查看: 5368|回复: 12

[参考资料] 的药学数据挖掘著作《药学数据挖掘》pdf下载

[复制链接]
论坛徽章:
0
发表于 2012-3-27 09:19 | 显示全部楼层 |阅读模式
本帖最后由 genesquared 于 2012-3-27 09:35 编辑

Pharmaceutical Data Mining: Approaches and Applications for Drug Discovery
关于药学数据挖掘著作

下载链接:
http://d.dxy.cn/detail/4082237
http://www.docin.com/p-371258809.html


By Konstantin V. Balakin
Publisher:  Wiley
Number Of Pages:  565
Publication Date:  2009-12-21
ISBN-10 / ASIN:  0470196084
ISBN-13 / EAN:  9780470196083


Product Description:


Leading experts illustrate how sophisticated computational data mining techniques can impact contemporary drug discovery and development

In the era of post-genomic drug development, extracting and applying knowledge from chemical, biological, and clinical data is one of the greatest challenges facing the pharmaceutical industry. Pharmaceutical Data Mining brings together contributions from leading academic and industrial scientists, who address both the implementation of new data mining technologies and application issues in the industry. This accessible, comprehensive collection discusses important theoretical and practical aspects of pharmaceutical data mining, focusing on diverse approaches for drug discovery—including chemogenomics, toxicogenomics, and individual drug response prediction. The five main sections of this volume cover:

A general overview of the discipline, from its foundations to contemporary industrial applications

Chemoinformatics-based applications

Bioinformatics-based applications

Data mining methods in clinical development

Data mining algorithms, technologies, and software tools, with emphasis on advanced algorithms and software that are currently used in the industry or represent promising approaches

In one concentrated reference, Pharmaceutical Data Mining reveals the role and possibilities of these sophisticated techniques in contemporary drug discovery and development. It is ideal for graduate-level courses covering pharmaceutical science, computational chemistry, and bioinformatics. In addition, it provides insight to pharmaceutical scientists, principal investigators, principal scientists, research directors, and all scientists working in the field of drug discovery and development and associated industries.


CONTENTS
Section I. Data mining in pharmaceutical industry: a general overview.
Chapter 1. A History of the Development of Datamining in Pharmaceutical Research (David J. Livingstone and John Bradshaw).

1.1. Introduction.

1.2. Technology.

1.3. Computers.

1.3.1. Mainframes.

1.3.2. General Purpose Computers.

1.3.3. Graphics Workstations.

1.3.4. Personal Computers.

1.4. Data Storage and Manipulation.

1.5. Molecular Modelling.

1.6. Characterising Molecules and QSAR.

1.7. Drawing and Storing Chemical Structures.

1.7.1. Line Notations.

1.8. Databases.

1.9. Libraries and Information.

1.10. Summary.

Chapter 2. Drug Gold and Data Dragons. Myths and Realities of Data Mining in the Pharmaceutical Industry (Barry Robson and Andy Vaithiligam).

2.1. The Pharmaceutical Challenge.

2.1.1. A Period of Transition.

2.1.2. The Dragon on the Gold.

2.1.3. The Pharmaceutical Industry is an Information Industry.

2.1.4. Biological Information.

2.1.5. The Available Information in Medical Data.

2.1.6. The Information Flow.

2.1.7. The Information in Complexity.

2.1.8. The Datum, Element of Information.

2.1.9. Data and Metadata.

2.1.10. Rule Weights.

2.2. Probabilities, Rules, and Hypotheses.

2.2.1. Semantic Interpretation of Probabilities.

2.2.2. Probability Theory as Quantification of Logic.

2.2.3. Comparison of Probability and Higher Order Logic Perspective Clarifies the Notions of Hypotheses.

2.2.4. Pharmaceutical Implications.

2.2.5. Probability Distributions.

2.3. Pattern and Necessity.

2.3.1. Mythological Constellations Can Appear in Projection.

2.3.2. The Hunger for Higher Complexity.

2.3.3. Does Sparseness of Data Breed Abundance of Pattern?

2.3.4. Sparse Data Can in Context be Strong Data, when Associated with Contrary Evidence.

2.4. Contrary Evidence.

2.4.1. Lack of Contrary evidence Breeds Superstition and Mythology.

2.5. Some Problems of Classical Statistical Thinking.

2.5.1. Statistical Myth 1. Classical Statistics is Objective, against the Yardstick of Bayesian Thinking Which is Subjective.

