Cluster analysis approach

Identification of Groupings of Graph Theoretical Descriptors Using a Hybrid Cluster Analysis Approach. 

Taraviras, S.L., Ivanciuc, O. and Cabrol-Bass, D. (2000) Identification of groupings of graph theoretical molecular descriptors using a hybrid cluster analysis approach. /. Chem. Inf. Comput. Sci., 40, 1128-1146. 

Another strategy for the detection of glutathione adducts is to rely on cluster analysis approaches in which a labeled form and a nonlabeled form of glutathione are used at a defined ratio. Various labels (Table 6.1) have been proposed and Mutlib et al. [18] used a deuterium labeled in the glutamate moiety (mass difference 3 Da) and switched later to a GSH-labeled 13C2-15N in the glycine moiety (mass difference 3 Da) [19], If the data-dependent acquisition mode is positive in the survey scan, then the... 

There is no correct method of performing cluster analysis and a large number of algorithms have been devised from which one must choose the most appropriate approach. There can also be a wide variation in the efficiency of the various cluster algorithms, which may be an important consideration if the data set is large. 

A major potential drawback with cluster analysis and dissimilarity-based methods f selecting diverse compounds is that there is no easy way to quantify how completel one has filled the available chemical space or to identify whether there are any hole This is a key advantage of the partition-based approaches (also known, as cell-bas( methods). A number of axes are defined, each corresponding to a descriptor or son combination of descriptors. Each axis is divided into a number of bins. If there are axes and each is divided into b bins then the number of cells in the multidimension space so created is ... 

Hence there are multiple solutions for the final set of 10000 compounds. The final selection can be diversity driven using for example cluster analysis based on multiple fingerprints [63], hole filling strategies by using scaffold/ring analysis (LeadScope [66], SARVision [66]) or pharmacophore analysis [67, 68]. For a review of computational approaches to diversity and similarity-based selections, see the paper of Mason and Hermsmeier [69] and the references therein. 

Use of multivariate approaches based on classification modelling based on cluster analysis, factor analysis and the SIMCA technique [98,99], and the Kohonen artificial neural network [100]. All these methods, though rarely implemented, lead to very good results not achievable with classical strategies (comparisons, amino acid ratios, flow charts) and, moreover it is possible to know the confidence level of the classification carried out. 

In an extension to the studies mentioned above, the actions of 11 commercial pyrethroids on calcium influx and glutamate release were assessed using a high-throughput approach with rat brain synaptosomes [75, 76]. Concentration-dependent response curves for each commercial pyrethroid were determined and the data used in a cluster analysis. Previously characterized Type II pyrethroids that induce the CS-syndrome symptoms (cypermethrin, deltamethrin, and esfenvalerate) increased calcium influx and glutamate release, and clustered with two other ot-cyano pyrethroids (p-cyfluthrin and A-cyhalothrin) that shared these same actions. Previously characterized Type I pyrethroids (bioallethrin, cismethrin, and fenpropathrin) did not share these actions and clustered with two other non-cyano pyrethroids (tefluthrin and bifenthrin) that likewise did not elicit these actions. 

The final methodological chapter (Chapter 6) is devoted to cluster analysis. Besides a general treatment of different clustering approaches, also more specific problems in chemometrics are included, like clustering binary vectors indicating presence or absence of certain substructures. 

Kowalski and Bender presented chemometrics (at this time called pattern recognition and roughly considered as a branch of artificial intelligence) in a broader scope as a general approach to interpret chemical data, especially by mapping multivariate data with the purposes of cluster analysis and classification (Kowalski and Bender 1972). 

Exploratory data analysis has the aim to learn about the data distribution (clusters, groups of similar objects). In multivariate data analysis, an X-matrix (objects/samples characterized by a set of variables/measurements) is considered. Most used method for this purpose is PCA, which uses latent variables with maximum variance of the scores (Chapter 3). Another approach is cluster analysis (Chapter 6). 

It is this diversity of metabolites that presents the most difficult challenge. There are not only a variety of metabolites but they are also dynamic spatially and temporally. To master a universal "omics" approach, one has to have several measurement strategies. For example, a suite of quantitative methods analyzing key metabolites from different biochemical pathways and metabolic "fingerprinting" that compares patterns like multidimensional hierarchical clustering or principal cluster analysis.9... 

Because the FCV algorithms are basically a non-statistlcal approach to cluster analysis it was not possible to attach estimates of mlsclasslfication error for step 2a). Similarly, the amount of data which could be collected for the investigation was not considered sufficient for use in defining confidence levels for the absolute values of plant emissions determined by step 2b). These qualifications need to be taken into consideration when interpreting the results of the investigation. 

---