de
en
Schliessen
Detailsuche
Bibliotheken
Projekt
Impressum
Datenschutz
zum Inhalt
Detailsuche
Schnellsuche:
OK
Ergebnisliste
Titel
Titel
Inhalt
Inhalt
Seite
Seite
Im Dokument suchen
ter Horst, Hendrik: Ranking of disease gene associations from large corpora of scientific publications. 2015
Inhalt
Abstract
1 Introduction
1.1 Motivation
1.2 Goals And Contributions
1.3 Outline
2 Related Work
3 Materials
3.1 The Investigated Corpora PubMed
3.2 Data for Entity Disambiguation
3.3 Gold Standards
4 System Architecture
4.1 Information Extraction
4.2 Data Conversion
4.3 Data Storage and Supply
4.4 Gene Ranking System
5 Approach and Resource Generation
5.1 Disease Recognition and Normalization
5.1.1 Disease Mention Recognition
5.1.2 Disease Surface Form Normalization using DiNo
5.2 Extraction of Gene Interaction Events and Gene Normalization
5.2.1 Gene Event Recognition
5.2.2 Gene Surface Form Normalization
5.3 Gene-Interaction Network
5.3.1 Graph Construction and Transformation
5.3.2 Extraction of Path Signatures
5.4 The Graph Database
5.4.1 Blazegraph
5.4.2 Population of the Database
5.5 Feature Extraction
5.5.1 Co-occurrences Based Features
5.5.2 Gene Interaction Based Features
5.5.3 The Feature Vector
5.6 Summary
6 Experiments and Evaluation
6.1 Classification of Genes Candidates
6.1.1 Methods and Experimental Setup
6.1.2 Evaluation Results and Discussion
6.2 Ranking of Gene Candidates
6.2.1 Methods and Experimental Setup
6.2.2 Evaluation Results and Discussion
6.3 Case Study with Pulmonary Fibrosis
7 Conclusion
Bibliography