Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909655691689984 |
|---|---|
| author | Vilalta-Mor, Júlia Molina, Alexis Varga, Laura Ortega Filella-Merce, Isaac Guallar, Victor |
| author_facet | Vilalta-Mor, Júlia Molina, Alexis Varga, Laura Ortega Filella-Merce, Isaac Guallar, Victor |
| contents | Simultaneously optimizing molecules against multiple therapeutic targets remains a profound challenge in drug discovery, particularly due to sparse rewards and conflicting design constraints. We propose a structured active learning (AL) paradigm integrating a sequence-to-sequence (Seq2Seq) variational autoencoder (VAE) into iterative loops designed to balance chemical diversity, molecular quality, and multi-target affinity. Our method alternates between expanding chemically feasible regions of latent space and progressively constraining molecules based on increasingly stringent multi-target docking thresholds. In a proof-of-concept study targeting three related coronavirus main proteases (SARS-CoV-2, SARS-CoV, MERS-CoV), our approach efficiently generated a structurally diverse set of pan-inhibitor candidates. We demonstrate that careful timing and strategic placement of chemical filters within this active learning pipeline markedly enhance exploration of beneficial chemical space, transforming the sparse-reward, multi-objective drug design problem into an accessible computational task. Our framework thus provides a generalizable roadmap for efficiently navigating complex polypharmacological landscapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15309 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation Vilalta-Mor, Júlia Molina, Alexis Varga, Laura Ortega Filella-Merce, Isaac Guallar, Victor Machine Learning Artificial Intelligence Biomolecules Simultaneously optimizing molecules against multiple therapeutic targets remains a profound challenge in drug discovery, particularly due to sparse rewards and conflicting design constraints. We propose a structured active learning (AL) paradigm integrating a sequence-to-sequence (Seq2Seq) variational autoencoder (VAE) into iterative loops designed to balance chemical diversity, molecular quality, and multi-target affinity. Our method alternates between expanding chemically feasible regions of latent space and progressively constraining molecules based on increasingly stringent multi-target docking thresholds. In a proof-of-concept study targeting three related coronavirus main proteases (SARS-CoV-2, SARS-CoV, MERS-CoV), our approach efficiently generated a structurally diverse set of pan-inhibitor candidates. We demonstrate that careful timing and strategic placement of chemical filters within this active learning pipeline markedly enhance exploration of beneficial chemical space, transforming the sparse-reward, multi-objective drug design problem into an accessible computational task. Our framework thus provides a generalizable roadmap for efficiently navigating complex polypharmacological landscapes. |
| title | Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation |
| topic | Machine Learning Artificial Intelligence Biomolecules |
| url | https://arxiv.org/abs/2506.15309 |