Linking machine learning and biophysical structural features in drug discovery
IntroductionMachine learning methods were applied to analyze pharmacophore features derived from four protein-binding sites, aiming to identify key features associated with ligand-specific protein conformations.MethodsUsing molecular dynamics simulations, we generated an ensemble of protein conforma...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Molecular Biosciences |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmolb.2024.1305272/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591005758521344 |
|---|---|
| author | Armin Ahmadi Shivangi Gupta Vineetha Menon Jerome Baudry |
| author_facet | Armin Ahmadi Shivangi Gupta Vineetha Menon Jerome Baudry |
| author_sort | Armin Ahmadi |
| collection | DOAJ |
| description | IntroductionMachine learning methods were applied to analyze pharmacophore features derived from four protein-binding sites, aiming to identify key features associated with ligand-specific protein conformations.MethodsUsing molecular dynamics simulations, we generated an ensemble of protein conformations to capture the dynamic nature of their binding sites. By leveraging pharmacophore descriptors, the AI/ML framework prioritized features uniquely associated with ligand-selected conformations, enabling a mechanism-driven understanding of binding interactions. This novel approach integrates biophysical insights with machine learning, focusing on pharmacophoric properties such as charge, hydrogen bonding, hydrophobicity, and aromaticity.ResultsResults showed significant enrichment of true positive ligands—improving database enrichment by up to 54-fold compared to random selection—demonstrating the robustness of this approach across diverse proteins.ConclusionUnlike conventional structure-based or ligand-based screening methods, this work emphasizes the role of specific protein conformations in driving ligand binding, making the process highly interpretable and actionable for drug discovery. The key innovation lies in identifying pharmacophore features tied to conformations selected by ligands, offering a predictive framework for optimizing drug candidates. This study illustrates the potential of combining ML and pharmacophoric analysis to develop intuitive and mechanism-driven tools for lead optimization and rational drug design. |
| format | Article |
| id | doaj-art-040bd8b2cc5943f2b5cdfcbba1430eeb |
| institution | Kabale University |
| issn | 2296-889X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Molecular Biosciences |
| spelling | doaj-art-040bd8b2cc5943f2b5cdfcbba1430eeb2025-01-23T05:10:17ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2025-01-011110.3389/fmolb.2024.13052721305272Linking machine learning and biophysical structural features in drug discoveryArmin Ahmadi0Shivangi Gupta1Vineetha Menon2Jerome Baudry3Department of Biological Sciences, The University of Alabama in Huntsville, Huntsville, AL, United StatesDepartment of Computer Science, The University of Alabama in Huntsville, Huntsville, AL, United StatesDepartment of Computer Science, The University of Alabama in Huntsville, Huntsville, AL, United StatesDepartment of Biological Sciences, The University of Alabama in Huntsville, Huntsville, AL, United StatesIntroductionMachine learning methods were applied to analyze pharmacophore features derived from four protein-binding sites, aiming to identify key features associated with ligand-specific protein conformations.MethodsUsing molecular dynamics simulations, we generated an ensemble of protein conformations to capture the dynamic nature of their binding sites. By leveraging pharmacophore descriptors, the AI/ML framework prioritized features uniquely associated with ligand-selected conformations, enabling a mechanism-driven understanding of binding interactions. This novel approach integrates biophysical insights with machine learning, focusing on pharmacophoric properties such as charge, hydrogen bonding, hydrophobicity, and aromaticity.ResultsResults showed significant enrichment of true positive ligands—improving database enrichment by up to 54-fold compared to random selection—demonstrating the robustness of this approach across diverse proteins.ConclusionUnlike conventional structure-based or ligand-based screening methods, this work emphasizes the role of specific protein conformations in driving ligand binding, making the process highly interpretable and actionable for drug discovery. The key innovation lies in identifying pharmacophore features tied to conformations selected by ligands, offering a predictive framework for optimizing drug candidates. This study illustrates the potential of combining ML and pharmacophoric analysis to develop intuitive and mechanism-driven tools for lead optimization and rational drug design.https://www.frontiersin.org/articles/10.3389/fmolb.2024.1305272/fulldrug discoverymachine learningpharmacophoreconformational selectiondockingensemble docking |
| spellingShingle | Armin Ahmadi Shivangi Gupta Vineetha Menon Jerome Baudry Linking machine learning and biophysical structural features in drug discovery Frontiers in Molecular Biosciences drug discovery machine learning pharmacophore conformational selection docking ensemble docking |
| title | Linking machine learning and biophysical structural features in drug discovery |
| title_full | Linking machine learning and biophysical structural features in drug discovery |
| title_fullStr | Linking machine learning and biophysical structural features in drug discovery |
| title_full_unstemmed | Linking machine learning and biophysical structural features in drug discovery |
| title_short | Linking machine learning and biophysical structural features in drug discovery |
| title_sort | linking machine learning and biophysical structural features in drug discovery |
| topic | drug discovery machine learning pharmacophore conformational selection docking ensemble docking |
| url | https://www.frontiersin.org/articles/10.3389/fmolb.2024.1305272/full |
| work_keys_str_mv | AT arminahmadi linkingmachinelearningandbiophysicalstructuralfeaturesindrugdiscovery AT shivangigupta linkingmachinelearningandbiophysicalstructuralfeaturesindrugdiscovery AT vineethamenon linkingmachinelearningandbiophysicalstructuralfeaturesindrugdiscovery AT jeromebaudry linkingmachinelearningandbiophysicalstructuralfeaturesindrugdiscovery |