Adding Chemical Structures to a Recent COVID-19 Drug Repurposing Dataset

In a preprint posted on bioRxiv on April 5, 2020, Franck Touret and coworkers from Aix Marseille Université published the results from a SARS-CoV-2 cellular assay of 1520 compounds from the Prestwick Chemical Library, a collection of off-patent marketed drugs.  Unfortunately, the authors published the preprint without including the chemical structures of the compounds.   Fortunately, Brian Cole used a couple of databases to associate structures with this screening data and posted the revised data, as well as the scripts he used to do the annotation on GitHub. 

This short post serves two purposes. 
  • It highlights data that may be useful to those working on treatments for SARS-CoV-2.  It may be possible to associate this screening data with recently released biophysical data and obtain mechanistic insights. 
  • The solution that Brian came up with is generally applicable,  and can be applied to the many cases where data is published without associated chemical structures.
In Brian's approach, he uses ChEMBL, a database of more than 2 million molecules and associated biological data, curated from the medicinal chemistry literature.   Each of the drug names supplied in the supporting information for the preprint is used to "lookup" the corresponding chemical structure in the ChEMBL database.   ChEMBL can be downloaded in a variety of formats, or accessed through an application programming interface (API).  For tasks like this, which require more than a thousand database queries, the direct method is preferred over the API.  

Brian's method begins with SQL to join the necessary database tables. 

select 
compound_structures.canonical_smiles as compound_smiles, 
molecule_dictionary.chembl_id as compound_chembl_id, 
molecule_dictionary.pref_name as compound_name, 
molecule_dictionary.max_phase as drug_development_phase 
FROM compound_structures 
JOIN molecule_dictionary 
ON compound_structures.molregno = molecule_dictionary.molregno

In this query, we are accessing two ChEMBL tables.  
  • compound_strucutures - contains the chemical structures of the database molecules in SMILES, molfile, and InChI formats.
  • molecule_dictionary - maps molecule identifiers between different tables
The function search_chembl_for_compound then extends the SQL above with 
WHERE molecule_dictionary.pref_name LIKE ? COLLATE NOCASE

This combined SQL will then perform a case insensitive search (specified by COLLATE NOCASE) on the joined tables to find drugs with a specific name (e.g. Desonide).  

As Brian points out in his README file, ChEMBL was able to associate structures with 1504 of the 1520 compounds.  In order to locate the chemical structures for the remaining 16 molecules, Brian used the NIH Chemical Identifier Resolver, a web service for converting names to chemical structures.  Using this approach, he was able to assign structures to 14 of the 16 names not listed in the ChEMBL database.   Brian's README describes the additional detective work necessary to complete the dataset. 

In addition to the valuable public service provided by the data, Brian's code presents a very useful approach to associating chemical structures with the names of drugs or other molecules.  Thanks, Brian! 



Comments

Post a Comment

Popular posts from this blog

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

Generative Molecular Design Isn't As Easy As People Make It Look

Image
I was taken aback by a recent CNBC article entitled “ Generative AI will be designing new drugs all on its own in the near future ”.  I should know better than to pay attention to AI articles in the popular press, but I feel that even scientists working in drug discovery may have a skewed perception of what generative AI can and can’t do.  To understand exactly what’s involved, it might be instructive to walk through a typical generative molecular design workflow and point out a few things.  First, these programs are far from autonomous.  Even when presented with a well-defined problem, generative algorithms produce a tremendous amount of nonsense.  Second, domain expertise is essential when sifting through the molecules produced by a generative algorithm.  Without a significant medicinal chemistry background, one can’t make sense of the results.  Third, while a few nuggets exist in the generative modeling output, a lot of work and good old-fashioned cheminformatics are required to ext
Read more

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

Image
Picking up where we left off in Part I , this post covers several other ML in drug discovery topics that interested me in 2023.  Some areas, like large language models, are new, and most of the work is at the proof-of-concept stage.  Others, like active learning, are more mature, and several groups are starting to explore nuances of the methods.   Here’s the structure of Part II.  4. Large Language Models 5. Active Learning 6. Federated Learning 7. Generative Models 8. Explainable AI 9. Other Stuff 4. Large Language Models The emergence of GPT-4 and ChatGPT brought considerable attention to large language models (LLMs) in 2023.  In November and December, several large pharmas held “AI Day” presentations featuring LLM applications for clinical trial data analysis. Many of these groups demonstrated the ability of LLMs to ingest large bodies of unstructured clinical data and subsequently generate tables and reports based on natural language queries.  Aside from some very brief demos on co
Read more