Chemical patent information systems

Abstract

The chemical structure information in patents remains difficult to access, partly because it is frequently expressed in the form of Markush structures, which can encompass enormous numbers of individual compounds. Early search systems were based on chemical ‘fragment codes’ that have still not been entirely superseded by the ‘topological’ systems developed during the 1980s. There are a number of databases of specific patented structures, which can be searched using standard substructure search software, and the more recently developed ones use automated data mining techniques to extract chemical nomenclature from patent text and translate it into searchable representations. Although some work has been done on automatic reconstruction of searchable Markush structures from patent text, this has proved to be considerably more refractory. A number of alternative approaches to chemical patent searching are being explored, some involving similarity and nearest‐neighbor searching concepts, and some based on both existing curated databases and direct utilization of full‐text patents. In‐house systems, which facilitate integration with other cheminformatics systems, are also under development. These new systems may allow improvements in retrieval performance, especially with regard to search precision. © 2011 John Wiley & Sons, Ltd. WIREs Comput Mol Sci 2011 1 727‐741 DOI: 10.1002/wcms.41 This article is categorized under: Computer and Information Science > Chemoinformatics

The Literature of Chemoinformatics: 1978–2018

“…For those new to the field, the best single introduction to the subject is probably the book by Leach and Gillet [40], with a more recent, but far larger, coverage being presented in two books edited by Engel and Gasteiger [41,42]. Chen [43] and Willett [44] describe the subject's historical development, and there are now many excellent reviews that provide introductions to specific topics in chemoinformatics, e.g., conformational analysis [45], data mining [46], library design [47], machine learning [48], molecular similarity [49], patent information systems [50], pharmacophore analysis [51], reaction databases [52], scaffold hopping [53], structure representations [54], text mining [55], and virtual screening [56] inter alia.…”

Cheminformatics and the Semantic Web: adding value with linked data and enhanced provenance

“…Using unique identifiers and relationships, represented as RDF triples, they create a semantic database with the potential to enrich the exploitation of the data therein. One aspect of structure searching that has yet to feel the influence of the Semantic Web is that of finding chemical structures in patents, an area recently reviewed by Downs and Barnard 52…”

SureChEMBL: a large-scale, chemically annotated patent document database

“…Undoubtedly, the continued growth in the number of published patent applications worldwide and the use of sophisticated automated text, image and data mining have opened new opportunities and challenges in the field of patent information management and searching ( 1 ). This is true especially in the context of chemical and pharmaceutical patents, where useful and accurate chemical annotation and indexing poses notable challenges ( 1 , 2 ).…”