2.5.2. Statistical Myth 2. Ho the Null Hypothesis.

2.5.3. Statistical Myth 3. Rejection and the Falsifiability Model.

2.5.4. Statistical Myth 4: The value of  P(D | Ho )  is Interesting.

2.5.5. Statistical Myth 5. The value of  P(Ho | D)  is Interesting.

2.5.6. Statistical Myth 6. Rejecting the Null hypotheses is a Conservative Choice.

2.6. Data Mining versus the Molecule Whisperer Prior Data D*.

2.6.1. The Two Edged Sword.

2.6.2. Types of Data Mining Reflect types of Measure.

2.6.3. Including D*.

2.6.4. D* and the Filtering Effect.

2.6.5. No Prior Hunch, No Hypothesis to Test.

2.6.6. Good Data Mining is not Just Testing of Many Randomly Generated Hypotheses.

2.7. Inference from Rules.

2.7.1. Rule Interaction.

2.7.2. It is Useful to Have Rules in Information Theoretic Form.

2.7.3. A Predicate Calculus under Uncertainty.

2.7.4. Borrowing from Dirac.

2.8. Clinical Applications.

2.9. Molecular Applications.

2.9.1. Molecular Descriptors.

2.9.2. Complex Descriptors.

2.9.3. Global invariance of Complex Descriptors.

2.9.4. Peptide and Protein Structures.

2.9.5. Mining Systems Biology Input and Output.

2.10. Discussion and Conclusions.

Chapter 3. Application of data mining algorithms in pharmaceutical research and development (Konstantin V. Balakin).

3.1. Introduction.

3.2. Chemoinformatics-based applications.

3.2.1. Analysis of HTS data.

3.2.2. Target-specific library design.

3.2.3. Assessment of ADME/Tox and physico-chemical properties.

3.3. Bioinformatics-based applications.

3.4. Post-genome data mining.

3.5. Data mining methods in clinical development.

3.6. The future.

Section II. Chemoinformatics-Based Applications.

Chapter 4. Data Mining Approaches for Compound Selection and Iterative Screening (Martin Vogt and Jürgen Bajorath).

4.1. Introduction.

4.2. Molecular Representations and Descriptors.

4.2.1. Graph Representations.

4.2.2. Fingerprints.

4.3. Data Mining Techniques.

4.3.1. Clustering and Partitioning.

4.3.2. Similarity Searching.

4.4. Bayesian Modeling.

4.4.1. Predicting the performance of Bayesian screening.

4.4.2. Binary Kernel Discrimination.

4.5. Support Vector Machines.

4.6. Application Areas.

4.7. Conclusions.

Chapter 5. Prediction of toxic effects of pharmaceutical agents (Andreas Maunz and Christoph Helma).

5.1. Introduction.

5.1.1. Problem description.

5.1.2. Predictive toxicology approaches.

5.1.3. (Q)SAR model development.

5.2. Feature Generation.

5.3. Feature selection.

5.3.1. Unsupervised techniques.

5.3.2. Supervised techniques.

5.4. Model Learning.

5.4.1. Data Preprocessing.

5.4.2. Modelling techniques.

5.4.3. Global models.

5.4.4. Instance-based techniques (local models).

5.5. Combination of (Q)SAR steps.

5.5.1. Constraint-based feature selection.

5.5.2. Graph kernels.

5.6. Applicability domain.

5.6.1. Definition and purpose of Applicability Domains.

5.6.2. Determination of Applicability Domains.

5.7. Model Validation.

5.7.1. Validation procedures.

5.7.2. Performance measures.

5.7.3. Mechanistic Interpretation.

5.8. Conclusion.

Chapter 6. Chemogenomics-based design of GPCR-targeted libraries using data mining techniques (Konstantin V. Balakin and Elena V. Bovina).

6.1. Introduction.

6.2. Data mining techniques in the design of GPCR-targeted chemical libraries.

6.3. Mining the chemogenomics space.

6.3.1. Annotated libraries.

6.3.2. Technologies based on annotated databases.

6.3.3. Chemogenomics-based design of GPCR ligands.

6.4. Chemogenomics-based analysis of chemokine receptor ligands.

6.4.1. Mapping the chemogenomic space of GPCR ligands.

6.4.2. GPCR target classes.

6.4.3. Similarity across the Chemokine receptor superfamily.

6.5. Conclusion.

Chapter 7. Mining High-throughput Screening Data by Novel Knowledge-based Optimization Analysis (S. Frank Yan, Frederick J. King, Sumit K. Chanda, Jeremy S. Caldwell, Elizabeth A. Winzeler, Yingyao Zhou).

