I came across a paper named "Chemical Similarity Searching" by Peter Willett John M. Barnard and Geoffrey M. Downs, 1998. At one place, this paper talks of finding chemical structure similarity between two chemical compounds using Tanimoto method. Now I want to understand how it is done but could not derive anything just by reading the paper. I wanted to know if someone can explain how the distance is found taking two compounds into consideration. I wanted a step by step explanation. I have failed to derive how to find similarity from the paper. Please help.


1 Answer 1


Apparently, it is more generally known as the "Jaccard Index":

In "A Computer Program for Classifying Plants", published in October 1960,[5] a method of classification based on a similarity ratio, and a derived distance function, is given. It seems that this is the most authoritative source for the meaning of the terms "Tanimoto similarity" and "Tanimoto Distance". The similarity ratio is equivalent to Jaccard similarity, but the distance function is not the same as Jaccard distance.

In terms of chemistry, this calculation is carried out on a fingerprint of the molecule. That wikipedia page has a nice reference to this paper, although it is not open access. There are no doubt many resources out there about fingerprints/Tanimoto, even open source implementations...

This also looks interesting: "Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?".


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.