Chemical Similarity Searching

By Peter Willett, J. Barnard, Geoffrey M. Downs. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Massively Multitask Networks for Drug Discovery (2015, background): “ECFP4 and other ﬁngerprints are commonly used in cheminformatics applications, especially to measure similarity between compounds (Willett et al., 1998).”
BindingDB: a web-accessible database of experimentally determined protein–ligand binding affinities (2006, background): “(18)] of each candidate compound to each active, and ranks the candidate compounds according to their maximal similarity to any active.”
mVOC: a database of microbial volatiles (2013, methodology): “For the purpose of calculating the Tanimoto coefficient (26), it is obligatory to assign fingerprints to the compounds.”
jCompoundMapper: An open source Java library and command-line tool for chemical fingerprints (2011, background): “These encodings are important for data mining applications like similarity-based machine learning approaches or similarity searches [2].”
Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? (2015, unknown): “1998 article [32].”
Comparing Stars: On Approximating Graph Edit Distance (2009, background): “3. similarity search : ﬁnd all graphs g i in D s.t. g i is similar to q within a user-speciﬁed threshold based on some similarity measures [23, 31].”
HIT: linking herbal active ingredients to targets (2010, unknown): “de/cdk/), using Tanimoto coefficient (16).”
ChemMine. A Compound Mining Database for Chemical Genomics1 (2005, methodology): “The current online version of this tool can use either atom pairs (Carhart et al., 1985) or atom sequences as structural descriptors, and uses the Tanimoto coefficient as similarity measure (Willett et al., 1998).”