Related Experiment Video
Updated: Aug 5, 2025
Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays
Published on: October 23, 2019
Utilization of Supervised Machine Learning to Understand Kinase Inhibitor Toxophore Profiles
Andrew A Bieberich1, Christopher R M Asquith2,3,4
1AsedaSciences Inc., 1281 Win Hentschel Boulevard, West Lafayette, IN 47906, USA.
Abstract:
There have been more than 70 FDA-approved drugs to target the ATP binding site of kinases, mainly in the field of oncology. These compounds are usually developed to target specific kinases, but in practice, most of these drugs are multi-kinase inhibitors that leverage the conserved nature of the ATP pocket across multiple kinases to increase their clinical efficacy. To utilize kinase inhibitors in targeted therapy and outside of oncology, a narrower kinome profile and an understanding of the toxicity profile is imperative. This is essential when considering treating chronic diseases with kinase targets, including neurodegeneration and inflammation. This will require the exploration of inhibitor chemical space and an in-depth understanding of off-target interactions. We have developed an early pipeline toxicity screening platform that uses supervised machine learning (ML) to classify test compounds' cell stress phenotypes relative to a training set of on-market and withdrawn drugs. Here, we apply it to better understand the toxophores of some literature kinase inhibitor scaffolds, looking specifically at a series of 4-anilinoquinoline and 4-anilinoquinazoline model libraries.
Insights
This study uses machine learning to predict drug toxicity by analyzing cell stress phenotypes. The platform helps understand kinase inhibitor toxophores for safer drug development in chronic diseases.
Area of Science:
- Biochemistry
- Pharmacology
- Computational Biology
Background:
- Over 70 FDA-approved drugs target the ATP binding site of kinases, primarily in oncology.
- Many kinase inhibitors are multi-targeted due to conserved ATP pockets, increasing clinical efficacy.
- Targeted therapy outside oncology requires narrower kinome profiles and better toxicity understanding.
Purpose of the Study:
- To develop an early pipeline toxicity screening platform using machine learning (ML).
- To classify test compounds' cell stress phenotypes against known drugs.
- To understand the toxophores of kinase inhibitor scaffolds, specifically 4-anilinoquinoline and 4-anilinoquinazoline libraries.
Main Methods:
- Developed a supervised ML platform for toxicity screening.
- Classified cell stress phenotypes of test compounds.
- Applied the platform to model kinase inhibitor libraries.
Main Results:
- The ML platform successfully classified cell stress phenotypes.
- Identified potential toxophores within the studied kinase inhibitor scaffolds.
- Provided insights into off-target interactions relevant to chronic diseases.
Conclusions:
- The ML-based toxicity screening platform aids in understanding kinase inhibitor safety.
- This approach is crucial for developing targeted therapies for chronic diseases like neurodegeneration and inflammation.
- Further exploration of inhibitor chemical space and toxicity profiles is essential for advancing drug development.
More Related Videos
11:23Characterization at the Molecular Level using Robust Biochemical Approaches of a New Kinase Protein
Published on: June 30, 2019
09:24Generation of Microtumors Using 3D Human Biogel Culture System and Patient-derived Glioblastoma Cells for Kinomic Profiling and Drug Response Testing
Published on: June 9, 2016