List of datasets in AqSolDB.
<div><p>Aqueous solubility, an essential physical property of compounds, has significant applications across various fields. However, verifying the solubility of compounds through experimental methods often requires substantial human and material resources. To address this issue, this st...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852017156584112128 |
|---|---|
| author | Bin Pan (742525) |
| author2 | Xiaoyu Hou (1571344) Mingxin Zhang (4898947) Jingxian Yu (1332696) Conghui Zhang (3456536) Yunhui Zhang (65111) Xiaolong Su (2015140) Shuangcai Li (16458999) |
| author2_role | author author author author author author author |
| author_facet | Bin Pan (742525) Xiaoyu Hou (1571344) Mingxin Zhang (4898947) Jingxian Yu (1332696) Conghui Zhang (3456536) Yunhui Zhang (65111) Xiaolong Su (2015140) Shuangcai Li (16458999) |
| author_role | author |
| dc.creator.none.fl_str_mv | Bin Pan (742525) Xiaoyu Hou (1571344) Mingxin Zhang (4898947) Jingxian Yu (1332696) Conghui Zhang (3456536) Yunhui Zhang (65111) Xiaolong Su (2015140) Shuangcai Li (16458999) |
| dc.date.none.fl_str_mv | 2025-08-29T17:56:10Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0330598.t001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/List_of_datasets_in_AqSolDB_/30014345 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Genetics Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified prediction results indicate mean absolute error essential physical property generalizable prediction model stackboost model excels stackboost model decreases successfully identified compounds div >< p predicting aqueous solubility stackboost model model ’ aqueous solubility xgboost ), water solubility transfer learning throughput screening systematically compares significantly outperforming scale datasets rf ). random forest organic compounds material resources high potential generalization ability five well different datasets determination () conducted high comparative models adaptive boosting |
| dc.title.none.fl_str_mv | List of datasets in AqSolDB. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Aqueous solubility, an essential physical property of compounds, has significant applications across various fields. However, verifying the solubility of compounds through experimental methods often requires substantial human and material resources. To address this issue, this study introduces the StackBoost model for predicting the solubility of organic compounds and systematically compares it with five well-known ensemble learning algorithms: Adaptive Boosting (AdaBoost), Gradient Boosted Regression Trees (GBRT), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF). The prediction results indicate that the StackBoost model excels in predicting aqueous solubility, achieving a coefficient of determination () of 0.90, a root mean square error (RMSE) of 0.29, and a mean absolute error (MAE) of 0.22, significantly outperforming the other comparative models. Furthermore, this study further conducted high-throughput screening on large-scale datasets and successfully identified compounds with high potential for water solubility. Additionally, the model’s generalization ability is verified through transfer learning. Although the performance of the StackBoost model decreases when applied to different datasets, it still shows considerable transferability, making it a more generalizable prediction model for aqueous solubility.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_7bf4c2b4cff3d1b663232da2bc549a39 |
| identifier_str_mv | 10.1371/journal.pone.0330598.t001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30014345 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | List of datasets in AqSolDB.Bin Pan (742525)Xiaoyu Hou (1571344)Mingxin Zhang (4898947)Jingxian Yu (1332696)Conghui Zhang (3456536)Yunhui Zhang (65111)Xiaolong Su (2015140)Shuangcai Li (16458999)GeneticsEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedprediction results indicatemean absolute erroressential physical propertygeneralizable prediction modelstackboost model excelsstackboost model decreasessuccessfully identified compoundsdiv >< ppredicting aqueous solubilitystackboost modelmodel ’aqueous solubilityxgboost ),water solubilitytransfer learningthroughput screeningsystematically comparessignificantly outperformingscale datasetsrf ).random forestorganic compoundsmaterial resourceshigh potentialgeneralization abilityfive welldifferent datasetsdetermination ()conducted highcomparative modelsadaptive boosting<div><p>Aqueous solubility, an essential physical property of compounds, has significant applications across various fields. However, verifying the solubility of compounds through experimental methods often requires substantial human and material resources. To address this issue, this study introduces the StackBoost model for predicting the solubility of organic compounds and systematically compares it with five well-known ensemble learning algorithms: Adaptive Boosting (AdaBoost), Gradient Boosted Regression Trees (GBRT), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF). The prediction results indicate that the StackBoost model excels in predicting aqueous solubility, achieving a coefficient of determination () of 0.90, a root mean square error (RMSE) of 0.29, and a mean absolute error (MAE) of 0.22, significantly outperforming the other comparative models. Furthermore, this study further conducted high-throughput screening on large-scale datasets and successfully identified compounds with high potential for water solubility. Additionally, the model’s generalization ability is verified through transfer learning. Although the performance of the StackBoost model decreases when applied to different datasets, it still shows considerable transferability, making it a more generalizable prediction model for aqueous solubility.</p></div>2025-08-29T17:56:10ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0330598.t001https://figshare.com/articles/dataset/List_of_datasets_in_AqSolDB_/30014345CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300143452025-08-29T17:56:10Z |
| spellingShingle | List of datasets in AqSolDB. Bin Pan (742525) Genetics Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified prediction results indicate mean absolute error essential physical property generalizable prediction model stackboost model excels stackboost model decreases successfully identified compounds div >< p predicting aqueous solubility stackboost model model ’ aqueous solubility xgboost ), water solubility transfer learning throughput screening systematically compares significantly outperforming scale datasets rf ). random forest organic compounds material resources high potential generalization ability five well different datasets determination () conducted high comparative models adaptive boosting |
| status_str | publishedVersion |
| title | List of datasets in AqSolDB. |
| title_full | List of datasets in AqSolDB. |
| title_fullStr | List of datasets in AqSolDB. |
| title_full_unstemmed | List of datasets in AqSolDB. |
| title_short | List of datasets in AqSolDB. |
| title_sort | List of datasets in AqSolDB. |
| topic | Genetics Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified prediction results indicate mean absolute error essential physical property generalizable prediction model stackboost model excels stackboost model decreases successfully identified compounds div >< p predicting aqueous solubility stackboost model model ’ aqueous solubility xgboost ), water solubility transfer learning throughput screening systematically compares significantly outperforming scale datasets rf ). random forest organic compounds material resources high potential generalization ability five well different datasets determination () conducted high comparative models adaptive boosting |