QSAR-based virtual screening

Simplistic and heuristic similarity-based approaches can hardly produce as good predictive models as modern statistical and machine learning methods that are able to assess quantitatively biological or physicochemical properties. QSAR-based virtual screening consists of direct assessment of activity values (numerical or binary) of all compounds in the database followed by selection of hits possessing desirable activity. Mathematical methods used for models preparation can be subdivided into classification and regression approaches. The former decide whether a given compound is active, whereas the latter numerically evaluate the activity values. Classification approaches that assess probability of decisions are called probabilistic. 

I 5 Strengths and Limitations of Pharmacophore-Based Virtual Screening Tab. 5.2 The six-variable linear overlay-based Cox2 QSAR model... 

Figure 4.1 Ligand-based virtual screening methods. The figure shows different computational methods for screening compound databases that take either a local or a global view on molecular structure. Molecular similarity methods that operate on molecular descriptors, histogram representations, superposition or (reduced) molecular graphs evaluate molecular structure globally. By contrast, local structural features are explored by substructure and pharmacophore searching or QSAR modeling.

Prathipati P, Saxena AK. Evaluation of binary qsar models derived from ludi and moe scoring functions for structure based virtual screening. J Chem Inf Model 2006 46 39-51. 

Willett, P. (2006a). Enhancing the effectiveness of ligand-based virtual screening using data fusion. QSAR Comb. Sci. 25,1143-1152. 

Prathipati, P. and Saxena, A.K. (2006) Evaluation of binary QSAR models derived from LUDl and MOE scoring functions for structure based virtual screening./. Chem. Inf. Model., 46, 39—51. 

XuE, L, Godden, J.W., and Bajorath, J. Mini-fingerprints for virtual screening design principles and generation of novel prototypes based on information theory. SAR QSAR Environ. Res. 2003, 14, 27-40. 

Virtual Screening Models and Focused Libraries 2D, 3D-QSAR, Pharmacophore based models Structure Based models (Docking)... 

Generally speaking, 3D QSAR approaches provide useful tools for drug design and virtual screening. However, in many cases they require one to go back to topology-based (2D or 2.5D) structure representation rather than analyze the 3D molecular models directly. 

---