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.
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.
We plan to publish the corpora, annotation guideline as well as the conditional random field model as a UIMA component.
UniChem is a low-maintenance, fast and freely available compound identifier mapping service, recently made available on the Internet. Until now, the criterion of molecular equivalence within UniChem has been on the basis of complete identity between Standard InChIs. However, a limitation of this approach is that stereoisomers, isotopes and salts of otherwise identical molecules are not considered as related. Here, we describe how we have exploited the layered structural representation of the Standard InChI to create new functionality within UniChem that integrates these related
molecular forms. The service, called ‘Connectivity Search’ allows molecules to be first matched on the basis of complete identity between the connectivity layer of their corresponding Standard InChIs, and the remaining layers then compared to highlight stereochemical and isotopic differences. Parsing of Standard InChI sub-layers permits mixtures and salts to also be included in this integration process. Implementation of these enhancements required simple modifications to the schema, loader and web application, but none of which have changed the original UniChem functionality or services. The scope of queries may be varied using a variety of easily configurable options, and the output is annotated to assist the user to filter, sort and understand the difference between query and retrieved structures. A RESTful web service output may be easily processed programmatically to allow developers to present the data in whatever form they believe their users will require, or to define their own level of molecular equivalence for their resource, albeit within the constraint of identical connectivity.
Learn about technology that solves the issue of interpreting 3D stereochemical information implied in 2D structure representations.
The InChI algorithms are written in C++ and not available as Java library. Integration into software written in Java therefore requires a bridge between C and Java libraries, provided by the Java Native Interface (JNI) technology.
We here describe how the InChI library is used in the Bioclipse workbench and the Chemistry Development Kit (CDK) cheminformatics library. To make this possible, a JNI bridge to the InChI library was developed, JNI-InChI, allowing Java software to access the InChI algorithms. By using this bridge, the CDK project packages the InChI binaries in a module and offers easy access from Java using the CDK API. The Bioclipse project packages and offers InChI as a dynamic OSGi bundle that can easily be used by any OSGi-compliant software, in addition to the regular Java Archive and Maven bundles. Bioclipse itself uses the InChI as a key component and calculates it on the fly when visualizing and editing chemical structures. We demonstrate the utility of InChI with various applications in CDK and Bioclipse, such as decision support for chemical liability assessment, tautomer generation, and for knowledge aggregation using a linked data approach.
These results show that the InChI library can be used in a variety of Java library dependency solutions, making the functionality easily accessible by Java software, such as in the CDK. The applications show various ways the InChI has been used in Bioclipse, to enrich its functionality.
InChI, InChIKey, Chemical structures, JNI-InChI, The Chemistry Development Kit, OSGi, Bioclipse, Decision
support, Linked data, Tautomers, Databases, Semantic web
The HIV structural database (HIVSDB) is a comprehensive collection of the structures of HIV protease, both of unliganded enzyme and of its inhibitor complexes. It contains abstracts and crystallographic data such as inhibitor and protein coordinates for 248 data sets, of which only 141 are from the Protein Data Bank (PDB). Efficient annotation, indexing, and querying of the inhibitor data is crucial for their effective use for technological and industrial applications. The application of IUPAC International Chemical Identifier (InChI) to index, curate, and query inhibitor structures HIVSDB is described. Proteins 2005. Published 2005 Wiley‐Liss, Inc.
This presentation is a part of Google Tech Talks which was added to the GoogleTalksArchive on August 22, 2006. The original presentation date took place on November 2, 2006.
ABSTRACT (Imported From YouTube Source)
The central token of information in Chemistry is a chemical substance, an entity that can often be represented as a well-defined chemical structure. With InChI we have a means of representing this entity as a unique string of characters, which is otherwise represented by various of 2-D and 3-D chemical drawings, ‘connection tables’ and synonyms. InChI therefore represents a discrete physical entity, to which is associated as array of chemical properties and data. NIST has long been involved in disseminating chemical reference data associated with such discrete substances. A InChI is therefore the key index to this data. Many other types of data and information are also naturally tied to it, including biological information, commercial availability, toxicity, drug effectiveness and so forth. Because of the diversity of properties and interactions of a chemical substance, effective location of chemical information generally requires further qualifiers, which may be represented coarsely as a key word, but more precisely using a controlled vocabulary. There are no simple separations between information sought by difference disciplines and for different objectives. However, reference data may be organized according the disciplines most directly involved in making the measurements: -isolated substance – mass, infrared, NMR, spectra; physical properties -substance in the context of others – solubility, affinity, .. -properties of a mixture containing the substance The desired data can be a number, vector or image, usually associated with dimensions and links to source information. In some cases, this information is typically converted to a curve or diagram for use by an expert and may be further processed by specialized software. In other cases, a single numerical values is the target. Also, some complexities of structure that must be dealt with in practical search is represented in InChI, but must be decoded for use in searching.