Joe Townsend

Chemical documents: machine understanding and automated information extraction

Automatically extracting chemical information from documents is a challenging task, but an essential one for dealing with the vast quantity of data that is available. The task is least difficult for structured documents, such as chemistry department web pages or the output of computational chemistry programs, but requires increasingly sophisticated approaches for less structured documents, such as chemical papers. The identification of key units of information, such as chemical names, makes the extraction of useful information from unstructured documents possible.

The semantics of Chemical Markup Language (CML) for computational chemistry : CompChem

This paper introduces a subdomain chemistry format for storing computational chemistry data called CompChem. It has been developed based on the design, concepts and methodologies of Chemical Markup Language (CML) by adding computational chemistry semantics on top of the CML Schema. The format allows a wide range of ab initio quantum chemistry calculations of individual molecules to be stored. These calculations include, for example, single point energy calculation, molecular geometry optimization, and vibrational frequency analysis. The paper also describes the supporting infrastructure, such as processing software, dictionaries, validation tools and database repositories. In addition, some of the challenges and difficulties in developing common computational chemistry dictionaries are discussed. The uses of CompChem are illustrated by two practical applications.

SPECTRa-T: Machine-Based Data Extraction and Semantic Searching of Chemistry e-Theses

The SPECTRa-T project has developed text-mining tools to extract named chemical entities (NCEs), such as chemical names and terms, and chemical objects (COs), e.g., experimental spectral assignments and physical chemistry properties, from electronic theses (e-theses). Although NCEs were readily identified within the two major document formats studied, only the use of structured documents enabled identification of chemical objects and their association with the relevant chemical entity (e.g., systematic chemical name). A corpus of theses was analyzed and it is shown that a high degree of semantic information can be extracted from structured documents. This integrated information has been deposited in a persistent Resource Description Framework (RDF) triple-store that allows users to conduct semantic searches. The strength and weaknesses of several document formats are reviewed.

Ami - The chemist's amanuensis

The Ami project was a six month Rapid Innovation project sponsored by JISC to explore the Virtual Research Environment space. The project brainstormed with chemists and decided to investigate ways to facilitate monitoring and collection of experimental data.A frequently encountered use-case was identified of how the chemist reaches the end of an experiment, but finds an unexpected result. The ability to replay events can significantly help make sense of how things progressed. The project therefore concentrated on collecting a variety of dimensions of ancillary data - data that would not normally be collected due to practicality constraints. There were three main areas of investigation: 1) Development of a monitoring tool using infrared and ultrasonic sensors; 2) Time-lapse motion video capture (for example, videoing 5 seconds in every 60); and 3) Activity-driven video monitoring of the fume cupboard environs.The Ami client application was developed to control these separate logging functions. The application builds up a timeline of the events in the experiment and around the fume cupboard. The videos and data logs can then be reviewed after the experiment in order to help the chemist determine the exact timings and conditions used.The project experimented with ways in which a Microsoft Kinect could be used in a laboratory setting. Investigations suggest that it would not be an ideal device for controlling a mouse, but it shows promise for usages such as manipulating virtual molecules.

The semantic architecture of the World-Wide Molecular Matrix (WWMM)

The World-Wide Molecular Matrix (WWMM) is a ten year project to create a peer-to-peer (P2P) system for the publication and collection of chemical objects, including over 250, 000 molecules. It has now been instantiated in a number of repositories which include data encoded in Chemical Markup Language (CML) and linked by URIs and RDF. The technical specification and implementation is now complete. We discuss the types of architecture required to implement nodes in the WWMM and consider the social issues involved in adoption.

Note on naive Bayes based on binary descriptors in cheminformatics.

A plethora of articles on naive Bayes classifiers, where the chemical compounds to be classified are represented by binary-valued (absent or present type) descriptors, have appeared in the cheminformatics literature over the past decade. The principal goal of this paper is to describe how a naive Bayes classifier based on binary descriptors (NBCBBD) can be employed as a feature selector in an efficient manner suitable for cheminformatics. In the process, we point out a fact well documented in other disciplines that NBCBBD is a linear classifier and is therefore intrinsically suboptimal for classifying compounds that are nonlinearly separable in their binary descriptor space. We investigate the performance of the proposed algorithm on classifying a subset of the MDDR data set, a standard molecular benchmark data set, into active and inactive compounds.