Natural product-likeness of a molecule, i.e.
similarity of this molecule to the structure space covered by natural products,
is a useful criterion in screening compound libraries and in designing new lead compounds.
This NP-likeness scorer has been trained on 315 916 natural products (NP) from various public databases
on a manually curated NP dataset used for the publication of the previous standalone NP-likeness scorer 
and on 488 642 randomly selected synthetic molecules (SM) from the ZINC
Sugar moieties are removed from the molecules for the training and for the computation of the NP-likeness score as in 
The stereochemistry is removed from the training set and from the user-submitted molecules.
Four ways to use the NP-likeness scorer:
- Upload a molecular file in one of the accepted formats (MOL, SDF or smiles). Maximum 1000 molecules per file.
- Paste a SMILES string of a molecule
- Draw a molecule
- Visualise the distribution of the NP-likeness score across natural products of public databases and taxonomy (bacteria, fungi and plants)
Upload a file
 Jayaseelan et al., Natural product-likeness score revisited: an open-source, open-data implementation.
In: BMC Bioinformatics, 13 (1), pp. 106, 2012.
 Peter Ertl et al., Natural Product-likeness Score and Its Application for Prioritization of Compound Libraries.
In: Journal of Chemical Information and Modeling 48 (1), 68-74, 2008