Chemoinformatics for Drug Discovery

Chemoinformatics strategies to improve drug discovery results

With contributions from leading researchers in academia and the pharmaceutical industry as well as experts from the software industry, this book explains how chemoinformatics enhances drug discovery and pharmaceutical research efforts, describing what works and what doesn't. Strong emphasis is put on tested and proven practical applications, with plenty of case studies detailing the development and implementation of chemoinformatics methods to support successful drug discovery efforts. Many of these case studies depict groundbreaking collaborations between academia and the pharmaceutical industry.

Chemoinformatics for Drug Discovery is logically organized, offering readers a solid base in methods and models and advancing to drug discovery applications and the design of chemoinformatics infrastructures. The book features 15 chapters, including:

• What are our models really telling us? A practical tutorial on avoiding common mistakes when building predictive models
• Exploration of structure-activity relationships and transfer of key elements in lead optimization
• Collaborations between academia and pharma
• Applications of chemoinformatics in pharmaceutical research—experiences at large international pharmaceutical companies
• Lessons learned from 30 years of developing successful integrated chemoinformatic systems

Throughout the book, the authors present chemoinformatics strategies and methods that have been proven to work in pharmaceutical research, offering insights culled from their own investigations. Each chapter is extensively referenced with citations to original research reports and reviews.

Integrating chemistry, computer science, and drug discovery, Chemoinformatics for Drug Discovery encapsulates the field as it stands today and opens the door to further advances.

Preface vii

Contributors xiii

1 What Are Our Models Really Telling Us? A Practical Tutorial on Avoiding Common Mistakes when Building Predictive Models 1
W. Patrick Walters

2 The Challenge of Creativity in Drug Design 33
Ajay N. Jain

3 A Rough Set Theory Approach to the Analysis of Gene Expression Profiles 51
Joachim Petit, Nathalie Meurice, José Luis Medina-Franco, and Gerald M. Maggiora

4 Bimodal Partial Least-Squares Approach and Its Application to Chemogenomics Studies for Molecular Design 85
Kiyoshi Hasegawa and Kimito Funatsu

5 Stability in Molecular Fingerprint Comparison 97
Anthony Nicholls and Brian Kelley

6 Critical Assessment of Virtual Screening for Hit Identification 113
Dagmar Stumpfe and Jürgen Bajorath

7 Chemometric Applications of Naïve Bayesian Models in Drug Discovery: Beyond Compound Ranking 131
Eugen Lounkine, Peter S. Kutchukian, and Meir Glick

8 Chemoinformatics in Lead Optimization 149
Darren V. S. Green and Matthew Segall

9 Using Chemoinformatics Tools to Analyze Chemical Arrays in Lead Optimization 179
George Papadatos, Valerie J. Gillet, Christopher N. Luscombe, Iain M. McLay, Stephen D. Pickett, and Peter Willett

10 Exploration of Structure–Activity Relationships (SARs) and Transfer of Key Elements in Lead Optimization 205
Hans Matter, Stefan Güssregen, Friedemann Schmidt, Gerhard Hessler, Thorsten Naumann, and Karl-Heinz Baringhaus

11 Development and Applications of Global ADMET Models: In Silico Prediction of Human Microsomal Lability 245
Karl-Heinz Baringhaus, Gerhard Hessler, Hans Matter, and Friedemann Schmidt

12 Chemoinformatics and Beyond: Moving from Simple Models to Complex Relationships in Pharmaceutical Computational Toxicology 267
Catrin Hasselgren, Daniel Muthas, Ernst Ahlberg, Samuel Andersson, Lars Carlsson, Tobias Noeske, Jonna Stålring, and Scott Boyer

13 Applications of Cheminformatics in Pharmaceutical Research: Experiences at Boehringer Ingelheim in Germany 291
Bernd Beck, Michael Bieler, Peter Haebel, Andreas Teckentrup, Alexander Weber, and Nils Weskamp

14 Lessons Learned from 30 Years of Developing Successful Integrated Cheminformatic Systems 321
Michael S. Lajiness and Thomas R. Hagadone

15 Molecular Similarity Analysis 343
José L. Medina-Franco and Gerald M. Maggiora

Index 401

JÜRGEN BAJORATH, PhD, is Chair of Life Science Informatics at the University of Bonn and also an Affiliate Professor in the Department of Biological Structure at the University of Washington. In addition, he has more than 10 years' experience in drug disovery. His research focuses on the development of computational methods for medicinal chemistry and chemical biology. Dr. Bajorath holds 26 patents, has authored more than 400 scientific articles, and edited four books.