Cheminformatics and bioinformatics

We have been developing cutting-edge data analysis tools for the pharmaceutical industry for over a decade, with a particular focus in the fields of cheminformatics and bioinformatics. We now describe how our insights apply to these areas. 

However, given that the cheminformatics and bioinformatics worlds have evolved more or less independently, it is first necessary to establish classification and annotation schemes that link the chemical and biological knowledge spaces. 

SCONP and PSSC themselves are cheminformatics-and bioinformatics-based approaches for the design of biologically prevalidated compound collections which aim to improve the probability for successful discovery of small molecule ligands and inhibitors. The combined use... 

Bayesian statistics Bayesian inference is a variant of statistics where prior information is allowed to influence the posterior probability of an event via application of Bayes rule. Complex problems of cheminformatics and bioinformatics often benefit from Bayesian models. A schism divides statisticians from Bayesians. 

Pattern recognition techniques can be divided into display, preprocessing, supervised, and unsupervised learning. Pattern recognition methods are used among others in the search for correlations between sequence, structure, and biological activity in cheminformatics and bioinformatics. 

Data Discovery, bioinformatics and cheminformatics, and called naive Bayes... 

Artificial neural networks A machine or program for supervised or unsupervised learning based on a layered network of neurons. Normally, a network is trained to best describe a biological or chemical system, in order to classify new systems. Used for pattern recognition in cheminformatics, QSAR, and bioinformatics. 

For a discussion of the inherent, or structural limitations of the two main conventional formalisms—vector space, or numeric, and logical—see [4], [5]. Incidentally, it is these inherent limitation of the numeric (representational) formalism that, I believe, are responsible for the predominance of statistical over structural considerations in machine learning, pattern recognition, data mining, information retrieval, bioinformatics, cheminformatics, and many other applied areas. The question is not whether the appropriate statistical considerations should play some role in these areas, the obvious answer to which is yes, of course , but, as I emphasized above, whether, at present—when we lack any satisfactory formalism for structural representation—we should be focusing on the development of new statistical techniques for the conventional formalisms that are inherently inadequate for dealing with classes (and hence, with the class-oriented needs of the above areas). 

In addition to the new theoretical horizons that are being opened up within new (event-based) representational formahsms, the other main reason why such formalisms should be of interest to researchers in computation has to do with the immediate practical benefits one can derive from their various applications in machine learning, pattern recognition, data mining, information retrieval, bioinformatics, cheminformatics, and many other applied areas. The validity of the last statement should become apparent if one followed carefully the above point regarding the new and rich aspect of object representation—i.e. the object s formative history—that now becomes available within the ETS formalism. 

More can be found at http //www.bioinformatics.org, http //www.open-bio.org, http //www.cheminformatics.org, and http //www.chemoinf.com. 

The value of the BioPrint dataset is achieved from a combination of high quality in vitro data generated for each compound, and in vivo data extracted from public medical literature (see below). Relating both types of information supports the bioinformatics applications of the database. Also of value is the diversity of compounds, both chemical and biological, which are indicated for a large array of therapeutic areas. This diversity provides a good training set to develop and test various QSAR methods, and supports the cheminformatics applications of the database (Fig. 1). 

Cheminformatics is the chemistry equivalent to bioinformatics and involves the tools and techniques (usually computational) for storing, handling, and communicating the massive and ever-increasing amounts of data concerning molecular structures. Like bioinformatics, cheminformatics attempts to combine data from varying sources ... 

Cheminformatics, Bioinformatics, and Computer-Aided Molecular Design... 

---