Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules
Alzheimer’s disease (AD) is marked by the pathological accumulation of amyloid beta-42 (Aβ42), contributing to synaptic dysfunction and neurodegeneration. While extracellular amyloid plaques are well-studied, increasing evidence highlights intracellular Aβ42 as an early and toxic driver of disease p...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/15/6/849 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849432982699376640 |
|---|---|
| author | Naeyma N. Islam Thomas R. Caulfield |
| author_facet | Naeyma N. Islam Thomas R. Caulfield |
| author_sort | Naeyma N. Islam |
| collection | DOAJ |
| description | Alzheimer’s disease (AD) is marked by the pathological accumulation of amyloid beta-42 (Aβ42), contributing to synaptic dysfunction and neurodegeneration. While extracellular amyloid plaques are well-studied, increasing evidence highlights intracellular Aβ42 as an early and toxic driver of disease progression. In this study, we present a novel, Generative AI–based drug design approach to promote targeted degradation of Aβ42 via the ubiquitin–proteasome system (UPS), using E3 ligase–directed molecular glues. We systematically evaluated the ternary complex formation potential of Aβ42 with three E3 ligases (CRBN, VHL, and MDM2) through structure-based modeling, ADMET screening, and docking. We then developed a Ligase-Conditioned Junction Tree Variational Autoencoder (LC-JT-VAE) to generate ligase-specific small molecules, incorporating protein sequence embeddings and torsional angle-aware molecular graphs. Our results demonstrate that this generative model can produce chemically valid, novel, and target-specific molecular glues capable of facilitating Aβ42 degradation. This integrated approach offers a promising framework for designing UPS-targeted therapies for neurodegenerative diseases. |
| format | Article |
| id | doaj-art-e197d0764dc843afbcaa5c8dc611eecb |
| institution | Kabale University |
| issn | 2218-273X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj-art-e197d0764dc843afbcaa5c8dc611eecb2025-08-20T03:27:13ZengMDPI AGBiomolecules2218-273X2025-06-0115684910.3390/biom15060849Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like MoleculesNaeyma N. Islam0Thomas R. Caulfield1Department of Neuroscience, Mayo Clinic, Jacksonville, FL 32224, USADigital Ether Computing, Miami, FL33130, USAAlzheimer’s disease (AD) is marked by the pathological accumulation of amyloid beta-42 (Aβ42), contributing to synaptic dysfunction and neurodegeneration. While extracellular amyloid plaques are well-studied, increasing evidence highlights intracellular Aβ42 as an early and toxic driver of disease progression. In this study, we present a novel, Generative AI–based drug design approach to promote targeted degradation of Aβ42 via the ubiquitin–proteasome system (UPS), using E3 ligase–directed molecular glues. We systematically evaluated the ternary complex formation potential of Aβ42 with three E3 ligases (CRBN, VHL, and MDM2) through structure-based modeling, ADMET screening, and docking. We then developed a Ligase-Conditioned Junction Tree Variational Autoencoder (LC-JT-VAE) to generate ligase-specific small molecules, incorporating protein sequence embeddings and torsional angle-aware molecular graphs. Our results demonstrate that this generative model can produce chemically valid, novel, and target-specific molecular glues capable of facilitating Aβ42 degradation. This integrated approach offers a promising framework for designing UPS-targeted therapies for neurodegenerative diseases.https://www.mdpi.com/2218-273X/15/6/849molecular gluesartificial intelligencevariable autoencodersligase-conditioned junction tree variational autoencoder |
| spellingShingle | Naeyma N. Islam Thomas R. Caulfield Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules Biomolecules molecular glues artificial intelligence variable autoencoders ligase-conditioned junction tree variational autoencoder |
| title | Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules |
| title_full | Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules |
| title_fullStr | Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules |
| title_full_unstemmed | Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules |
| title_short | Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules |
| title_sort | conditioned generative modeling of molecular glues a realistic ai approach for synthesizable drug like molecules |
| topic | molecular glues artificial intelligence variable autoencoders ligase-conditioned junction tree variational autoencoder |
| url | https://www.mdpi.com/2218-273X/15/6/849 |
| work_keys_str_mv | AT naeymanislam conditionedgenerativemodelingofmoleculargluesarealisticaiapproachforsynthesizabledruglikemolecules AT thomasrcaulfield conditionedgenerativemodelingofmoleculargluesarealisticaiapproachforsynthesizabledruglikemolecules |