Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929264379559936 |
|---|---|
| author | Zhang, Chengwei Zhai, Yushuang Gong, Ziyang Duan, Hongliang She, Yuan-Bin Yang, Yun-Fang Su, An |
| author_facet | Zhang, Chengwei Zhai, Yushuang Gong, Ziyang Duan, Hongliang She, Yuan-Bin Yang, Yun-Fang Su, An |
| contents | Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual screening of organic materials. By fine-tuning the BERT models with data from five virtual screening tasks, the version pretrained with the USPTO-SMILES dataset achieved R2 scores exceeding 0.94 for three tasks and over 0.81 for two others. This performance surpasses that of models pretrained on the small molecule or organic materials databases and outperforms three traditional machine learning models trained directly on virtual screening data. The success of the USPTO-SMILES pretrained BERT model can be attributed to the diverse array of organic building blocks in the USPTO database, offering a broader exploration of the chemical space. The study further suggests that accessing a reaction database with a wider range of reactions than the USPTO could further enhance model performance. Overall, this research validates the feasibility of applying transfer learning across different chemical domains for the efficient virtual screening of organic materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_18377 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data Zhang, Chengwei Zhai, Yushuang Gong, Ziyang Duan, Hongliang She, Yuan-Bin Yang, Yun-Fang Su, An Chemical Physics Machine Learning Biomolecules Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual screening of organic materials. By fine-tuning the BERT models with data from five virtual screening tasks, the version pretrained with the USPTO-SMILES dataset achieved R2 scores exceeding 0.94 for three tasks and over 0.81 for two others. This performance surpasses that of models pretrained on the small molecule or organic materials databases and outperforms three traditional machine learning models trained directly on virtual screening data. The success of the USPTO-SMILES pretrained BERT model can be attributed to the diverse array of organic building blocks in the USPTO database, offering a broader exploration of the chemical space. The study further suggests that accessing a reaction database with a wider range of reactions than the USPTO could further enhance model performance. Overall, this research validates the feasibility of applying transfer learning across different chemical domains for the efficient virtual screening of organic materials. |
| title | Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data |
| topic | Chemical Physics Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2311.18377 |