7.1. Introduction.

7.2. KOA Algorithm-Concept, Validation, and Its Applications in Target Identification.

7.2.1. KOA Analysis for High-throughput siRNA Function Screening.

7.2.2. Experimental Validation of KOA by Genome-wide siRNA Screening.

7.2.3. KOA for In Silico Gene Function Prediction.

7.3. Applications of the KOA Approach in Small Molecule HTS Data Mining.

7.3.1. Scaffold-based HTS Compound Triage and Prioritization for Improved Lead Discovery.

7.3.2. Identify Promiscuous and Toxic Scaffolds by Mining Multi-assay HTS Database.

7.4. Other Related Approaches for Biological Data Mining.

7.4.1. k-means Clustering Algorithm.

7.4.2. Iterative Group Analysis Algorithm.

7.4.3. Gene Set Enrichment Analysis.

7.5. Conclusion.

Section III. Bioinformatics-Based Applications.

Chapter 8. Mining DNA microarray gene expression data (Paolo Magni).

8.1. Introduction.

8.2.  Microarray technology.

8.2.1.  Type of microarrays.

8.2.2.  DNA microarrays.

8.2.3.  Sample preparation, labelling and hybridization.

8.2.4.  From arrays to numbers: acquisition and preprocessing.

8.3.  Data mining techniques.

8.3.1  Kind of experiments.

8.3.2.  Gene selection.

8.3.3.  Classification.

8.3.4.  Clustering.

8.4.  Summary.

Chapter 9. Bioinformatics approaches for analysis of protein-ligand interactions (Munazah Andrabi, Chioko Nagao, Kenji Mizuguchi and Shandar Ahmad).

9.1.  Introduction.

9.2.  Ligands in Bioinformatics.

9.3.  Representation and visualization of ligands.

9.4.  Identifying interactions from structure.

9.5.  Identifying interactions from in-vitro thermodynamic data.

9.6.  Thermodynamic databases of protein-ligand interactions.

9.7.  Data analysis and knowledge generation.

9.8.  Analysis of databases.

9.9.  Simulations and molecular docking.

9.10.  High Throughput Docking (HTD).

9.11.  Conclusion.

Chapter 10. Analysis of Toxicogenomics Databases (Lyle D. Burgoon).

10.1. Introduction.

10.2. Toxicogenomic Databases and Repositories.

10.2.1. Toxicogenomic Information Management Systems.

10.2.2. Toxicogenomic Data Repositories.

10.3. Toxicogenomic Data Standards.

10.3.1. Regulatory Guidance from the US FDA and US EPA.

10.3.2. Standards vs. Guidelines.

10.4. Data Extraction and Data Mining.

10.5. Is a TIMS Right For You?

Chapter 11. Bridging the Pharmaceutical Shortfall: Informatics approaches to the discovery of Vaccines, Antigens, Epitopes, and Adjuvants (Matthew N. Davies and Darren R. Flower).

11.1. Introduction.

11.2. Predicting Antigens.

11.3. Reverse Vaccinology.

11.4. Epitope prediction.

11.5. Designing Delivery Vectors.

11.6. Adjuvant Discovery.

11.7. Discussion.

Section IV. Data Mining Methods in Clinical Development.

Chapter 12. Data mining in pharmacovigilance (Manfred Hauben and Andrew Bate).

12.1. Introduction.

12.2. The Need for Post marketing Drug Safety Surveillance.

12.3. The Relationship Between Data Quantity and Quality.

12.4. Signal Detection-The Front Line of Pharmacovigilance.

12.4.1. Pharmacovigilance.

12.4.2. Signal Detection in PhV.

12.5. Targets, Tools and Datasets.

12.6. The Sample Space of Adverse Events.

12.7. Reporting Mechanism.

12.8. The Anatomy of Spontaneous Reporting System Data Bases.

12.9. Methods in Drug Safety Surveillance.

12.10. Traditional Approaches to Drug Safety Surveillance.

12.11. Quantitative Approaches.

12.12. Classical or Frequentist Approaches.

12.12.1. Overview: The Bayesian Approach.

12.12.2. The Principle Bayesian Methods: BCPNN and MGPS.

12.12.3. The Principle Bayesian Methods: BCPNN and MGPS.

12.13. Evaluating and Validating Data Mining Performance in Pharmacovigilance.

12.14. Practical Implementation.

12.15. The need for complex methods.

12.16. Discussion.

Chapter 13. Data-mining methods as tools for predicting individual drug response (Sabbagh Audrey and Darlu Pierre).

