Chemical entity recognition

Chemical Entity Recognition in Chemical Structure Depictions.130... 

In an impressive body of work, researchers from IBM published on using the UIMA framework for the assembly of a complex workflow composed of services for biological, medical, and chemical entity recognition and relationship extraction. This publication is discussed in more detail in the following section. 

Much effort has been devoted toward efficient chemical text mining. A chemically intelligent tool is OSCAR4 (Open Source Chemical Analysis Routine), designed for chemistry-specific NLP [85]. It performs chemical NLP, chemical entity recognition (CER), chemical name recognition by direct lookup or ML. Its parsers... 

Dmg receptors are chemical entities which are typically, but not exclusively, small molecules that interact with cellular components, frequently at the plasma membrane level (1,2). There are many types of receptors heat, light, immune, hormone, ion channel, toxin, and vims are but a few that can excite a cell. The receptor concept can be appHed generally to signal recognition processes where a chemical or physical signal is recognized. This recognition is translated into response (Fig. 3) and the process can be seen as a flow of information. 

The complexation process is characterized by its thermodynamic and kinetic stability and selectivity, i.e. by the amount of energy and the amount of information brought into operation. Thus, conceptually, energy (interaction) and information are at the bottom of the recognition process of one chemical entity by another, and the design of molecular systems capable of forming stable and selective complexes becomes a problem in information storage and readout at the molecular level. 

Chemical systems may store information either in an analog fashion, in the structural features (size, shape, nature and disposition of interaction sites, etc. [1.27]) of a molecule or a supermolecule, or in a digital fashion, in the various states or connectivities of a chemical entity. Information theory has been applied to the description of the features of molecular machines [10.2]. The evaluation of the information content of a recognition process based on structural sensing in receptor-substrate pairs... 

As detection needs continually move to the specificity offered only by biological and chemical recognition, reactive chemical entities will play an increasingly important role. The discovery of new metallo-l,2-enedithiolates and the further study of the reactivity of these complexes is important to their potential use in detection. Much of the work described in this chapter is <5 years old, which underlies the importance of continued study. The reactivity of complexes with important analytes such as olefins (90) [see Chapter 6 in this volume (88)], oxygen, and organophosphates make metallo-l,2-enedithiolates of potential use as components in analyte detection strategies. 

Recognition of chemical entities in text (drug names, chemical descriptors, registry numbers, common and brand names, etc.)... 

Therefore, automated methods for the detection and extraction of chemical information in scientific text are required. Although chemical named entity recognition is dealt with in detail in Chapter 3 of this book, we briefly summarize the principles underlying chemical named entity recognition. We also briefly elucidate on the need for reconstruction of chemical information from chemical structure depictions, as detailed in Chapter 4. 

When discussing chemical named entity recognition, distinguishing between the different nomenclatures types used for chemical entities in text is inevitable. Basically, there are five classes ... 

---