Design Through Statistics

Having identified a natural lead and developed a synthetic route to it, it is then a small step for the chemist to prepare simple analogues of the natural material and investigate their properties. As a result, the chemist then begins to build up a library of chemical structures the properties of which are known as far as the application in question is concerned. This database then enables the pursuit of one of the approaches to rational design of novel molecules, that of design through statistics. 

An example of the process from natural chemicals to high performance synthetic ingredients is given in chapter 3 of the book by Pybus and Sell.101 In this example, the development of modern jasmine ingredients based on the key odour components of natural jasmine extracts is outlined. 

The molecular structure of any chemical will determine all of its physical, chemical and biological properties. Discovery chemists will therefore seek correlations between molecular structure and a desired property and the search for novel materials is therefore often guided by structure/ activity relationships (SARs). These can also be referred to as structure/ property relationships (SPRs) and when carried out with data inputs in a numerical form and using statistical methods for their analysis, the adjective quantitative is added giving quantitative structure/activity 

With a large data set of structures and properties, it is possible to use multivariate statistical methods such as principal components analysis to try to identify patterns. The applications of statistics to chemistry is known as chemometrics and an internet search for this keyword will lead to a variety of useful sources of information on the field. Some QSAR methods are based on the molecular orbitals of the compounds in the 

QSARs are second nature to the discovery chemist and contribute much to the search for efficacious novel molecules. However, there are a number of points which must be borne in mind when using QSARs. 

---

The proper conduct of complex exposure studies requires that the quality of the data be well defined and the statistical basis be sufficient to support rule making if necessary. These requirements, from study design through chemical analysis to data reduction and interpretation, focused our attention on the application of chemometric techniques to environmental problems. 

According to the FDA, assurance of product quality is derived from careful and systemic attention to a number of important factors, including selection of quality components and materials, adequate product and process design, and (statistical) control of the process through in-process and end-product testing. 

Nguyen NAT, Wells ML, Cooper DC. Identification of factors affecting preservative efficacy and chemical stability of lamivudine oral solution through statistical experimental design. Drug Dev Ind Pharm 1995 21 1671-1682. 

Optimization of Fermentation Conditions Through Statistically Based Experimental Designs... 

Chipman, H. A. (1998). Fast model search for designed experiments. In Quality Improvement Through Statistical Methods. Editor B. Abraham, pages 205-220. Birkhauser, Boston. 

Sources of process variance can be quantified and ranked through statistical design o experiments. Relations between variances of process input and output can be developed. In this way, the e ect of laboratory analyses, as well as of parallel or sequential manufacturing steps, on the overall variance for a catalyst can be determined. 

Provided that a proper experimental design has been used to establish the model parameters, and that the model adequately describes the variation of y in the experimental domain, we can use the model to evaluate the influence of each variable and assess the significance of each term in the model. This can be accomplished through statistical tests which compare the estimated parameters to estimates of the experimental error. This will answer the Which and How questions.[4]... 

The basic, macroscopic theories of matter are equilibrium thermodynamics, irreversible thermodynamics, and kinetics. Of these, kinetics provides an easy link to the microscopic description via its molecular models. The thermodynamic theories are also connected to a microscopic interpretation through statistical thermodynamics or direct molecular dynamics simulation. Statistical thermodynamics is also outlined in this section when discussing heat capacities, and molecular dynamics simulations are introduced in Sect 1.3.8 and applied to thermal analysis in Sect. 2.1.6. The basics, discussed in this chapter are designed to form the foundation for the later chapters. After the introductory Sect. 2.1, equilibrium thermodynamics is discussed in Sect. 2.2, followed in Sect. 2.3 by a detailed treatment of the most fundamental thermodynamic function, the heat capacity. Section 2.4 contains an introduction into irreversible thermodynamics, and Sect. 2.5 closes this chapter with an initial description of the different phases. The kinetics is closely link to the synthesis of macromolecules, crystal nucleation and growth, as well as melting. These topics are described in the separate Chap. 3. 

Methods for the production of rubber bonded components have to be established and firmly founded within strict limits of the many parameters for the control of quality. It is in the initial stages of the development of the production process that the use of suitable bond tests is vital. The test values will allow the manufacturer to discover the operational limits for all process variables and ensure that the set conditions for production do not allow a knife-edge situation where small changes can produce large variations in the quality of the bond. This is best achieved through the use of factorial experiment design and statistical regression analysis of the results. 

KA Borden, RC Weil, CR Manganaro. The Effect of Polymeric Coupling Agent on Mica-FiUed Polypropylene Optimization of Properties through Statistical Experimental Design. ANTEC, 1993, pp. 2167-2170. 

Lotfy WA, Ghanem KM, El-Helow ER. Citric acid production by a novel Aspergillus niger isolate II. Optimization of process parameters through statistical experimental designs. Bioresour Technol 2007 98 3470-7. 

MUcent S, Carrere H. Clarification of lactic acid fermentation broths. Sep Puri Technol 2001 22 393-401. Liu C, Liu Y, Liao W, Wen Z, Chen S. Simultaneous production of nisin and lactic acid from cheese whey optimization of fermentation conditions through statistically based experimental designs. Appl Biochem Biotechnol 2004 114 627-38. 

Optimization of Material Design through Correlation Statistics... 

---