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.


An example of a dependency tree of a sentence. The dependency tree of the following sentence is illustrated: “Aspirin is used in the treatment of inflammation and not nasal polyps”.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig3: An example of a dependency tree of a sentence. The dependency tree of the following sentence is illustrated: “Aspirin is used in the treatment of inflammation and not nasal polyps”.

Mentions: Dependency trees [13] are syntactic constructs of sentences in which each node of the tree represents a token (word or symbol) of the underlying sentence and each arch represents a dependency between two tokens of that sentence. In dependency grammars (DG) the verb always takes the central role of the sentence and is therefore always the root of the tree independent from the rest. Furthermore DGs do not require any ordering of the sentence words and are thus also applicable to languages in which the order of words in a sentence is all the same (e.g., in Czech or Turkish). Unlike phrase structure grammars (constituency grammars) DGs do not explicitly structure sentences into phrases but rely only on dependencies between words in a sentence [14]. An example of a dependency tree is shown in Figure 3.Figure 3


Discovering relations between indirectly connected biomedical concepts.

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

An example of a dependency tree of a sentence. The dependency tree of the following sentence is illustrated: “Aspirin is used in the treatment of inflammation and not nasal polyps”.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Fig3: An example of a dependency tree of a sentence. The dependency tree of the following sentence is illustrated: “Aspirin is used in the treatment of inflammation and not nasal polyps”.
Mentions: Dependency trees [13] are syntactic constructs of sentences in which each node of the tree represents a token (word or symbol) of the underlying sentence and each arch represents a dependency between two tokens of that sentence. In dependency grammars (DG) the verb always takes the central role of the sentence and is therefore always the root of the tree independent from the rest. Furthermore DGs do not require any ordering of the sentence words and are thus also applicable to languages in which the order of words in a sentence is all the same (e.g., in Czech or Turkish). Unlike phrase structure grammars (constituency grammars) DGs do not explicitly structure sentences into phrases but rely only on dependencies between words in a sentence [14]. An example of a dependency tree is shown in Figure 3.Figure 3

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.