A Simple Tool for Exploring Structural Alerts

 When working in drug design, we often need filters to identify molecules containing functional groups that may be toxic, reactive, or could interfere with an assay.  A few years ago, I collected the functional group filters available in the ChEMBL database and wrote some Python code that made applying these filters to an arbitrary set of molecules easy.  This functionality is available in the pip installable useful_rdkit_utils package that's available on PyPI and GitHub.  Applying these filters is easy.  If we have a Pandas dataframe with a SMILES column, we can do something like this. 

import useful_rdkit_utils as uru

reos = uru.REOS("BMS")  #optionally specify the rule set to use
df[['rule_set','reos']] = df.SMILES.apply(reos.process_smiles).tolist()

This adds two columns, rule_set, and reos, to the dataframe with the name of the rule_set and the name of the rule matched by each molecule.  If the molecule doesn't match any rules, both columns contain 'ok'.   This is nice, but I'm not intimately familiar with each of these rule sets.  Sometimes, I'd like to look at chemical structures and see what was matched.  To make my life, and hopefully yours, easier, I've written a simple interactive viewer for functional group filters.  This tool takes advantage of the lasso_highlight_image capability recently released by the Datamol team. 

To use this tool, we need to get the SMARTS that were used by the filtering rules. We can do this by adding one line to the code above.  The new code is below. Note that we also added a "smarts" column to the dataframe. 

import useful_rdkit_utils as uru

reos = uru.REOS('BMS')
reos.set_output_smarts(True) # the new code
df[['rule_set','reos','smarts']] =  df.SMILES.apply(reos.process_smiles).tolist()

Now that we have the SMARTS, we can create an interactive tool using ipywidgets.  The tool, shown in the movie below, has a menu and a slider.  The menu is arranged according to functional group filter frequency, with the most frequently matching filter shown at the top.  The value in parentheses is the number of molecules matching that filter.  Changing the menu selection will change the highlighted chemical structure below the menu.  The slider enables us to move through and view individual molecules matching the rule shown in the menu. The slider can be operated by clicking and dragging or by clicking on the slider and using the arrow keys to navigate.  




As I finished this post, the Datamol team released an update with another great addition to the lasso_highlight_image method.  In the new version, we can pass a list of SMILES or RDKit molecules and display a grid of structures with substructures highlighted. The movie below shows an example of how we can display multiple example molecules matching each structural alert. 


The Jupyter notebook demonstrating this functionality can found in the notebooks directory in the useful_rdkit_utils package.  I hope others find it useful.  Please let me know if you run into issues or have suggestions for improvements.   Please note that this notebook requires the latest versions of datamol and useful_rdkit_tuils; make sure you update. 
pip install -U useful_rdkit_utils datamol

I'd like to thank Hadrien Mary from the Datamol team for a quick bug fix and feature enhancements.  I'll be posting more uses for lasso_highlight_image and other datamol capabilities soon. 





Comments

Post a Comment

Popular posts from this blog

We Need Better Benchmarks for Machine Learning in Drug Discovery

Image
Most papers describing new methods for machine learning (ML) in drug discovery report some sort of benchmark comparing their algorithm and/or molecular representation with the current state of the art.  In the past, I’ve written extensively about statistics and how methods should be compared .  In this post, I’d like to focus instead on the datasets we use to benchmark and compare methods.  Many papers I’ve read recently use the MoleculeNet dataset, released by the Pande group at Stanford in 2017, as the “standard” benchmark.   This is a mistake.  In this post, I’d like to use the MoleculeNet dataset to point out flaws in several widely used benchmarks.  Beyond this, I’d like to propose some alternate strategies that could be used to improve benchmarking efforts and help the field to move forward.   To begin, let’s examine the MoleculeNet benchmark, which to date, has been cited more than 1,800 times.   The MoleculeNet collection consists of 16 datasets divided into 4 categories.  Qua
Read more

AI in Drug Discovery 2023 - A Highly Opinionated Literature Review (Part I)

Image
Here’s the first part of my review of some interesting machine learning (ML) papers I read in 2023.  As with the previous editions , this shouldn’t be considered a comprehensive review.  The papers covered here reflect my research interests and biases, and I’ve certainly overlooked areas that others consider vital.  This post is pretty long, so I've split it into three parts, with parts II and III to be posted in the next couple of weeks.    I. Docking, protein structure prediction, and benchmarking II. Large Language Models, active learning, federated learning, generative models, and explainable AI III. Review articles 2023 was a bit of a mixed bag for AI in drug discovery.  Several groups reported that the deep learning methods for protein-ligand docking weren’t quite what they were initially cracked up to be.  AlphaFold2 became pervasive, and people started to investigate, with mixed success, the utility of predicted protein structures.  There were reports of significant advanc
Read more

Getting Real with Molecular Property Prediction

Image
Introduction If you believe everything you read in the popular press, this AI business is easy. Just ask ChatGPT, and the perfect solution magically appears. Unfortunately, that's not the reality. In this post, I'll walk through a predictive modeling example and demonstrate that there are still a lot of subtleties to consider. In addition, I want to show that data is critical to building good machine learning (ML) models. If you don't have the appropriate data, a simple empirical approach may be better than an ML model.  A recent paper from Cheng Fang and coworkers at Biogen presents prospective evaluations of machine learning models on several ADME endpoints.  As part of this evaluation, the Biogen team released a large dataset of measured in vitro assay values for several thousand commercially available compounds.  One component of this dataset is 2,173 solubility values measured at pH 6.8 using chemiluminescent nitrogen detection (CLND), a technique currently consider
Read more