iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models
Background Dihydrouridine (D) is one of the most significant uridine modifications that have a prominent occurrence in eukaryotes. The folding and conformational flexibility of transfer RNA (tRNA) can be attained through this modification. Objective The modification also triggers lung cancer in huma...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-03-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076231165963 |
| _version_ | 1797856135499218944 |
|---|---|
| author | Muhammad Taseer Suleman Fahad Alturise Tamim Alkhalifah Yaser Daanial Khan |
| author_facet | Muhammad Taseer Suleman Fahad Alturise Tamim Alkhalifah Yaser Daanial Khan |
| author_sort | Muhammad Taseer Suleman |
| collection | DOAJ |
| description | Background Dihydrouridine (D) is one of the most significant uridine modifications that have a prominent occurrence in eukaryotes. The folding and conformational flexibility of transfer RNA (tRNA) can be attained through this modification. Objective The modification also triggers lung cancer in humans. The identification of D sites was carried out through conventional laboratory methods; however, those were costly and time-consuming. The readiness of RNA sequences helps in the identification of D sites through computationally intelligent models. However, the most challenging part is turning these biological sequences into distinct vectors. Methods The current research proposed novel feature extraction mechanisms and the identification of D sites in tRNA sequences using ensemble models. The ensemble models were then subjected to evaluation using k-fold cross-validation and independent testing. Results The results revealed that the stacking ensemble model outperformed all the ensemble models by revealing 0.98 accuracy, 0.98 specificity, 0.97 sensitivity, and 0.92 Matthews Correlation Coefficient. The proposed model, iDHU-Ensem, was also compared with pre-existing predictors using an independent test. The accuracy scores have shown that the proposed model in this research study performed better than the available predictors. Conclusion The current research contributed towards the enhancement of D site identification capabilities through computationally intelligent methods. A web-based server, iDHU-Ensem, was also made available for the researchers at https://taseersuleman-idhu-ensem-idhu-ensem.streamlit.app/ . |
| first_indexed | 2024-04-09T20:35:28Z |
| format | Article |
| id | doaj.art-379482fb27fa4a7eb97c01bdd875b088 |
| institution | Directory Open Access Journal |
| issn | 2055-2076 |
| language | English |
| last_indexed | 2024-04-09T20:35:28Z |
| publishDate | 2023-03-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj.art-379482fb27fa4a7eb97c01bdd875b0882023-03-30T09:34:50ZengSAGE PublishingDigital Health2055-20762023-03-01910.1177/20552076231165963iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning modelsMuhammad Taseer Suleman0Fahad Alturise1 Tamim Alkhalifah2Yaser Daanial Khan3 Department of Computer Science, School of systems and technology, , Lahore, Pakistan Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia Department of Computer Science, School of systems and technology, , Lahore, PakistanBackground Dihydrouridine (D) is one of the most significant uridine modifications that have a prominent occurrence in eukaryotes. The folding and conformational flexibility of transfer RNA (tRNA) can be attained through this modification. Objective The modification also triggers lung cancer in humans. The identification of D sites was carried out through conventional laboratory methods; however, those were costly and time-consuming. The readiness of RNA sequences helps in the identification of D sites through computationally intelligent models. However, the most challenging part is turning these biological sequences into distinct vectors. Methods The current research proposed novel feature extraction mechanisms and the identification of D sites in tRNA sequences using ensemble models. The ensemble models were then subjected to evaluation using k-fold cross-validation and independent testing. Results The results revealed that the stacking ensemble model outperformed all the ensemble models by revealing 0.98 accuracy, 0.98 specificity, 0.97 sensitivity, and 0.92 Matthews Correlation Coefficient. The proposed model, iDHU-Ensem, was also compared with pre-existing predictors using an independent test. The accuracy scores have shown that the proposed model in this research study performed better than the available predictors. Conclusion The current research contributed towards the enhancement of D site identification capabilities through computationally intelligent methods. A web-based server, iDHU-Ensem, was also made available for the researchers at https://taseersuleman-idhu-ensem-idhu-ensem.streamlit.app/ .https://doi.org/10.1177/20552076231165963 |
| spellingShingle | Muhammad Taseer Suleman Fahad Alturise Tamim Alkhalifah Yaser Daanial Khan iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models Digital Health |
| title | iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models |
| title_full | iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models |
| title_fullStr | iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models |
| title_full_unstemmed | iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models |
| title_short | iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models |
| title_sort | idhu ensem identification of dihydrouridine sites through ensemble learning models |
| url | https://doi.org/10.1177/20552076231165963 |
| work_keys_str_mv | AT muhammadtaseersuleman idhuensemidentificationofdihydrouridinesitesthroughensemblelearningmodels AT fahadalturise idhuensemidentificationofdihydrouridinesitesthroughensemblelearningmodels AT tamimalkhalifah idhuensemidentificationofdihydrouridinesitesthroughensemblelearningmodels AT yaserdaanialkhan idhuensemidentificationofdihydrouridinesitesthroughensemblelearningmodels |