Background: Identification of gene and protein names in biomedical text is a challenging task as the corresponding nomenclature has evolved over time. This has led to multiple synonyms for individual genes and proteins, as well as names that may be ambiguous with other gene names or with general English words. The Gene List Task of the BioCreAtIvE challenge evaluation enables comparison of systems addressing the problem of protein and gene name identification on common benchmark data. Methods: The ProMiner system uses a pre-processed synonym dictionary to identify potential name occurrences in the biomedical text and associate protein and gene database identifiers with the detected matches. It follows a rule-based approach and its search algorithm is geared towards recognition of multi-word names [1]. To account for the large number of ambiguous synonyms in the considered organisms, the system has been extended to use specific variants of the detection procedure for highly ambiguous and case-sensitive synonyms. Based on all detected synonyms for one abstract, the most plausible database identifiers are associated with the text. Organism specificity is addressed by a simple procedure based on additionally detected organism names in an Results: The extended ProMiner system has been applied to the test cases of the BioCreAtIvE competition with highly encouraging results. In blind predictions, the system achieved an F-measure of approximately 0.8 for the organisms mouse and fly and about 0.9 for the organism yeast.

Background: The goal of the gene normalization task is to link genes or gene products mentioned in the literature to biological databases. This is a key step in an accurate search of the biological literature. It is a challenging task, even for the human expert; genes are often described rather than referred to by gene symbol and, confusingly, one gene name may refer to different genes (often from different organisms). For BioCreative II, the task was to list the Entrez Gene identifiers for human genes or gene products mentioned in PubMed/MEDLINE abstracts. We selected abstracts associated with articles previously curated for human genes. We provided 281 expert-annotated abstracts containing 684 gene identifiers for training, and a blind test set of 262 documents containing 785 identifiers, with a gold standard created by expert annotators. Inter-annotator agreement was measured at over 90%. Results: Twenty groups submitted one to three runs each, for a total of 54 runs. Three systems achieved F-measures (balanced precision and recall) between 0.80 and 0.81. Combining the system outputs using simple voting schemes and classifiers obtained improved results; the best composite system achieved an F-measure of 0.92 with 10-fold cross-validation. A 'maximum recall' system based on the pooled responses of all participants gave a recall of 0.97 (with precision 0.23), identifying 763 out of 785 identifiers. Conclusion: Major advances for the BioCreative II gene normalization task include broader participation (20 versus 8 teams) and a pooled system performance comparable to human experts, at over 90% agreement. These results show promise as tools to link the literature with biological databases.

Motivation: Chemical compounds like small signal molecules or other biological active chemical substances are an important entity class in life science publications and patents. Several representations and nomenclatures for chemicals like SMILES, InChI, IUPAC or trivial names exist. Only SMILES and InChI names allow a direct structure search, but in biomedical texts trivial names and Iupac like names are used more frequent. While trivial names can be found with a dictionary-based approach and in such a way mapped to their corresponding structures, it is not possible to enumerate all IUPAC names. In this work, we present a new machine learning approach based on conditional random fields (CRF) to find mentions of IUPAC and IUPAC-like names in scientific text as well as its evaluation and the conversion rate with available name-to-structure tools. Results: We present an IUPAC name recognizer with an F₁ measure of 85.6% on a MEDLINE corpus. The evaluation of different CRF orders and offset conjunction orders demonstrates the importance of these parameters. An evaluation of hand-selected patent sections containing large enumerations and terms with mixed nomenclature shows a good performance on these cases (F₁ measure 81.5%). Remaining recognition problems are to detect correct borders of the typically long terms, especially when occurring in parentheses or enumerations. We demonstrate the scalability of our implementation by providing results from a full MEDLINE run. Availability: We plan to publish the corpora, annotation guideline as well as the conditional random field model as a UIMA component. Contact: roman.klinger@scai.fraunhofer.de