Domain-Agnostic Molecular Generation with Chemical Feedback
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929263172648960 |
|---|---|
| author | Fang, Yin Zhang, Ningyu Chen, Zhuo Guo, Lingbing Fan, Xiaohui Chen, Huajun |
| author_facet | Fang, Yin Zhang, Ningyu Chen, Zhuo Guo, Lingbing Fan, Xiaohui Chen, Huajun |
| contents | The generation of molecules with desired properties has become increasingly popular, revolutionizing the way scientists design molecular structures and providing valuable support for chemical and drug design. However, despite the potential of language models in molecule generation, they face challenges such as generating syntactically or chemically flawed molecules, having narrow domain focus, and struggling to create diverse and feasible molecules due to limited annotated data or external molecular databases. To tackle these challenges, we introduce MolGen, a pre-trained molecular language model tailored specifically for molecule generation. Through the reconstruction of over 100 million molecular SELFIES, MolGen internalizes structural and grammatical insights. This is further enhanced by domain-agnostic molecular prefix tuning, fostering robust knowledge transfer across diverse domains. Importantly, our chemical feedback paradigm steers the model away from molecular hallucinations, ensuring alignment between the model's estimated probabilities and real-world chemical preferences. Extensive experiments on well-known benchmarks underscore MolGen's optimization capabilities in properties such as penalized logP, QED, and molecular docking. Additional analyses confirm its proficiency in accurately capturing molecule distributions, discerning intricate structural patterns, and efficiently exploring the chemical space. Code is available at https://github.com/zjunlp/MolGen. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_11259 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Domain-Agnostic Molecular Generation with Chemical Feedback Fang, Yin Zhang, Ningyu Chen, Zhuo Guo, Lingbing Fan, Xiaohui Chen, Huajun Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language The generation of molecules with desired properties has become increasingly popular, revolutionizing the way scientists design molecular structures and providing valuable support for chemical and drug design. However, despite the potential of language models in molecule generation, they face challenges such as generating syntactically or chemically flawed molecules, having narrow domain focus, and struggling to create diverse and feasible molecules due to limited annotated data or external molecular databases. To tackle these challenges, we introduce MolGen, a pre-trained molecular language model tailored specifically for molecule generation. Through the reconstruction of over 100 million molecular SELFIES, MolGen internalizes structural and grammatical insights. This is further enhanced by domain-agnostic molecular prefix tuning, fostering robust knowledge transfer across diverse domains. Importantly, our chemical feedback paradigm steers the model away from molecular hallucinations, ensuring alignment between the model's estimated probabilities and real-world chemical preferences. Extensive experiments on well-known benchmarks underscore MolGen's optimization capabilities in properties such as penalized logP, QED, and molecular docking. Additional analyses confirm its proficiency in accurately capturing molecule distributions, discerning intricate structural patterns, and efficiently exploring the chemical space. Code is available at https://github.com/zjunlp/MolGen. |
| title | Domain-Agnostic Molecular Generation with Chemical Feedback |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language |
| url | https://arxiv.org/abs/2301.11259 |