MedScan, a natural language processing engine for MEDLINE abstracts

Novichkova, Svetlana; Egorov, Sergei; Daraselia, Nikolai

doi:10.1093/bioinformatics/btg207

Cited by 208 publications

(141 citation statements)

References 9 publications

Supporting

Mentioning

134

Contrasting

Unclassified

Order By: Relevance

“…For this specific purpose we use the information contained in the ResNet mammalian database from Ariadne Genomics (http://www.ariadnegenomics.com/) (Novichkova et al, 2003;Daraselia et al, 2004). We selected only the interactions included in the category of Promoter Binding and Direct Regulation.…”

Section: Gene Regulatory Network Reconstructionmentioning

confidence: 99%

Global DNA methylation and transcriptional analyses of human ESC-derived cardiomyocytes

Liu

Plongthongkum³

et al. 2013

Protein Cell

View full text Add to dashboard Cite

With defined culture protocol, human embryonic stem cells (hESCs) are able to generate cardiomyocytes in vitro, therefore providing a great model for human heart development, and holding great potential for cardiac disease therapies. In this study, we successfully generated a highly pure population of human cardiomyocytes (hCMs) (>95% cTnT + ) from hESC line, which enabled us to identify and characterize an hCM-specific signature, at both the gene expression and DNA methylation levels. Gene functional association network and gene-disease network analyses of these hCM-enriched genes provide new insights into the mechanisms of hCM transcriptional regulation, and stand as an informative and rich resource for investigating cardiac gene functions and disease mechanisms. Moreover, we show that cardiac-structural genes and cardiac-transcription factors have distinct epigenetic mechanisms to regulate their gene expression, providing a better understanding of how the epigenetic machinery coordinates to regulate gene expression in different cell types.

show abstract

Section: Gene Regulatory Network Reconstructionmentioning

confidence: 99%

Global DNA methylation and transcriptional analyses of human ESC-derived cardiomyocytes

Liu

Plongthongkum³

et al. 2013

Protein Cell

View full text Add to dashboard Cite

show abstract

“…Interestingly, this information then supports secondary studies concerned with the consistency of the information [18], methods to imitate manual curation [19] and the propagation of facts in the literature [20]. Other automated approaches to the curation of pathway information include the MedScan system [21,22].…”

Section: Related Workmentioning

confidence: 75%

Infrastructure for Annotation-Driven Information Extraction from the Primary Scientific Literature: Principles and Practice

Burns

Feng

Ingulfsen

et al. 2007

2007 IEEE Congress on Services (Services 2007)

View full text Add to dashboard Cite

show abstract

“…It was observed that a F-score of 50.4% was achieved when tested on a general corpus randomly extracted from MEDLINE, which is impossible to those systems based on predefined semantic grammar rules. For example, MedScan [13] can only successfully parse and generate semantic structures for about 34% sentences randomly picked from MEDLINE. The recall rate of MedScan was found to be 21% [13].…”

Section: Resultsmentioning

confidence: 99%

“…For example, MedScan [13] can only successfully parse and generate semantic structures for about 34% sentences randomly picked from MEDLINE. The recall rate of MedScan was found to be 21% [13]. This demonstrated the robustness of the HVS model.…”

Section: Resultsmentioning

confidence: 99%

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Zhou

Kwoh

2006

Computational Science – ICCS 2006

View full text Add to dashboard Cite

Abstract. In the field of bioinformatics in solving biological problems, the huge amount of knowledge is often locked in textual documents such as scientific publications. Hence there is an increasing focus on extracting information from this vast amount of scientific literature. In this paper, we present an information extraction system which employs a semantic parser using the Hidden Vector State (HVS) model for protein-protein interactions. Unlike other hierarchical parsing models which require fully annotated treebank data for training, the HVS model can be trained using only lightly annotated data whilst simultaneously retaining sufficient ability to capture the hierarchical structure needed to robustly extract task domain semantics. When applied in extracting protein-protein interactions information from medical literature, we found that it performed better than other established statistical methods and achieved 47.9% and 72.8% in recall and precision respectively.

show abstract

MedScan, a natural language processing engine for MEDLINE abstracts

Cited by 208 publications

References 9 publications

Global DNA methylation and transcriptional analyses of human ESC-derived cardiomyocytes

Global DNA methylation and transcriptional analyses of human ESC-derived cardiomyocytes

Infrastructure for Annotation-Driven Information Extraction from the Primary Scientific Literature: Principles and Practice

Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Contact Info

Product

Resources

About