Knowledge-Based Expert Systems in Chemistry: Not Counting on Computers (RSC Theoretical and Computational Chemistry, 1) - Hardcover

Judson, Phillip

Hardcover

ISBN 10: 0854041605 ISBN 13: 9780854041602

Verlag: Royal Society of Chemistry, 2009

Inhaltsangabe

This is currently the only book available on the development of knowledge-based, and related, expert systems in chemistry and toxicology. Written by a pioneer in the field, it shows how computers can work with qualitative information where precise numerical methods are not satisfactory. An underlying theme is the current concern in society about the conflicts between basing decisions on reasoned judgements and wanting precise decisions and measurable effectiveness. As well as explaining how the computer programs work, the book provides insights into how personal and political factors influence scientific progress. The introduction of regulations such as REACH in Europe and modifications to UN and OECD Guidelines on assessment of chemical hazard mean that the use of toxicity prediction is at a turning point. They put a heavy burden on the chemical industry but, for the first time, allow for the use of computer prediction to support or replace in vivo and in vitro experiments. There is increasing recognition among scientists and regulators that qualitative computer methods have much to offer and that in some circumstances they may be more reliable and informative than quantitative methods. This excellent introduction to a field where employment opportunities are growing is aimed at students, scientists and academics with a knowledge of chemistry.

Über diesen Titel

Über die Autorinnen und Autoren

Philip Judson studied chemistry at the University of Manchester before working on the synthesis of novel herbicides and fungicides for Fisons. When computing started being used in chemistry he made a change of career which later led to his becoming Head of Chemical Information and Computing for Schering AG. He was one of the founders of Lhasa Limited, a not-for-profit company specialising in knowledge-based expert systems in chemistry including the widely-used Derek for Windows system for predicting chemical toxicity. His research interests centre on the use of non-numerical reasoning methods for computer prediction of chemical toxicity, metabolism, and degradation. He developed and maintains software for chemical hazard classification and material safety data sheet management which are supplied by his company, Lexeus Limited.

Philip Judson studied chemistry at the University of Manchester before working on the synthesis of novel herbicides and fungicides for Fisons. When computing started being used in chemistry he made a change of career which later led to his becoming Head of Chemical Information and Computing for Schering AG. He was one of the founders of Lhasa Limited, a not-for-profit company specialising in knowledge-based expert systems in chemistry including the widely-used Derek for Windows system for predicting chemical toxicity. His research interests centre on the use of non-numerical reasoning methods for computer prediction of chemical toxicity, metabolism, and degradation. He developed and maintains software for chemical hazard classification and material safety data sheet management which are supplied by his company, Lexeus Limited.

Von der hinteren Coverseite

This is currently the only book available on the development of knowledge-based, and related, expert systems in chemistry and toxicology. Written by a pioneer in the field, it shows how computers can work with qualitative information where precise numerical methods are not satisfactory. An underlying theme is the current concern in society about the conflicts between basing decisions on reasoned judgements and wanting precise decisions and measurable effectiveness. As well as explaining how the computer programs work, the book provides insights into how personal and political factors influence scientific progress. The introduction of regulations such as REACH in Europe and modifications to UN and OECD Guidelines on assessment of chemical hazard mean that the use of toxicity prediction is at a turning point. They put a heavy burden on the chemical industry but, for the first time, allow for the use of computer prediction to support or replace in vivo and in vitro experiments. There is increasing recognition among scientists and regulators that qualitative computer methods have much to offer and that in some circumstances they may be more reliable and informative than quantitative methods. This excellent introduction to a field where employment opportunities are growing is aimed at students, scientists and academics with a knowledge of chemistry.

Auszug. © Genehmigter Nachdruck. Alle Rechte vorbehalten.

Knowledge-Based Expert Systems in Chemistry

Not Counting on Computers

By Philip Judson

The Royal Society of Chemistry

Copyright © 2009 Philip Judson
All rights reserved.

ISBN: 978-0-85404-160-2

Contents

Chapter 1 Artificial Intelligence – Making Use of Reasoning, 1, 
Chapter 2 Synthesis Planning by Computer, 6, 
Chapter 3 Other Programs to Support Chemical Synthesis Planning, 16, 
Chapter 4 International Repercussions of the Harvard LHASA Project, 35, 
Chapter 5 Structure Representation, 41, 
Chapter 6 Structure, Sub-Structure and Super-Structure Searching, 55, 
Chapter 7 Protons that Come and Go, 78, 
Chapter 8 Aromaticity and Stereochemistry, 85, 
Chapter 9 Derek – Predicting Toxicity, 94, 
Chapter 10 Other Alert-Based Toxicity Prediction Systems, 103, 
Chapter 11 Rule Discovery, 110, 
Chapter 12 The 2D–3D Debate, 119, 
Chapter 13 Making Use of Reasoning: Derek for Windows, 124, 
Chapter 14 Predicting Metabolism, 142, 
Chapter 15 Relative Reasoning, 155, 
Chapter 16 Predicting Biodegradation, 165, 
Chapter 17 Other Applications and Potential Applications of Knowledge-Based Prediction in Chemistry, 
176, 
Chapter 18 Evaluation and Validation of Knowledge-Based Systems, 183, 
Chapter 19 Combining Predictions, 191, 
Chapter 20 A Subjective View of the Future, 201, 
Subject Index, 204, 

CHAPTER 1

Artificial Intelligence – Making Use of Reasoning

Launched by half a dozen young men at a run, a three-metre long paper dart can fly successfully, dare we even say "gracefully", the length of a research station canteen before making an unfortunate landing in the director of research's Christmas lunch. It is just a question of getting the aerodynamics right. My school mathematics teacher reminded us on most days (several times on some) that all science is mathematics. But was it only the power of numbers he had in mind? Does science come down to a sweatshop full of equations mindlessly crunching numbers, real and imaginary?

