Multi-task aquatic toxicity prediction model based on multi-level features fusion
Introduction: With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how differen...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Journal of Advanced Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090123224002261 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595799147544576 |
|---|---|
| author | Xin Yang Jianqiang Sun Bingyu Jin Yuer Lu Jinyan Cheng Jiaju Jiang Qi Zhao Jianwei Shuai |
| author_facet | Xin Yang Jianqiang Sun Bingyu Jin Yuer Lu Jinyan Cheng Jiaju Jiang Qi Zhao Jianwei Shuai |
| author_sort | Xin Yang |
| collection | DOAJ |
| description | Introduction: With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how different species respond to these compounds helps assess the potential ecological impact of pollution on aquatic ecosystems as a whole. Compared with traditional experimental methods, deep learning methods have higher accuracy in predicting aquatic toxicity, faster data processing speed and better generalization ability. Objectives: This article presents ATFPGT-multi, an advanced multi-task deep neural network prediction model for organic toxicity. Methods: The model integrates molecular fingerprints and molecule graphs to characterize molecules, enabling the simultaneous prediction of acute toxicity for the same organic compound across four distinct fish species. Furthermore, to validate the advantages of multi-task learning, we independently construct prediction models, named ATFPGT-single, for each fish species. We employ cross-validation in our experiments to assess the performance and generalization ability of ATFPGT-multi. Results: The experimental results indicate, first, that ATFPGT-multi outperforms ATFPGT-single on four fish datasets with AUC improvements of 9.8%, 4%, 4.8%, and 8.2%, respectively, demonstrating the superiority of multi-task learning over single-task learning. Furthermore, in comparison with previous algorithms, ATFPGT-multi outperforms comparative methods, emphasizing that our approach exhibits higher accuracy and reliability in predicting aquatic toxicity. Moreover, ATFPGT-multi utilizes attention scores to identify molecular fragments associated with fish toxicity in organic molecules, as demonstrated by two organic molecule examples in the main text, demonstrating the interpretability of ATFPGT-multi. Conclusion: In summary, ATFPGT-multi provides important support and reference for the further development of aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/ATFPGT-multi. |
| format | Article |
| id | doaj-art-c87780f771f946a3896f67e66b83a44f |
| institution | Kabale University |
| issn | 2090-1232 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Advanced Research |
| spelling | doaj-art-c87780f771f946a3896f67e66b83a44f2025-01-18T05:04:23ZengElsevierJournal of Advanced Research2090-12322025-02-0168477489Multi-task aquatic toxicity prediction model based on multi-level features fusionXin Yang0Jianqiang Sun1Bingyu Jin2Yuer Lu3Jinyan Cheng4Jiaju Jiang5Qi Zhao6Jianwei Shuai7School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China; Wenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, ChinaSchool of Information Science and Engineering, Linyi University, Linyi 276000, ChinaSchool of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, ChinaWenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, ChinaWenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, ChinaCollege of Life Sciences, Sichuan University, Chengdu 610064, ChinaSchool of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China; Corresponding authors at: School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China (Q. Zhao); Wenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, China (J. Shuai).Wenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, China; Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Wenzhou 325001, China; Corresponding authors at: School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China (Q. Zhao); Wenzhou Institute, University of Chinese Academy of Sciences, Wenzhou 325001, China (J. Shuai).Introduction: With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how different species respond to these compounds helps assess the potential ecological impact of pollution on aquatic ecosystems as a whole. Compared with traditional experimental methods, deep learning methods have higher accuracy in predicting aquatic toxicity, faster data processing speed and better generalization ability. Objectives: This article presents ATFPGT-multi, an advanced multi-task deep neural network prediction model for organic toxicity. Methods: The model integrates molecular fingerprints and molecule graphs to characterize molecules, enabling the simultaneous prediction of acute toxicity for the same organic compound across four distinct fish species. Furthermore, to validate the advantages of multi-task learning, we independently construct prediction models, named ATFPGT-single, for each fish species. We employ cross-validation in our experiments to assess the performance and generalization ability of ATFPGT-multi. Results: The experimental results indicate, first, that ATFPGT-multi outperforms ATFPGT-single on four fish datasets with AUC improvements of 9.8%, 4%, 4.8%, and 8.2%, respectively, demonstrating the superiority of multi-task learning over single-task learning. Furthermore, in comparison with previous algorithms, ATFPGT-multi outperforms comparative methods, emphasizing that our approach exhibits higher accuracy and reliability in predicting aquatic toxicity. Moreover, ATFPGT-multi utilizes attention scores to identify molecular fragments associated with fish toxicity in organic molecules, as demonstrated by two organic molecule examples in the main text, demonstrating the interpretability of ATFPGT-multi. Conclusion: In summary, ATFPGT-multi provides important support and reference for the further development of aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/ATFPGT-multi.http://www.sciencedirect.com/science/article/pii/S2090123224002261Acute toxicityDeep learningMulti-task modelMolecular fingerprintsMolecular graph features |
| spellingShingle | Xin Yang Jianqiang Sun Bingyu Jin Yuer Lu Jinyan Cheng Jiaju Jiang Qi Zhao Jianwei Shuai Multi-task aquatic toxicity prediction model based on multi-level features fusion Journal of Advanced Research Acute toxicity Deep learning Multi-task model Molecular fingerprints Molecular graph features |
| title | Multi-task aquatic toxicity prediction model based on multi-level features fusion |
| title_full | Multi-task aquatic toxicity prediction model based on multi-level features fusion |
| title_fullStr | Multi-task aquatic toxicity prediction model based on multi-level features fusion |
| title_full_unstemmed | Multi-task aquatic toxicity prediction model based on multi-level features fusion |
| title_short | Multi-task aquatic toxicity prediction model based on multi-level features fusion |
| title_sort | multi task aquatic toxicity prediction model based on multi level features fusion |
| topic | Acute toxicity Deep learning Multi-task model Molecular fingerprints Molecular graph features |
| url | http://www.sciencedirect.com/science/article/pii/S2090123224002261 |
| work_keys_str_mv | AT xinyang multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT jianqiangsun multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT bingyujin multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT yuerlu multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT jinyancheng multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT jiajujiang multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT qizhao multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion AT jianweishuai multitaskaquatictoxicitypredictionmodelbasedonmultilevelfeaturesfusion |