Expert systems: empirical rules

Foulkes et al. (1988) have approached the synthesis of operating procedures from a more empirical angle. They have extended the work of Rivas and Rudd (1974) for the synthesis of complex pump and valve sequencing operations, relying on the use of logical propositions (implemented as rule-based expert systems), which capture the various types of constraints imposed on the states of a processing system. 

There is some disagreement within the AI community as to what qualifies a computer program to be called an "expert system". We use the term to describe a program which has the following characteristics 1) The program performs some task (e.g., HPLC methods design) which requires specialized human expertise. This human expertise often takes the form of heuristics (empirical rules of... 

Computational approaches to predict toxicity are based on expert systems containing empirical or computationally derived rules, typically encoded via structural fragments that potentially could cause toxicity." " ... 

Peter Politakis PhD thesis entitled "Empirical Analysis for Expert Systems" (26) is an excellent introduction to the subject of expert systems V V. Politakis and Weiss (27) cover the use of case experience to refine the rules of a model in a medical diagnostics system. 

The purpose of a chemical expert system is to provide fast, easy, efficient and effective access to chemical information and knowledge in a specific domain of expertise, via computer-representation of integrated reference data, theoretical and empirical knowledge (e.g., in the form of rules ), system models and reasoning mechanisms. An expert system should not only contain (integrated) relevant hard facts (e.g., numerical correlations and statistics) but also the expertise ( soft knowledge ) of experienced specialists in the field. For structure elucidation of organic molecules various spectrometric methods are available. In many cases different methods such as mass, infra-red, NMR and ultra-violet spectroscopy provide complementary structural information. This is one of the basic elements of EXSPEC, an expert system for computer-aided interpretation of combined spectral data. ... 

As with the simple example of benzene, there are many ways to modify an API s structure. Well-established test systems, empirical data, rules of thumb " (Figure 7.2) and computer-based systems for the assessment of the properties of molecules, such as biodegradability, are available. Their careful combination allows for the theoretical design of molecules and the assessment of their properties without the need for them to be synthesized. Computer-based systems that assist human experts with the handling of complex knowledge are widely in use within pharmaceutical industries for the optimization of APIs by in silico screening.This allows for a very early and comparatively inexpensive evaluation of the environmental properties of candidates. At the same time, undesirable properties such as mutagenicity can be reduced. This can and should also be done with respect to full mineralization of APIs when they reach the environment. 

There are two major approaches to de novo sequencing by mass spectrometry. The first one is based on a number of empirical rules obtained by observing typical peptide fragmentation schemes [20]. Current versions of this approach rely on computerized expert systems that are built on the dozens of empirical rules and factors. These include general observations on the prevalence of certain fragments in spectra produced by the used fragmentation methods and in typical instruments. For example, CAD is known to produce predominantly y- and fc-type ions. There... 

---