CDD Vault now allows you to build predictive models. Because we believe in collaboration and reproducible results, we are releasing the core algorithms that underly this feature as open source software. The chemical fingerprints are detailed below, and we have also released our modified Bayesian model. Send an email to info@collaborativedrug.com if you'd like to try using models in CDD Vault.
By Alex Clark; portions of this post originally appeared in Cheminformatics 2.0 As of now, the latest version of the popular open source Chemistry Development Kit (CDK) has its own implementation of the highly regarded ECFP and FCFP classes of chemical structure fingerprints (sometimes referred to as circular or Morgan fingerprints). While the general recipe for this kind of fingerprint has been available for awhile, and there are a number of implementations in various different toolkits, this one distinguishes itself in several ways: it has been implemented as closely as possible to the description of the original definition (without having access to the trade secrets that were left out of the paper); it includes resolution of chiral centers; it is freely available as open source Java code; and, last but not least, the algorithm is designed to be as portable as possible, with no major dependencies on specific programming languages or cheminformatics toolkits. [caption id="attachment_7271" align="alignnone" width="603"]

Other posts you might be interested in
View All Posts
CDD Vault Updates
5 min
January 29, 2025
CDD Vault Update (January 2025): New Curve Fits, Exponential Decay and Scatter Plot, Hide Outliers in Plot Export, Register an AI Generated Molecule, Create Custom Molecule Optimization Scores
Read More
CDD Blog
8 min
January 9, 2025
Drug Discovery Industry Roundup with Barry Bunin — January 9th, 2025
Read More
CDD Vault Updates
3 min
January 6, 2025
CDD Vault Update (December #2): Create a Sample from a Debit, Suggest Bioisosteres for Unregistered Structures, Copy Protocols Across Vaults
Read More