scholarly journals Design of chemical libraries with potentially bioactive molecules applying a maximum common substructure concept

2009 ◽  
Vol 14 (2) ◽  
pp. 401-408 ◽  
Author(s):  
Michael Lisurek ◽  
Bernd Rupp ◽  
Jörg Wichard ◽  
Martin Neuenschwander ◽  
Jens Peter von Kries ◽  
...  
Keyword(s):  
Bioactive Molecules ◽  
Chemical Libraries ◽  
Maximum Common Substructure ◽  
Common Substructure

The optimization of running time for a maximum common substructure-based algorithm and its application in drug design

2014 ◽  
Vol 48 ◽  
pp. 14-20 ◽  
Author(s):  
Jian Chen ◽  
Jia Sheng ◽  
Dijing Lv ◽  
Yang Zhong ◽  
Guoqing Zhang ◽  
...  
Keyword(s):  
Drug Design ◽  
Running Time ◽  
Maximum Common Substructure ◽  
Common Substructure

scholarly journals fmcsR: mismatch tolerant maximum common substructure searching in R

2013 ◽  
Vol 29 (21) ◽  
pp. 2792-2794 ◽  
Author(s):  
Yan Wang ◽  
Tyler W. H. Backman ◽  
Kevin Horan ◽  
Thomas Girke
Keyword(s):  
Maximum Common Substructure ◽  
Common Substructure

scholarly journals VAE-Sim: a novel molecular similarity measure based on a variational autoencoder

2020 ◽  
Author(s):  
Soumitra Samanta ◽  
Steve O’Hagan ◽  
Neil Swainston ◽  
Timothy J. Roberts ◽  
Douglas B. Kell
Keyword(s):  
Molecular Similarity ◽  
A Priori ◽  
Molecular Structures ◽  
Maximum Common Substructure ◽  
Latent Vector ◽  
Novel Approach ◽  
Variational Autoencoder ◽  
Common Substructure ◽  
Similarity Problem ◽  
Better Than

AbstractMolecular similarity is an elusive but core ‘unsupervised’ cheminformatics concept, yet different ‘fingerprint’ encodings of molecular structures return very different similarity values even when using the same similarity metric. Each encoding may be of value when applied to other problems with objective or target functions, implying that a priori none is ‘better’ than the others, nor than encoding-free metrics such as maximum common substructure (MCSS). We here introduce a novel approach to molecular similarity, in the form of a variational autoencoder (VAE). This learns the joint distribution p(z|x) where z is a latent vector and x are the (same) input/output data. It takes the form of a ‘bowtie’-shaped artificial neural network. In the middle is a ‘bottleneck layer’ or latent vector in which inputs are transformed into, and represented as, a vector of numbers (encoding), with a reverse process (decoding) seeking to return the SMILES string that was the input. We train a VAE on over 6 million druglike molecules and natural products (including over one million in the final holdout set). The VAE vector distances provide a rapid and novel metric for molecular similarity that is both easily and rapidly calculated. We describe the method and its application to a typical similarity problem in cheminformatics.

Sign in / Sign up

Export Citation Format

Share Document