Data interpretation knowledge-based system approaches

The data-driven approach does not render the model-driven approach obsolete or superfluous. In fact, data-driven approaches have to rely, and will do so for the foreseeable future, on model-driven advances in single fields of science (Aebersold, 2000). In addition, without knowledge gained with reductionist approaches interpretation of data with the systems approach is not possible. Novel tools such as pathway analysis and pattern recognition, and novel kinds of research questions such as the investigation of hypotheses based on the interaction of several system components, become possible with the systems approach. 

The first is a rule-based system, which makes predictions for untested agents by drawing upon the human interpretation of toxicity data and biological information. That is, it captures, organizes, and applies scientific expertise that relates chemical structures with developmental toxicity. Examples of commercially available rule-based approaches include HazardExpert,23 Deductive Estimation of Risk from Existing Knowledge (DEREK),24... 

The interpretation of IR spectra is therefore of enormous interest. The prediction and interpretation of IR spectra with ab initio, quantum chemical methods, or a density functional theory approach is quite time consuming and is thus limited to small molecules. Semi-empirical methods are faster but the results need to be scaled to achieve satisfactory correspondence with experimental data. For this reason, there is a need for systems that model the relationship between structures and IR spectra based on knowledge derived from experimental data. 

---