Limits...
Discovering relations between indirectly connected biomedical concepts.

Weissenborn D, Schroeder M, Tsatsaronis G - J Biomed Semantics (2015)

Bottom Line: Towards this direction, it is necessary to combine facts in order to formulate hypotheses or draw conclusions about the domain concepts.Results suggest that relation discovery using indirect knowledge is possible, with an AUC that can reach up to 0.8, a result which is a great improvement compared to the random classification, and which shows that good predictions can be prioritized by following the suggested approach.Furthermore, this work demonstrates that the constructed graph allows for the easy integration of heterogeneous information and discovery of indirect connections between biomedical concepts.

View Article: PubMed Central - PubMed

Affiliation: DFKI Projektbüro Berlin, Alt-Moabit 91c, Berlin, 10559 Germany ; Biotechnology Center, Technische Universität Dresden, Tatzberg 47/49, Dresden, 01307 Germany.

ABSTRACT

Background: The complexity and scale of the knowledge in the biomedical domain has motivated research work towards mining heterogeneous data from both structured and unstructured knowledge bases. Towards this direction, it is necessary to combine facts in order to formulate hypotheses or draw conclusions about the domain concepts. This work addresses this problem by using indirect knowledge connecting two concepts in a knowledge graph to discover hidden relations between them. The graph represents concepts as vertices and relations as edges, stemming from structured (ontologies) and unstructured (textual) data. In this graph, path patterns, i.e. sequences of relations, are mined using distant supervision that potentially characterize a biomedical relation.

Results: It is possible to identify characteristic path patterns of biomedical relations from this representation using machine learning. For experimental evaluation two frequent biomedical relations, namely "has target", and "may treat", are chosen. Results suggest that relation discovery using indirect knowledge is possible, with an AUC that can reach up to 0.8, a result which is a great improvement compared to the random classification, and which shows that good predictions can be prioritized by following the suggested approach.

Conclusions: Analysis of the results indicates that the models can successfully learn expressive path patterns for the examined relations. Furthermore, this work demonstrates that the constructed graph allows for the easy integration of heterogeneous information and discovery of indirect connections between biomedical concepts.

No MeSH data available.


Change of classification performance using different amounts of training data. The difference in classification performance is plotted when a varying number of training examples is used for the LDA and the plain feature extraction method respectively.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4492092&req=5

Fig11: Change of classification performance using different amounts of training data. The difference in classification performance is plotted when a varying number of training examples is used for the LDA and the plain feature extraction method respectively.

Mentions: The impact of the different feature types cannot directly be inferred from Table 6. In the may treat dataset the LDA encoding seems to help a lot, but on the has target dataset, which contains about double the amount of training examples, it does not. To evaluate the impact of the different feature types, experiments with different amounts of training examples of the has target-dataset were conducted. The results were obtained using cross-validation and are presented in Figure 11.Figure 11


Discovering relations between indirectly connected biomedical concepts.

Weissenborn D, Schroeder M, Tsatsaronis G - J Biomed Semantics (2015)

Change of classification performance using different amounts of training data. The difference in classification performance is plotted when a varying number of training examples is used for the LDA and the plain feature extraction method respectively.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4492092&req=5

Fig11: Change of classification performance using different amounts of training data. The difference in classification performance is plotted when a varying number of training examples is used for the LDA and the plain feature extraction method respectively.
Mentions: The impact of the different feature types cannot directly be inferred from Table 6. In the may treat dataset the LDA encoding seems to help a lot, but on the has target dataset, which contains about double the amount of training examples, it does not. To evaluate the impact of the different feature types, experiments with different amounts of training examples of the has target-dataset were conducted. The results were obtained using cross-validation and are presented in Figure 11.Figure 11

Bottom Line: Towards this direction, it is necessary to combine facts in order to formulate hypotheses or draw conclusions about the domain concepts.Results suggest that relation discovery using indirect knowledge is possible, with an AUC that can reach up to 0.8, a result which is a great improvement compared to the random classification, and which shows that good predictions can be prioritized by following the suggested approach.Furthermore, this work demonstrates that the constructed graph allows for the easy integration of heterogeneous information and discovery of indirect connections between biomedical concepts.

View Article: PubMed Central - PubMed

Affiliation: DFKI Projektbüro Berlin, Alt-Moabit 91c, Berlin, 10559 Germany ; Biotechnology Center, Technische Universität Dresden, Tatzberg 47/49, Dresden, 01307 Germany.

ABSTRACT

Background: The complexity and scale of the knowledge in the biomedical domain has motivated research work towards mining heterogeneous data from both structured and unstructured knowledge bases. Towards this direction, it is necessary to combine facts in order to formulate hypotheses or draw conclusions about the domain concepts. This work addresses this problem by using indirect knowledge connecting two concepts in a knowledge graph to discover hidden relations between them. The graph represents concepts as vertices and relations as edges, stemming from structured (ontologies) and unstructured (textual) data. In this graph, path patterns, i.e. sequences of relations, are mined using distant supervision that potentially characterize a biomedical relation.

Results: It is possible to identify characteristic path patterns of biomedical relations from this representation using machine learning. For experimental evaluation two frequent biomedical relations, namely "has target", and "may treat", are chosen. Results suggest that relation discovery using indirect knowledge is possible, with an AUC that can reach up to 0.8, a result which is a great improvement compared to the random classification, and which shows that good predictions can be prioritized by following the suggested approach.

Conclusions: Analysis of the results indicates that the models can successfully learn expressive path patterns for the examined relations. Furthermore, this work demonstrates that the constructed graph allows for the easy integration of heterogeneous information and discovery of indirect connections between biomedical concepts.

No MeSH data available.