Improved Chemical Text Mining of Patents with Infinite Dictionaries and Automatic Spelling Correction

The text mining of patents of pharmaceutical interest poses a number of unique challenges not encountered in other fields of text mining. Unlike fields, such as bioinformatics, where the number of terms of interest is enumerable and essentially static, systematic chemical nomenclature can describe an infinite number of molecules. Hence, the dictionary- and ontology-based techniques that are commonly used for gene names, diseases, species, etc., have limited utility when searching for novel therapeutic compounds in patents. Additionally, the length and the composition of IUPAC-like names make them more susceptible to typographic problems: OCR failures, human spelling errors, and hyphenation and line breaking issues. This work describes a novel technique, called CaffeineFix, designed to efficiently identify chemical names in free text, even in the presence of typographical errors. Corrected chemical names are generated as input for name-to-structure software. This forms a preprocessing pass, independent of the name-to-structure software used, and is shown to greatly improve the results of chemical text mining in our study.

[1]  Michael F. Lynch,et al.  Extraction of Information from the Text of Chemical Patents. 1. Identification of Specific Chemical Names , 1998, J. Chem. Inf. Comput. Sci..

[2]  Hiroaki Wakabayashi,et al.  Predicting Key Example Compounds in Competitors' Patent Applications Using Structural Information Alone , 2008, J. Chem. Inf. Model..

[3]  Peter Murray-Rust,et al.  Chemical Name to Structure: OPSIN, an Open Source Solution , 2011, J. Chem. Inf. Model..

[4]  Bruce W. Watson,et al.  A taxonomy of algorithms for constructing minimal acyclic deterministic finite automata , 1999, South Afr. Comput. J..

[5]  Antonio Zamora,et al.  Collection and characterization of spelling errors in scientific and scholarly text , 1983, J. Am. Soc. Inf. Sci..

[6]  Roger A. Sayle.  Foreign Language Translation of Chemical Nomenclature by Computer , 2009, J. Chem. Inf. Model..

[7]  Dietrich Rebholz-Schuhmann,et al.  EBIMed - text crunching to gather facts for proteins from Medline , 2007, Bioinform..

[8]  Kemal Oflazer,et al.  Error-tolerant Finite-state Recognition with Applications to Morphological Analysis and Spelling Correction , 1995, CL.

[9]  G. H. Kirby,et al.  Computer translation of IUPAC systematic organic chemical nomenclature. 6. (Semi)automatic name correction , 1991, J. Chem. Inf. Comput. Sci..

[10]  Fred J. Damerau,et al.  A technique for computer detection and correction of spelling errors , 1964, CACM.

[11]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[12]  Antonio Zamora,et al.  Automatic spelling correction in scientific and scholarly text , 1984, CACM.

[13]  Noam Chomsky,et al.  Three models for the description of language , 1956, IRE Trans. Inf. Theory.

[14]  S. Henikoff,et al.  Amino acid substitution matrices from protein blocks. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[15]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[16]  Sorel Muresan,et al.  The Cinderella of Biological Data Integration: Addressing Some of the Challenges of Entity and Relationship Mining from Patent Sources , 2010, DILS.

[17]  Peter Murray-Rust,et al.  High-Throughput Identification of Chemistry in Life Science Texts , 2006, CompLife.

[18]  Edward Fredkin,et al.  Trie memory , 1960, Commun. ACM.

[19]  Simone Teufel,et al.  Annotation of Chemical Named Entities , 2007, BioNLP@ACL.

[20]  Yue Feng,et al.  Discovery of N-[(1S,2S)-3-(4-Chlorophenyl)-2- (3-cyanophenyl)-1-methylpropyl]-2-methyl-2- {[5-(trifluoromethyl)pyridin-2-yl]oxy}propanamide (MK-0364), a novel, acyclic cannabinoid-1 receptor inverse agonist for the treatment of obesity. , 2006, Journal of medicinal chemistry.

[21]  Gonzalo Navarro,et al.  A guided tour to approximate string matching , 2001, CSUR.

[22]  Daniel Hanisch,et al.  ProMiner: rule-based protein and gene entity recognition , 2005, BMC Bioinformatics.

[23]  James G. Nourse,et al.  Reoptimization of MDL Keys for Use in Drug Discovery , 2002, J. Chem. Inf. Comput. Sci..

[24]  Karen Kukich,et al.  Techniques for automatically correcting words in text , 1992, CSUR.

[25]  Martin Hofmann-Apitius,et al.  Detection of IUPAC and IUPAC-like chemical names , 2008, ISMB.