness. Manual exploration of links between a set of 18 well-known bioinformatics resources suggests that the method was able to identify and group semantically related entities.

Conclusions: The results have shown that the method can reconstruct interesting functional links between resources (e.g. linking data types and algorithms), in particular when tf*idf-like weights are used for profiling. This demonstrates the potential of combining literature mining and simple lexical kernel methods to model relatedness between resource descriptors in particular when there are few features, thus potentially improving the resource description, discovery and exploration process. The resource profiles are available at http://gnode1.mib.man.ac.uk/bioinf/semnets.html.

No MeSH data available.


Related in: MedlinePlus

Hierarchical clustering of e-resources using the shared descriptors similarity matrix (method 2). (A) The scores based on binary weights. (B) The scores based on tf*idf. Distances were calculated as (1 – Sim2). Ward’s minimum variance clustering method [21] was used to cluster the data. The tree was generated using R function ‘hclust’ [20].
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3105496&req=5

Figure 5: Hierarchical clustering of e-resources using the shared descriptors similarity matrix (method 2). (A) The scores based on binary weights. (B) The scores based on tf*idf. Distances were calculated as (1 – Sim2). Ward’s minimum variance clustering method [21] was used to cluster the data. The tree was generated using R function ‘hclust’ [20].

Mentions: To further highlight the subtle differences and similarities between the resources in the sample, we applied a hierarchical clustering algorithm [21] to the two matrices of scores. The tree in Figure 5A highlights some interesting clusters of the examined resources when only binary indication of descriptors’ presence was used. Binary weights provided a spread of similarity scores, which better suited hierarchical clustering. In the resulting dendrogram, many resources have been grouped together based on their class (e.g. PCA and MCMC are algorithms; COG and PDB are data resources as well as KEGG and MeSH). However, the cluster of pairwise alignment and HMM highlights the semantic theme of sequence analysis. It is interesting that BLAST was not linked to these, while it makes a protein-related cluster with COG, SCOP and PDB. Furthermore, KEGG, BLAST, COG, SCOP, PDB and MeSH form their own group, which does not highlight any obvious semantic relationships; a likely reason is that these resources represent very common and fundamental resources in bioinformatics, so share quite a large group of generic descriptors.


Mining semantic networks of bioinformatics e-resources from the literature.

Afzal H, Eales J, Stevens R, Nenadic G - J Biomed Semantics (2011)

Hierarchical clustering of e-resources using the shared descriptors similarity matrix (method 2). (A) The scores based on binary weights. (B) The scores based on tf*idf. Distances were calculated as (1 – Sim2). Ward’s minimum variance clustering method [21] was used to cluster the data. The tree was generated using R function ‘hclust’ [20].
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3105496&req=5

Figure 5: Hierarchical clustering of e-resources using the shared descriptors similarity matrix (method 2). (A) The scores based on binary weights. (B) The scores based on tf*idf. Distances were calculated as (1 – Sim2). Ward’s minimum variance clustering method [21] was used to cluster the data. The tree was generated using R function ‘hclust’ [20].
Mentions: To further highlight the subtle differences and similarities between the resources in the sample, we applied a hierarchical clustering algorithm [21] to the two matrices of scores. The tree in Figure 5A highlights some interesting clusters of the examined resources when only binary indication of descriptors’ presence was used. Binary weights provided a spread of similarity scores, which better suited hierarchical clustering. In the resulting dendrogram, many resources have been grouped together based on their class (e.g. PCA and MCMC are algorithms; COG and PDB are data resources as well as KEGG and MeSH). However, the cluster of pairwise alignment and HMM highlights the semantic theme of sequence analysis. It is interesting that BLAST was not linked to these, while it makes a protein-related cluster with COG, SCOP and PDB. Furthermore, KEGG, BLAST, COG, SCOP, PDB and MeSH form their own group, which does not highlight any obvious semantic relationships; a likely reason is that these resources represent very common and fundamental resources in bioinformatics, so share quite a large group of generic descriptors.

Bottom Line: These efforts rely on manual curation, making it difficult to cope with the huge influx of various electronic resources that have been provided by the bioinformatics community.Since such representations are typically sparse (on average 13.77 features per resource), we used lexical kernel metrics to identify semantically related resources via descriptor smoothing.Resources are then clustered or linked into semantic networks, providing the users (bioinformaticians, curators and service/tool crawlers) with a possibility to explore algorithms, tools, services and datasets based on their relatedness.

View Article: PubMed Central - HTML - PubMed

Affiliation: College of Telecommunication Engineering, National University of Sciences and Technology, Islamabad, Pakistan. Hammad.Afzal@deri.org.

ABSTRACT

Background: There have been a number of recent efforts (e.g. BioCatalogue, BioMoby) to systematically catalogue bioinformatics tools, services and datasets. These efforts rely on manual curation, making it difficult to cope with the huge influx of various electronic resources that have been provided by the bioinformatics community. We present a text mining approach that utilises the literature to automatically extract descriptions and semantically profile bioinformatics resources to make them available for resource discovery and exploration through semantic networks that contain related resources.

Results: The method identifies the mentions of resources in the literature and assigns a set of co-occurring terminological entities (descriptors) to represent them. We have processed 2,691 full-text bioinformatics articles and extracted profiles of 12,452 resources containing associated descriptors with binary and tf*idf weights. Since such representations are typically sparse (on average 13.77 features per resource), we used lexical kernel metrics to identify semantically related resources via descriptor smoothing. Resources are then clustered or linked into semantic networks, providing the users (bioinformaticians, curators and service/tool crawlers) with a possibility to explore algorithms, tools, services and datasets based on their relatedness. Manual exploration of links between a set of 18 well-known bioinformatics resources suggests that the method was able to identify and group semantically related entities.

Conclusions: The results have shown that the method can reconstruct interesting functional links between resources (e.g. linking data types and algorithms), in particular when tf*idf-like weights are used for profiling. This demonstrates the potential of combining literature mining and simple lexical kernel methods to model relatedness between resource descriptors in particular when there are few features, thus potentially improving the resource description, discovery and exploration process. The resource profiles are available at http://gnode1.mib.man.ac.uk/bioinf/semnets.html.

No MeSH data available.


Related in: MedlinePlus