Knowledge-based expert system

Expert systems are computer programs that simulate the decision-making process of human experts. The hallmark of expert systems is that decisions are based on heuristics (rules of thumb) when data is incomplete or there is not enough time to consider all possibilities [19]. An expert system can be a set of IF-THEN rules in FORTRAN, or it can be a written in one of the languages designed for expert systems, such as LISP. Expert systems can be used off-line to aid in cure cycle selection, or they can be used as real-time advisers or controllers. 

Expert systems can also be used off-line as advisory systems. If some leeway is left in the process specifications, operators can even be instructed to make simple variations in the process. Hajicek developed an expert system for troubleshooting injection molding, which was designed to be used by operators to adjust controls as needed whenever part quality suffered [20], These expert systems do not necessarily plan an entire cycle. As we will see in the section on in-process control, however, they can be used to do so. There are even specifications that include rules for altering the cure cycle in response to the results of quality acceptance tests such as flow and volatiles, a primitive set of heuristics. 

The development of expert systems need not be costly. There are several expert system shells commercially available, and an expert in artificial intelligence (AI) is no longer needed to program them. Simple IF-THEN rules can easily be programmed in more commonly used languages like FORTRAN and BASIC. In fact, the McDonnell Aircraft expert system referred to earilier was programmed in FORTRAN. Cost depends on the number of rules and 

---

Greene N, Judson PN, Langowski JJ, Marchant CA. Knowledge-based expert systems for toxicity and metabolism prediction DEREK, StAR and METEOR. SAR QSAR Environ Res 1999 10 299-314. 

CATABOL is a knowledge-based expert system for the prediction of biotransformation pathways. It works in tandem with a probabilistic model that calculates the probabilities of the individual transformations and overall biochemical oxygen demand (BOD) and extent of C02 production (Jaworska et al., 2002). The model assesses biodegradation based on the entire pathway and not,... 

There are a number of commercial expert in silico systems available for the prediction of toxicity. Examples of knowledge-based expert systems are DEREK (Lhasa, Leeds, UK), Hazard Expert (ComGenex, San Francisco, CA, USA), Oncologic (San Francisco, CA, USA) and COMPACT (University of Surrey, Guilford, UK). Examples of statistically-based systems are MultiCASE (MultiCase, Beachwood, OH, USA),... 

Greene N, Judson PN, Langowski JJ, Marchant CA (1999) Knowledge-based expert systems for toxicity and metabolism prediction DEREK, StAR and METEOR. SAR QSAR Environ Res 10 299-314 Greene N (2002) Computer systems for the prediction of toxicity an update. Adv Drug Deliv Rev 54 417—431 Lhasa homepage http //www.chem.leeds.ac.uk/luk/... 

In silico tools make a significant contribution to the SAR-based early identification of potential toxicity. An increasing volume of published preclinical and clinical toxicity data are collected and used to build structure-related searchable databases. These expert knowledge databases can analyze chemical structures and match them with potential mechanisms of toxicity. DEREK for Windows (Lhasa Ltd.)39 is one of such broadly used knowledge-based expert systems to provide toxicology alerts for new compounds. Although certainly not comprehensive, numerous efforts have been made to predict hepatotoxicity. Recently,... 

One of the most advanced in silico predictions of any clinical liability is based on hERG QSAR and homology models6. Structural features of hERG inhibition have been discussed and published in detail, and major structural alerts are built into knowledge-based expert systems and broadly used by chemists5. Detailed information on available QSAR efforts to predict toxic effect is discussed in details elsewhere.42-43 44... 

Hansch QSAR and related approaches belong to the world of numbers conceptually, knowledge-based expert system approaches do not. Three areas of debate about expert systems have arisen from the distinction. Can you devise ways to generate qualified output from computer-based expert systems without hiding quantitative methods inside them Assuming you can, how do you validate an expert system How can you usefully combine output from different systems—some quantitative and some qualitative—to make predictions more reliable The first of the questions is more a historical than a current one some of the systems described earlier in this chapter demonstrate... 

Metabolism databases and several predictive software packages also have been reviewed.A knowledge-based expert system for the prediction of phase I and II biotransformations called META was developed on the VAX/VMS platform,META contains over 750 biotransformations based on substrnctnres and qnantnm mechanical calculations that gave excellent predictions on test data and have been optimized using a genetic algorithm to perform better than human experts.However, when used to predict the metabolism of 42 polycyclic aromatic hydrocarbons (PAHs), META overpredicted 29 and missed 8 of 72 experimentally observed epoxidations, and missed 27 of 49 experimentally observed hydroxylations. ... 

Greene, N., et al. Knowledge-Based Expert System for Toxicity and Metabolism Prediction DEREK, StAR, and METEOR, SAR QSAR, Environ. Res., 10, 299, 1997. 

---