| |
PubViz |
An Interactive Medline Search Engine Utilizing External Knowledge |
|
Motivation: Although there are tremendous progresses in the development of Medline search functions, existing solutions are still less than ideal in providing highly efficient Medline exploration. PubViz is designed to overcome some of the limitations by taking advantage of external biomedical conceptual relationships for better information retrieval. It also provides flexible visualization functions for efficient visual queries.
|
In short, PubViz is developed to provide the capability of utilizing external knowledge as well as interactive visual query functions for more efficient exploration of the Medline database. The current version has the ability to utilize protein-protein interaction data during Medline search and enable researchers to identify functionally related Medline records not retrievable in existing search engines. It can also utilize the structure relationship of different type of genetic markers including cytobands, microsatellite/STS markers, SNPs and genes derived from human genome assembly and HapMap data for deep search of genetically related Medline records. We include many visualization functions in PubViz, such as interactive PMID, MeSH, Gene views, the transition between different views, selection of node description display on network graph, as well as details of abstract and sorting/filtering functions. The combination of these novel capabilities will make PubViz a powerful tool for Medline exploration.
(Please note: PubViz is currently development. Currently it support full Medline search only if user choose "PubMed" (one of the citation search method), but the corresponding visualization functions are still under active development.)
|
|
| |
More about PubViz and related resources |
| |
Link |
Description |
| |
|
|
| |
|
|
| |
|
|
| |
|
|
|
| |
Web serivce/Http service PubViz provides: |
| |
Service |
Description |
| |
|
GeneSearch: retrieves Medline abstracts related to specific genes. |
| |
|
MeSHSearch: retrieves most relevant Medline citations for specific MeSH terms in a user specific domain. |
| |
|
CitationSearch: retrieves Medline citations, including title, abstract, MeSH, journal, etc. |
| |
|
DiseaseSearch: retrieves Medline citations related to specific diseases. |
| |
|
GraphLayout: return graph layout results for given nodes and edges. |
| |
|
MeSHProfiling: return most significant MeSH terms that differentiate the current subset from whole Medline database. |
| |
|
GeneMapping: return identified genes in given Medline abstract and map to Entrez Gene database IDs. |
| |
|
GeneticMarkerMapping: return all genetically related markers based on linkage disequilibrium criteria. |
| |
|
UMLSMapping: return extracted UMLS concepts in Medline abstracts. |
| |
|
DiseaseAssociation: return identified diseases and mapped OMIM IDs if possible. |
| |
|
MiMIInteraction: wrap up MiMI service call, map to databases, and parse and filter results for proteins interacting with given proteins. |
| |
1) These web service or Http service were implemented for PubViz. Because of the flexible architecture of PubViz, we can quickly accommodate more external resources into our web services, and utilize them in PubViz program.
2) Many of the web services or HTTP services we are developing will also be openly available for bioinformatics developers to access programmatically, which we believe will significantly benefit the Biomedical text mining community.
|
| |
Some compiled resources: |
| |
Download |
Description |
| |
|
|
| |
|
|
| |
|
|
| |
|
|
| |
(* Corpus_BP5000 is 5000 abstracts Bipolar corpus, selected from Medline database) |
|
| PuvViz is in prototyping stage, and it is quickly evolving. |
We welcome any feedback to make it a powerful research tool that are freely available online to the Biomedical research community. |
If you have question, run into problem, or found bugs, please contact:  |
| |
| ACKNOWLEDGEMENT: |
We are members of the Pritzker Neuropsychiatric Disorders Research Consortium, which is supported by the Pritzker Neuropsychiatric Disorders Research Fund L.L.C. This work is also partly supported by the National Center for Integrated Biomedical Informatics through NIH grant 1U54DA021519-01A1. |
|
| |
|
|
