article thumbnail

Clustering Fragment Screening Hits With a Self-Organizing Map

Practical Cheminformatics

Anyway, I used a method similar to the one described in this blog post , which exploits the AllChem.AssignBondOrdersFromTemplate method in the RDKit. Cluster the fragment structures Readers of this blog probably know about my fondness for Self-Organizing Maps (SOMs), which I wrote about here and here.

article thumbnail

AI-based drug design?

Molecular Design

Trying to deal with the diverse hype of AI-based drug design in a single blog post is likely to send any blogger on a one-way trip to the funny farm so I’ll narrow the focus a bit. Specifically, I’ll be trying to understand the meaning of the term “AI-designed drug”.

Drugs 84
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Assessment of chemical probes

Molecular Design

First, structural alerts derived from analysis of screening hits (defined as responses that exceed a threshold when assayed at a particular concentration) are not necessarily useful for assessing higher affinity compounds for which concentration responses have been determined.

article thumbnail

We Need Better Benchmarks for Machine Learning in Drug Discovery

Practical Cheminformatics

Recent blog posts from Greg Landrum examined the impact of combining IC50 and Ki data from different assays. It is quite a bit more potent than the values one finds with screening hits, which typically have IC50s in the single to double-digit µM range. 200nM is an odd choice for an activity cutoff.

Drugs 94
article thumbnail

A PAINful itch

Molecular Design

The distinction between Type 1 and and Type 2 behaviors is an important and useful one to make from the perspective of drug discovery scientists who are making decisions as to which screening hits to take forward. It's now time to examine what SYI has to to say and singlet oxygen is as good a place as any to start from.