pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning
Abstract Worldwide, Cancer remains a significant health concern due to its high mortality rates. Despite numerous traditional therapies and wet-laboratory methods for treating cancer-affected cells, these approaches often face limitations, including high costs and substantial side effects. Recently...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84146-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559589557895168 |
|---|---|
| author | Shahid Maqsood Hayat Wajdi Alghamdi Shahid Akbar Ali Raza Rabiah Abdul Kadir Mahidur R. Sarker |
| author_facet | Shahid Maqsood Hayat Wajdi Alghamdi Shahid Akbar Ali Raza Rabiah Abdul Kadir Mahidur R. Sarker |
| author_sort | Shahid |
| collection | DOAJ |
| description | Abstract Worldwide, Cancer remains a significant health concern due to its high mortality rates. Despite numerous traditional therapies and wet-laboratory methods for treating cancer-affected cells, these approaches often face limitations, including high costs and substantial side effects. Recently the high selectivity of peptides has garnered significant attention from scientists due to their reliable targeted actions and minimal adverse effects. Furthermore, keeping the significant outcomes of the existing computational models, we propose a highly reliable and effective model namely, pACP-HybDeep for the accurate prediction of anticancer peptides. In this model, training peptides are numerically encoded using an attention-based ProtBERT-BFD encoder to extract semantic features along with CTDT-based structural information. Furthermore, a k-nearest neighbor-based binary tree growth (BTG) algorithm is employed to select an optimal feature set from the multi-perspective vector. The selected feature vector is subsequently trained using a CNN + RNN-based deep learning model. Our proposed pACP-HybDeep model demonstrated a high training accuracy of 95.33%, and an AUC of 0.97. To validate the generalization capabilities of the model, our pACP-HybDeep model achieved accuracies of 94.92%, 92.26%, and 91.16% on independent datasets Ind-S1, Ind-S2, and Ind-S3, respectively. The demonstrated efficacy, and reliability of the pACP-HybDeep model using test datasets establish it as a valuable tool for researchers in academia and pharmaceutical drug design. |
| format | Article |
| id | doaj-art-33ce078e4fe94b2fba68e8c4665d6d02 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-33ce078e4fe94b2fba68e8c4665d6d022025-01-05T12:22:02ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-024-84146-0pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learningShahid0Maqsood Hayat1Wajdi Alghamdi2Shahid Akbar3Ali Raza4Rabiah Abdul Kadir5Mahidur R. Sarker6Department of Computer Science, Abdul Wali Khan University MardanDepartment of Computer Science, Abdul Wali Khan University MardanDepartment of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz UniversityDepartment of Computer Science, Abdul Wali Khan University MardanDepartment of Computer Science, MY UniversityInstitute of Visual Informatics, Universiti Kebangsaan MalaysiaInstitute of Visual Informatics, Universiti Kebangsaan MalaysiaAbstract Worldwide, Cancer remains a significant health concern due to its high mortality rates. Despite numerous traditional therapies and wet-laboratory methods for treating cancer-affected cells, these approaches often face limitations, including high costs and substantial side effects. Recently the high selectivity of peptides has garnered significant attention from scientists due to their reliable targeted actions and minimal adverse effects. Furthermore, keeping the significant outcomes of the existing computational models, we propose a highly reliable and effective model namely, pACP-HybDeep for the accurate prediction of anticancer peptides. In this model, training peptides are numerically encoded using an attention-based ProtBERT-BFD encoder to extract semantic features along with CTDT-based structural information. Furthermore, a k-nearest neighbor-based binary tree growth (BTG) algorithm is employed to select an optimal feature set from the multi-perspective vector. The selected feature vector is subsequently trained using a CNN + RNN-based deep learning model. Our proposed pACP-HybDeep model demonstrated a high training accuracy of 95.33%, and an AUC of 0.97. To validate the generalization capabilities of the model, our pACP-HybDeep model achieved accuracies of 94.92%, 92.26%, and 91.16% on independent datasets Ind-S1, Ind-S2, and Ind-S3, respectively. The demonstrated efficacy, and reliability of the pACP-HybDeep model using test datasets establish it as a valuable tool for researchers in academia and pharmaceutical drug design.https://doi.org/10.1038/s41598-024-84146-0Anticancer peptidesTransformer encoderPhysiochemical propertiesDeep Hybrid neural networkBinary tree growth feature selection |
| spellingShingle | Shahid Maqsood Hayat Wajdi Alghamdi Shahid Akbar Ali Raza Rabiah Abdul Kadir Mahidur R. Sarker pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning Scientific Reports Anticancer peptides Transformer encoder Physiochemical properties Deep Hybrid neural network Binary tree growth feature selection |
| title | pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning |
| title_full | pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning |
| title_fullStr | pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning |
| title_full_unstemmed | pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning |
| title_short | pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning |
| title_sort | pacp hybdeep predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep hybrid learning |
| topic | Anticancer peptides Transformer encoder Physiochemical properties Deep Hybrid neural network Binary tree growth feature selection |
| url | https://doi.org/10.1038/s41598-024-84146-0 |
| work_keys_str_mv | AT shahid pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT maqsoodhayat pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT wajdialghamdi pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT shahidakbar pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT aliraza pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT rabiahabdulkadir pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning AT mahidurrsarker pacphybdeeppredictinganticancerpeptidesusingbinarytreegrowthbasedtransformerandstructuralfeatureencodingwithdeephybridlearning |