Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey
The precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep learningbased methods has shown remarkable potential in enhancing Molecular Property Prediction (MPP...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020028 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572871744946176 |
|---|---|
| author | Taojie Kuang Pengfei Liu Zhixiang Ren |
| author_facet | Taojie Kuang Pengfei Liu Zhixiang Ren |
| author_sort | Taojie Kuang |
| collection | DOAJ |
| description | The precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep learningbased methods has shown remarkable potential in enhancing Molecular Property Prediction (MPP), especially improving accuracy and insights into molecular structures. Yet, two critical questions arise: does the integration of domain knowledge augment the accuracy of molecular property prediction and does employing multi-modal data fusion yield more precise results than unique data source methods? To explore these matters, we comprehensively review and quantitatively analyze recent deep learning methods based on various benchmarks. We discover that integrating molecular information significantly improves Molecular Property Prediction (MPP) for both regression and classification tasks. Specifically, regression improvements, measured by reductions in Root Mean Square Error (RMSE), are up to 4.0%, while classification enhancements, measured by the area under the receiver operating characteristic curve (ROC-AUC), are up to 1.7%. Additionally, we discover that, as measured by ROC-AUC, augmenting 2D graphs with 3D information improves performance for classification tasks by up to 13.2% and enriching 2D graphs with 1D SMILES boosts multi-modal learning performance for regression tasks by up to 9.1%. The two consolidated insights offer crucial guidance for future advancements in drug discovery. |
| format | Article |
| id | doaj-art-4870300b0bb944759a1a547071cce1b1 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-4870300b0bb944759a1a547071cce1b12025-02-02T06:29:08ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017385888810.26599/BDMA.2024.9020028Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic SurveyTaojie Kuang0Pengfei Liu1Zhixiang Ren2Peng Cheng National Laboratory, Shenzhen 518000, China, and also with School of Future Technology, South China University of Technology, Guangzhou 511442, ChinaPeng Cheng National Laboratory, Shenzhen 518000, China, and also with School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, ChinaPeng Cheng National Laboratory, Shenzhen 518000, ChinaThe precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep learningbased methods has shown remarkable potential in enhancing Molecular Property Prediction (MPP), especially improving accuracy and insights into molecular structures. Yet, two critical questions arise: does the integration of domain knowledge augment the accuracy of molecular property prediction and does employing multi-modal data fusion yield more precise results than unique data source methods? To explore these matters, we comprehensively review and quantitatively analyze recent deep learning methods based on various benchmarks. We discover that integrating molecular information significantly improves Molecular Property Prediction (MPP) for both regression and classification tasks. Specifically, regression improvements, measured by reductions in Root Mean Square Error (RMSE), are up to 4.0%, while classification enhancements, measured by the area under the receiver operating characteristic curve (ROC-AUC), are up to 1.7%. Additionally, we discover that, as measured by ROC-AUC, augmenting 2D graphs with 3D information improves performance for classification tasks by up to 13.2% and enriching 2D graphs with 1D SMILES boosts multi-modal learning performance for regression tasks by up to 9.1%. The two consolidated insights offer crucial guidance for future advancements in drug discovery.https://www.sciopen.com/article/10.26599/BDMA.2024.9020028molecular property prediction (mpp)deep learning (dl)domain knowledgemulti-modalitydrug discovery |
| spellingShingle | Taojie Kuang Pengfei Liu Zhixiang Ren Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey Big Data Mining and Analytics molecular property prediction (mpp) deep learning (dl) domain knowledge multi-modality drug discovery |
| title | Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey |
| title_full | Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey |
| title_fullStr | Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey |
| title_full_unstemmed | Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey |
| title_short | Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey |
| title_sort | impact of domain knowledge and multi modality on intelligent molecular property prediction a systematic survey |
| topic | molecular property prediction (mpp) deep learning (dl) domain knowledge multi-modality drug discovery |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020028 |
| work_keys_str_mv | AT taojiekuang impactofdomainknowledgeandmultimodalityonintelligentmolecularpropertypredictionasystematicsurvey AT pengfeiliu impactofdomainknowledgeandmultimodalityonintelligentmolecularpropertypredictionasystematicsurvey AT zhixiangren impactofdomainknowledgeandmultimodalityonintelligentmolecularpropertypredictionasystematicsurvey |