13.1. The promise of pharmacogenomics.

13.2. Combinatorial pharmacogenomics.

13.2.1. DME-DME interactions.

13.2.2. Interactions between pharmacokinetic factors.

13.2.3. Interactions between pharmacokinetic and pharmacodynamic factors.

13.3. Identifying useful marker combinations for the prediction of individual drug response.

13.3.1. Logistic regression.

13.3.2. The need for higher-order computational methods.

13.4. Data-mining tools available to predict individual drug response from genetic data.

13.4.1. Tree-based methods.

13.4.2. Combinatorial methods.

13.4.3. Artificial neural networks.

13.5. Applications of data-mining tools in pharmacogenomics.

13.5.1. Development of pharmacogenomic classifiers from single-nucleotide germline polymorphisms.

13.5.2. Development of pharmacogenomic classifiers from gene expression data.

13.6. Conclusion.

Chapter 14. Data mining methods in pharmaceutical formulation (Raymond C. Rowe and Elizabeth A Colbourn).

14.1. Introduction.

14.2. Methodology.

14.3. Applications.

14.3.1. Tablet formulations (Immediate release).

14.3.2. Tablet formulations (Controlled release).

14.3.3. Topical formulations.

14.3.4. Other formulations.

14.3.5. Worked examples.

14.3.6. Controlled release tablets.

14.3.7. Immediate release tablets.

14.4. Drug-loaded nanoparticles.

14.5. Suspensions.

14.6. Benefits and issues.

Section V. Data Mining Algorithms and Technologies

Chapter 15. Dimensionality reduction techniques for pharmaceutical data mining (Igor V. Pletnev, Yan A. Ivanenkov and Alexey V. Tarasov).

15.1. Introduction.

15.2. Dimensionality reduction basics.

15.2.1. Clustering.

15.3. Linear Techniques for Dimensionality Reduction.

15.3.1. Principal component analysis.

15.3.2. Linear Discriminant Analysis.

15.3.3. Factor analysis.

15.4. Nonlinear Techniques for Dimensionality Reduction.

15.4.1. Global techniques.

15.4.2. Local techniques..

Chapter 16. Advanced methods of artificial intelligence in the design of pharmaceutical agents (Yan A. Ivanenkov and Ludmila M. Khandarova).

16.1. Introduction.

16.2. Advanced Computational Techniques for Chemical Data Mining.

16.2.1. Nonlinear Sammon Mapping.

16.2.2. Self-organizing Kohonen Maps.

16.2.3. IsoMap.

16.2.4. Stochastic Proximity Embedding.

16.3. Mapping Software.

16.4. Conclusion.

Chapter 17. Databases for chemical and biological information (Tudor I. Oprea, Liliana Ostopovici-Halip, Ramona Rad-Curpan).

17.1. Introduction.

17.2. Database management systems for Chemistry and Biology.

17.3. Informational Structure of Bioactivity Databases.

17.3.1. Chemical information.

17.3.2. Biological activity information.

17.3.3. Target information.

17.3.4. Information drift.

17.3.5. Protocol information.

17.3.6. References.

17.3.7. Integration with other databases.

17.4. Available Biological and Bioactivity Databases.

17.4.1. Bioactivity databases.

17.4.2. Biological information databases.

17.5. Conclusions.

Chapter 18. Mining Chemical Structural Information from the Literature (Debra L. Banville).

18.1. Introduction.

18.1.1.  Missed information costs time and money.

18.1.2.  Issues of drug safety require better information management capabilities.

18.2. Different needs, different challenges and the call for standardization.

18.2.1.  The ultimate backend solution is universal standards, especially for chemical and biological information.

18.2.2.  Main driver for standardization with life science literature is drug safety.

18.3. Current methodologies for converting chemical entities to structures.

18.3.1.  Multiple types of naming schemes, require diverse set of conversion capabilities.

18.3.2.  Systematic chemical name to structure conversion.

18.3.3.  Unsystematic chemical name look-up.

18.4. Representing chemical structures in machine-readable forms.

18.4.1. The language of e-Chem: InChI's, Smiles, CML and more.

18.5. Building context with NLP today.

18.6. A vision for the future.

18.6.1.  Crossing from Chemistry into Biomedical Space with chemically mined information.

18.6.2. Text Mining is about the generation of new knowledge.

Index.



