Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning

Abstract The stability and therapeutic efficacy of antibody-drug conjugates (ADCs) are critically determined by the chemical linkers that connect the antibody to the cytotoxic payload, which is a key factor influencing drug release, plasma stability, and off-target toxicity. However, the current lin...

Full description

Saved in:
Bibliographic Details
Main Authors: An Su, Yanlin Luo, Chengwei Zhang, Hongliang Duan
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05555-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238814039474176
author An Su
Yanlin Luo
Chengwei Zhang
Hongliang Duan
author_facet An Su
Yanlin Luo
Chengwei Zhang
Hongliang Duan
author_sort An Su
collection DOAJ
description Abstract The stability and therapeutic efficacy of antibody-drug conjugates (ADCs) are critically determined by the chemical linkers that connect the antibody to the cytotoxic payload, which is a key factor influencing drug release, plasma stability, and off-target toxicity. However, the current linker design space remains highly constrained, with most approved ADCs relying on a narrow set of established motifs. This limitation highlights an urgent need for computational tools capable of generating structurally diverse and synthetically accessible linkers. In this study, we introduce Linker-GPT, a Transformer-based deep learning framework leveraging self-attention mechanisms to generate novel ADC linkers with high structural diversity and synthetic feasibility. The model integrates transfer learning from large-scale molecular datasets and reinforcement learning (RL) to iteratively refine molecular properties such as drug-likeness and synthetic accessibility. During transfer learning, a pre-trained model was fine-tuned on a curated linker dataset, yielding molecules with high validity (0.894), novelty (0.997), and uniqueness (0.814 at 1k generation). RL further optimized the model to prioritize synthesizability and drug-like properties, resulting in 98.7% of generated molecules meeting target thresholds for QED (> 0.6), LogP (< 5), and synthetic accessibility score (SAS < 4). Linker-GPT demonstrates strong potential as a computational platform for accelerating the discovery and optimization of novel ADC linkers, offering a scalable solution for early-stage linker design. While these results are currently computational, they provide a foundation for future experimental validation and optimization.
format Article
id doaj-art-00a62bc36d6644cf831363a1f4e7d022
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-00a62bc36d6644cf831363a1f4e7d0222025-08-20T04:01:23ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-05555-3Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learningAn Su0Yanlin Luo1Chengwei Zhang2Hongliang Duan3Zhejiang Key Laboratory of Green Manufacturing Technology for Chemical Drugs, Key Laboratory of Pharmaceutical Engineering of Zhejiang Province, Key Laboratory for Green Pharmaceutical Technologies and Related Equipment of Ministry of Education, College of Pharmaceutical Science, Zhejiang University of TechnologyCollege of Chemical Engineering, Zhejiang University of TechnologyCollege of Chemical Engineering, Zhejiang University of TechnologyFaculty of Applied Sciences, Macao Polytechnic UniversityAbstract The stability and therapeutic efficacy of antibody-drug conjugates (ADCs) are critically determined by the chemical linkers that connect the antibody to the cytotoxic payload, which is a key factor influencing drug release, plasma stability, and off-target toxicity. However, the current linker design space remains highly constrained, with most approved ADCs relying on a narrow set of established motifs. This limitation highlights an urgent need for computational tools capable of generating structurally diverse and synthetically accessible linkers. In this study, we introduce Linker-GPT, a Transformer-based deep learning framework leveraging self-attention mechanisms to generate novel ADC linkers with high structural diversity and synthetic feasibility. The model integrates transfer learning from large-scale molecular datasets and reinforcement learning (RL) to iteratively refine molecular properties such as drug-likeness and synthetic accessibility. During transfer learning, a pre-trained model was fine-tuned on a curated linker dataset, yielding molecules with high validity (0.894), novelty (0.997), and uniqueness (0.814 at 1k generation). RL further optimized the model to prioritize synthesizability and drug-like properties, resulting in 98.7% of generated molecules meeting target thresholds for QED (> 0.6), LogP (< 5), and synthetic accessibility score (SAS < 4). Linker-GPT demonstrates strong potential as a computational platform for accelerating the discovery and optimization of novel ADC linkers, offering a scalable solution for early-stage linker design. While these results are currently computational, they provide a foundation for future experimental validation and optimization.https://doi.org/10.1038/s41598-025-05555-3Machine learningTransfer learningAntibody-drug conjugatesLinker designReinforcement learningMolecule generation
spellingShingle An Su
Yanlin Luo
Chengwei Zhang
Hongliang Duan
Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
Scientific Reports
Machine learning
Transfer learning
Antibody-drug conjugates
Linker design
Reinforcement learning
Molecule generation
title Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
title_full Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
title_fullStr Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
title_full_unstemmed Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
title_short Linker-GPT: design of Antibody-drug conjugates linkers with molecular generators and reinforcement learning
title_sort linker gpt design of antibody drug conjugates linkers with molecular generators and reinforcement learning
topic Machine learning
Transfer learning
Antibody-drug conjugates
Linker design
Reinforcement learning
Molecule generation
url https://doi.org/10.1038/s41598-025-05555-3
work_keys_str_mv AT ansu linkergptdesignofantibodydrugconjugateslinkerswithmoleculargeneratorsandreinforcementlearning
AT yanlinluo linkergptdesignofantibodydrugconjugateslinkerswithmoleculargeneratorsandreinforcementlearning
AT chengweizhang linkergptdesignofantibodydrugconjugateslinkerswithmoleculargeneratorsandreinforcementlearning
AT hongliangduan linkergptdesignofantibodydrugconjugateslinkerswithmoleculargeneratorsandreinforcementlearning