Learning in Chemoinformatics

In deductive learning one must have a fundamental theory that allows one to make inferences and to calculate the property of interest. 

Such a fundamental theory does exist for chemistry quantum mechanics. The dependence of the property of a compound on its three-dimensional structure is given by the Schrodinger equation. Great progress has been made both in the de- 

There is, however, another type of learning inductive learning. From a series of observations inferences are made to predict new observations. In order to be able to do this, the observations have to be put into a scheme that allows one to order them, and to recognize the features these observations have in common and the essential features that are different. On the basis of these observations a model of the principles that govern these observations must be built such a model then allows one to make predictions by analogy. 

Inductive learning has been the major process of acquiring chemical knowledge from the very beginnings of chemistry - or, to make the point, alchemy. Chemists have done experiments, have made measurements on the properties of their compounds, have treated them with other compounds to study their reactions, and have run reactions to make new compounds. Systematic variations in the structure of compounds, or in reaction conditions, provided results that were ordered by developing models. These models then allowed predictions to be made. 

A point in case is provided by the bromination of various monosubstituted benzene derivatives it was realized that substituents with atoms carrying free electron pairs bonded directly to the benzene ring (OH, NH2, etc) gave 0- and p-substituted benzene derivatives. Furthermore, in all cases except of the halogen atoms the reaction rates were higher than with unsubstituted benzene. On the other hand, substituents with double bonds in conjugation with the benzene ring (NO2, CHO, etc.) decreased reaction rates and provided m-substituted benzene derivatives. 

---