回复

使用道具 举报

论坛徽章:
6
spss初级
日期:2012-10-11 16:17:06EBS财务徽章
日期:2013-05-09 13:13:47EBS制造徽章
日期:2013-05-09 13:15:37python徽章
日期:2013-05-09 13:21:16Oracle研习者高级
日期:2013-08-25 14:24:54树莓派
日期:2014-09-19 15:22:08
发表于 2012-3-27 09:25 | 显示全部楼层
回复 支持 反对

使用道具 举报

论坛徽章:
0
 楼主| 发表于 2012-3-27 09:40 | 显示全部楼层
cruiser 发表于 2012-3-27 09:25

沙发抢得够快啊

基本忙完一个大project
能够挖掘蛋白之间的作用网络,
只需要很便宜和简单的一对芯片数据,
就可以开发出大药厂需要的靶点和新的基因功能通路

做出来, 然后找到理论根据,
就是这本书的
Chap 7 & 8
回复 支持 反对

使用道具 举报

论坛徽章:
6
spss初级
日期:2012-10-11 16:17:06EBS财务徽章
日期:2013-05-09 13:13:47EBS制造徽章
日期:2013-05-09 13:15:37python徽章
日期:2013-05-09 13:21:16Oracle研习者高级
日期:2013-08-25 14:24:54树莓派
日期:2014-09-19 15:22:08
发表于 2012-3-27 12:06 | 显示全部楼层
genesquared 发表于 2012-3-27 09:40
沙发抢得够快啊

基本忙完一个大project

听起来很牛啊

很好奇生物里用到的这些“芯片”是怎么回事,和IT里用的芯片有什么区别?
回复 支持 反对

使用道具 举报

论坛徽章:
0
 楼主| 发表于 2012-3-27 16:19 | 显示全部楼层
cruiser 发表于 2012-3-27 12:06
听起来很牛啊

很好奇生物里用到的这些“芯片”是怎么回事,和IT里用的芯片有什么区别?

生物芯片,又称DNA芯片或基因芯片,它们是DNA杂交探针技术与半导体工业技术相结合的结晶。该技术系指将大量探针分子固定于支持物上后与带荧光标记的DNA样品分子进行杂交,通过检测每个探针分子的杂交信号强度进而获取样品分子的数量和序列信息。
回复 支持 反对

使用道具 举报

论坛徽章:
6
spss初级
日期:2012-10-11 16:17:06EBS财务徽章
日期:2013-05-09 13:13:47EBS制造徽章
日期:2013-05-09 13:15:37python徽章
日期:2013-05-09 13:21:16Oracle研习者高级
日期:2013-08-25 14:24:54树莓派
日期:2014-09-19 15:22:08
发表于 2012-3-27 19:37 | 显示全部楼层
genesquared 发表于 2012-3-27 16:19
生物芯片,又称DNA芯片或基因芯片,它们是DNA杂交探针技术与半导体工业技术相结合的结晶。该技术系指将大 ...

听起来好像很神奇啊,这样就能测序了?
回复 支持 反对

使用道具 举报

论坛徽章:
6
spss初级
日期:2012-10-11 16:17:06EBS财务徽章
日期:2013-05-09 13:13:47EBS制造徽章
日期:2013-05-09 13:15:37python徽章
日期:2013-05-09 13:21:16Oracle研习者高级
日期:2013-08-25 14:24:54树莓派
日期:2014-09-19 15:22:08
发表于 2012-3-27 22:25 | 显示全部楼层
Pharmaceutical Data Mining.pdf (4.63 MB)
回复 支持 反对

使用道具 举报

论坛徽章:
7
R研习者中级
日期:2012-04-29 00:26:34R研习者中级
日期:2014-12-24 15:25:22R研习者中级
日期:2014-12-24 15:26:59R研习者中级
日期:2014-12-24 15:28:23R研习者中级
日期:2015-03-02 15:12:54scala徽章
日期:2015-04-10 15:06:34LATEX徽章
日期:2015-05-07 11:34:37
发表于 2012-3-27 23:38 | 显示全部楼层
感谢楼上的分享~~~数据挖掘无处不在~~
回复 支持 反对

使用道具 举报

论坛徽章:
0
 楼主| 发表于 2012-3-28 15:57 | 显示全部楼层
cruiser 发表于 2012-3-27 22:25

  挖这种数据得出来的结果, 直接可以卖给欧美的大药厂,
他们需要药物的靶点。
当然也申请自己专利。

NCBI GEO里面,都是免费公开的芯片数据和相对应的文献
回复 支持 反对

使用道具 举报

论坛徽章:
0
发表于 2013-12-1 20:57 | 显示全部楼层
感谢分享
回复 支持 反对

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册 新浪微博登陆

本版积分规则

 

GMT+8, 2018-11-16 13:41 , Processed in 0.309812 second(s), 55 queries .

关闭

扫一扫加入
本版微信群