@InProceedings{neglur05assigning,
  author    = {Neglur, Greeshma and Grossman, Robert L. and Liu, Bing},
  booktitle = {Data Integration in the Life Sciences},
  title     = {Assigning Unique Keys to Chemical Compounds for Data Integration: Some Interesting Counter Examples},
  year      = {2005},
  address   = {Berlin, Heidelberg},
  editor    = {Lud{\"a}scher, Bertram and Raschid, Louiqa},
  pages     = {145--157},
  publisher = {Springer},
  abstract  = {Integrating data involving chemical structures is simplified when unique identifiers (UIDs) can be associated with chemical structures. For example, these identifiers can be used as database keys. One common approach is to use the Unique SMILES notation introduced in [2]. The Unique SMILES views a chemical structure as a graph with atoms as nodes and bonds as edges and uses a depth first traversal of the graph to generate the SMILES strings. The algorithm establishes a node ordering by using certain symmetry properties of the graphs. In this paper, we present certain molecular graphs for which the algorithm fails to generate UIDs. Indeed, we show that different graphs in the same symmetry class employed by the Unique SMILES algorithm have different Unique SMILES IDs. We tested the algorithm on the National Cancer Institute (NCI) database [7] and found several molecular structures for which the algorithm also failed. We have also written a python script that generates molecular graphs for which the algorithm fails.},
  isbn      = {978-3-540-31879-8},
}

{"_id":"HKohheE3KMnRPcFk2","bibbaseid":"neglur-grossman-liu-assigninguniquekeystochemicalcompoundsfordataintegrationsomeinterestingcounterexamples-2005","authorIDs":[],"author_short":["Neglur, G.","Grossman, R. L.","Liu, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Neglur"],"firstnames":["Greeshma"],"suffixes":[]},{"propositions":[],"lastnames":["Grossman"],"firstnames":["Robert","L."],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Bing"],"suffixes":[]}],"booktitle":"Data Integration in the Life Sciences","title":"Assigning Unique Keys to Chemical Compounds for Data Integration: Some Interesting Counter Examples","year":"2005","address":"Berlin, Heidelberg","editor":[{"propositions":[],"lastnames":["Ludäscher"],"firstnames":["Bertram"],"suffixes":[]},{"propositions":[],"lastnames":["Raschid"],"firstnames":["Louiqa"],"suffixes":[]}],"pages":"145–157","publisher":"Springer","abstract":"Integrating data involving chemical structures is simplified when unique identifiers (UIDs) can be associated with chemical structures. For example, these identifiers can be used as database keys. One common approach is to use the Unique SMILES notation introduced in [2]. The Unique SMILES views a chemical structure as a graph with atoms as nodes and bonds as edges and uses a depth first traversal of the graph to generate the SMILES strings. The algorithm establishes a node ordering by using certain symmetry properties of the graphs. In this paper, we present certain molecular graphs for which the algorithm fails to generate UIDs. Indeed, we show that different graphs in the same symmetry class employed by the Unique SMILES algorithm have different Unique SMILES IDs. We tested the algorithm on the National Cancer Institute (NCI) database [7] and found several molecular structures for which the algorithm also failed. We have also written a python script that generates molecular graphs for which the algorithm fails.","isbn":"978-3-540-31879-8","bibtex":"@InProceedings{neglur05assigning,\n author = {Neglur, Greeshma and Grossman, Robert L. and Liu, Bing},\n booktitle = {Data Integration in the Life Sciences},\n title = {Assigning Unique Keys to Chemical Compounds for Data Integration: Some Interesting Counter Examples},\n year = {2005},\n address = {Berlin, Heidelberg},\n editor = {Lud{\\\"a}scher, Bertram and Raschid, Louiqa},\n pages = {145--157},\n publisher = {Springer},\n abstract = {Integrating data involving chemical structures is simplified when unique identifiers (UIDs) can be associated with chemical structures. For example, these identifiers can be used as database keys. One common approach is to use the Unique SMILES notation introduced in [2]. The Unique SMILES views a chemical structure as a graph with atoms as nodes and bonds as edges and uses a depth first traversal of the graph to generate the SMILES strings. The algorithm establishes a node ordering by using certain symmetry properties of the graphs. In this paper, we present certain molecular graphs for which the algorithm fails to generate UIDs. Indeed, we show that different graphs in the same symmetry class employed by the Unique SMILES algorithm have different Unique SMILES IDs. We tested the algorithm on the National Cancer Institute (NCI) database [7] and found several molecular structures for which the algorithm also failed. We have also written a python script that generates molecular graphs for which the algorithm fails.},\n isbn = {978-3-540-31879-8},\n}\n\n","author_short":["Neglur, G.","Grossman, R. L.","Liu, B."],"editor_short":["Ludäscher, B.","Raschid, L."],"key":"neglur05assigning","id":"neglur05assigning","bibbaseid":"neglur-grossman-liu-assigninguniquekeystochemicalcompoundsfordataintegrationsomeinterestingcounterexamples-2005","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://git.bio.informatik.uni-jena.de/fleisch/literature/raw/master/group-literature.bib","creationDate":"2020-08-07T09:43:58.772Z","downloads":0,"keywords":[],"search_terms":["assigning","unique","keys","chemical","compounds","data","integration","interesting","counter","examples","neglur","grossman","liu"],"title":"Assigning Unique Keys to Chemical Compounds for Data Integration: Some Interesting Counter Examples","year":2005,"dataSources":["C5FtkvWWggFfMJTFX"]}