Nondrug-likeness

Ajay A, Walters WP, Murcko MA. Can we learn to distinguish between druglike and nondrug-like molecules J Med Chem 1998 41 3314-24. 

Ajay, Walters, W. P., Murcko, M. A. Gan we learn to distinguish between drug-like and nondrug-like molecules J. Med. Chem. 1998, 41, 3314-3324. 

The first application of a computational method to select structurally diverse compounds for purchase started in 1992 at the Upjohn Company, which predated the formation of Pharmacia Upjohn by about three years. The basic approach selected compounds using a method based upon maximum dissimilarity and was implemented using SAS software [11]. This later evolved into the program Dfragall, which was written in C and is described in Section 13.6.3. Basically, a set of compounds that is maximally dissimilar from the corporate compound collection is chosen from the set of available vendor compounds. Early versions of the process relied solely on diversity-based metrics but it was found that many nondrug like compounds were identified. As a result, structural exclusion criteria were developed to eliminate compounds that were considered unsuitable for... 

Ajay, Walters, W.P. and Murcko, M. Can We Learn to Distinguish between Drug-like and Nondrug-like Molecules J. Med. Chem., 1998,41,3314-3324. 

Molecular holograms are an extended form of fingerprints based on the 2D structures. An HQSAR model was derived for 250 compounds (r2 = 0.93, q2 = 0.70) and tested with 52 compounds (r2 = 0.85) [37], which is a good result. The authors correctly point out some limitations of the model. Training is based on drugs, most compliant to the rule-of-5, and has no real solubility issues. The question therefore arises whether such model would be predictive for and pick out nondrug-like compounds. 

The scoring functions measure the similarity of compounds to existing drugs by either structural features or by chemical properties or by both structural and chemical properties their values are ideally distributed betv een zero (i.e., nondrug-like) and one (i.e., drug-like). 

Distinguish between Drug-Like and Nondrug-Like Molecules ... 

---