Text Mining for Drugs and Chemical Compounds: Methods, Tools and Applications

Abstract

Providing prior knowledge about biological properties of chemicals, such as kinetic values, protein targets, or toxic effects, can facilitate many aspects of drug development. Chemical information is rapidly accumulating in all sorts of free text documents like patents, industry reports, or scientific articles, which has motivated the development of specifically tailored text mining applications. Despite the potential gains, chemical text mining still faces significant challenges. One of the most salient is the recognition of chemical entities mentioned in text. To help practitioners contribute to this area, a good portion of this review is devoted to this issue, and presents the basic concepts and principles underlying the main strategies. The technical details are introduced and accompanied by relevant bibliographic references. Other tasks discussed are retrieving relevant articles, identifying relationships between chemicals and other entities, or determining the chemical structures of chemicals mentioned in text. This review also introduces a number of published applications that can be used to build pipelines in topics like drug side effects, toxicity, and protein-disease-compound network analysis. We conclude the review with an outlook on how we expect the field to evolve, discussing its possibilities and its current limitations.

Internet Databases of the Properties, Enzymatic Reactions, and Metabolism of Small Molecules—Search Options and Applications in Food Science

“…The current state of the art in text-based searching in chemical and biomedical sciences was surveyed by Vazquez et al [65] and Gonzalez et al [66]. The solutions applied in biomedicine are appropriate for food and nutrition sciences.…”

“…Systematic (chemical) names recommended by the International Union of Pure and Applied Chemistry (IUPAC) are more accurate. They are unambiguous, and they have been developed based on well-defined rules to reflect the compound’s structure [65]. In chemical databases, compound names are presented in English.…”

LimTox: a web tool for applied text mining of adverse event and toxicity associations of compounds, drugs and genes

“…protein–protein interactions. In comparison, there are fewer text-mining systems available that focus on chemical compounds and drugs, despite the central importance of these bio-entities, not only for pharmacological and toxicological research but for biomedicine in general (1). A number of text mining efforts that tried to detect pharmacogenomics-related aspects, including the extraction of gene-drug associations, were published (2,3), and some attempts were made to extract drug–drug interactions from text (4,5).…”

GeneDive: A gene interaction search and visualization tool to facilitate precision medicine

“…Modern data mining techniques can scale to meet the challenge, and are automating the process of extracting interactions from biomedical literature. 1,9,13,15,19,20 However, the volume of extracted data is large, and the quality is mixed. These extracted interactions must thus be made accessible to curators and researchers in such a way as to facilitate analysis, curation, exploration, and discovery of well-understood and poorly-understood disease mechanisms and drug responses and, ultimately, to inform and improve patient care.…”