Contrary to the perceptions of many people outside science, as well as too many inside it, science is not about proving facts: it is about testing hypotheses and theories; ultimately, it is about people and their opinions. Simple, rigid application of rules of aerodynamics may get you a paper dart that flies but in many fields human decision making is best supported by reasoned argument or the use of analogy and not much helped by numerical answers. The minimum braking distance for a car travelling at forty miles per hour is twenty-four metres, according to the Driving Manual from the Driving Standards Agency. Assuming you can countenance the required mixing of miles and metres, does this information help you to drive more safely? Have you any more idea than I have how far ahead an imaginary twenty-four metre boundary-marker precedes you along the road?

And there is a further problem. "Numbers out" implies "numbers in", so what do you do if you have no numbers to put in? A regrettably popular solution is to invent them – or at least to come up with dubious estimates to feed into a model that demands them, which is close to invention. It is the only option if you want to apply numerical methods and to give numbers to the people asking for solutions. That numbers make people feel comfortable is a bigger problem than it may at first appear to be, too. Uncritical recipients of numerical answers tend to believe them, and to act on them, without probing very deeply. More sceptical recipients want to judge for themselves how meaningful the answers are but often find that the kind of supporting evidence associated with a numerical method is not much help. Many are the controversies over whether this or that numerical method is more precise but they are missing the point if the data are far less precise than the method. Perhaps numbers are unnecessary – even unsuitable – for expressing some kinds of scientific knowledge.

There are circumstances in which numerical methods are highly reliable. Aeroplanes stay up in the sky and make it safely to earth where they are supposed to do. Chemical plants run twenty-four hours a day, year in year out. Numerical methods work routinely in physical chemistry laboratories, and toxicology and pharmacology departments. But it is unlikely that the designers of the three-metre paper dart that took flight at the start of this chapter did any calculations at all. My guess is that they just went with a gut feeling based on years of experience making little ones.

This book is about uses of artificial intelligence (AI) and databases in computational chemistry and related science where qualitative output may be of more practical use than quantitative output. It touches on quantitative structure–activity relationships (QSAR) and how they can inform qualitative predictions, but it is not about QSAR. Neither is it a book about molecular modelling. Both subjects are well-covered in too many books to list comprehensively. A few examples are given in the references at the end of this chapter. This book focuses on less widely described and yet, probably, more widely-used applications of AI in chemistry.

The term "artificial intelligence" carries with it notions of thinking computers but, as a radio personality in former times would have had it, it all depends on what you mean by intelligence. If you type "Liebig Consender" into the Google™ search box, Google™ responds with "Did you mean Liebig Condenser" and provides a list of corresponding links without waiting for an answer. That is worryingly like intelligent behaviour whether it is intelligent behaviour or not. Arguments continue about whether tests for artificial intelligence such as the Turing test are valid and whether a categorical test or set of tests can be devised. Perhaps it is sufficient to require that to be intelligent a system must be able to learn, be able to reason, be creative, and be able to explain itself persuasively. Currently, no artificial intelligence system can claim to have all of these characteristics. Individual systems typically have two or three.

To count as intelligent, solving problems needs to involve a degree of novel thinking, i.e. creativity. Restating the known, specific answer to a question requires only memory. Compare the following questions and answers. The first answer merely reproduces a single fact. Generating the second answer, simple though it is, requires reasoning and a degree of creativity.

"Where's the sugar?"

"In the sugar bowl".

"Where will the sugar be in this supermarket?"

"A lot of supermarkets put it near the tea and coffee, so it could be along the aisle labelled 'tea and coffee'. Alternatively, it might be in the aisle labelled 'baking'. Let's try 'baking' first – it is nearer".

One of the first computer systems to behave like an expert using a logical sequence of questions and answers to solve a problem was MYCIN, a system to support medical diagnosis.

"Doctor, I keep getting these terrible headaches".

"Sorry to hear that. Is there any pattern to when the headaches occur?"

"Now you ask, they do seem to come mostly on Sunday mornings".

"And what do you do on Saturday evenings?"

The doctor's questions are not arbitrary. You can see how they are directed by the patient's responses. You can probably see where they are leading, too, but the doctor would still want to ask further questions to rule out all...

Details zur Ausgabe

• Verlag: Royal Society of Chemistry
• Erscheinungsdatum: 2009
• Sprache: Englisch
• ISBN 10: 0854041605
• ISBN 13: 9780854041602
• Einband: Gebundene Ausgabe
• Anzahl der Seiten: 222
• Kontakt zum Hersteller: Nicht verfügbar
• Verantwortliche Person: Nicht verfügbar