Prediction of hemolytic peptides and their hemolytic concentration
Abstract Peptide-based drugs often fail in clinical trials due to their toxicity or hemolytic activity against red blood cells (RBCs). Existing methods predict hemolytic peptides but not the concentration (HC50) required to lyse 50% of RBCs. This study develops classification and regression models t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Communications Biology |
| Online Access: | https://doi.org/10.1038/s42003-025-07615-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861750429122560 |
|---|---|
| author | Anand Singh Rathore Nishant Kumar Shubham Choudhury Naman Kumar Mehta Gajendra P. S. Raghava |
| author_facet | Anand Singh Rathore Nishant Kumar Shubham Choudhury Naman Kumar Mehta Gajendra P. S. Raghava |
| author_sort | Anand Singh Rathore |
| collection | DOAJ |
| description | Abstract Peptide-based drugs often fail in clinical trials due to their toxicity or hemolytic activity against red blood cells (RBCs). Existing methods predict hemolytic peptides but not the concentration (HC50) required to lyse 50% of RBCs. This study develops classification and regression models to identify and quantify hemolytic activity. These models train on 1926 peptides with experimentally determined HC50 against mammalian RBCs. Analysis indicates that hydrophobic and positively charged residues were associated with higher hemolytic activity. Among classification models, including machine learning (ML), quantum ML, and protein language models, a hybrid model combining random forest (RF) and a motif-based approach achieves the highest area under the receiver operating characteristic curve (AUROC) of 0.921. Regression models achieve a Pearson correlation coefficient (R) of 0.739 and a coefficient of determination (R²) of 0.543. These models outperform existing methods and are implemented in HemoPI2, a web-based platform and standalone software for designing peptides with desired HC50 values ( http://webs.iiitd.edu.in/raghava/hemopi2/ ). |
| format | Article |
| id | doaj-art-ae110a865adc4fa79f3d3fb13d3472e0 |
| institution | Kabale University |
| issn | 2399-3642 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Biology |
| spelling | doaj-art-ae110a865adc4fa79f3d3fb13d3472e02025-02-09T12:50:43ZengNature PortfolioCommunications Biology2399-36422025-02-018111410.1038/s42003-025-07615-wPrediction of hemolytic peptides and their hemolytic concentrationAnand Singh Rathore0Nishant Kumar1Shubham Choudhury2Naman Kumar Mehta3Gajendra P. S. Raghava4Department of Computational Biology, Indraprastha Institute of Information TechnologyDepartment of Computational Biology, Indraprastha Institute of Information TechnologyDepartment of Computational Biology, Indraprastha Institute of Information TechnologyDepartment of Computational Biology, Indraprastha Institute of Information TechnologyDepartment of Computational Biology, Indraprastha Institute of Information TechnologyAbstract Peptide-based drugs often fail in clinical trials due to their toxicity or hemolytic activity against red blood cells (RBCs). Existing methods predict hemolytic peptides but not the concentration (HC50) required to lyse 50% of RBCs. This study develops classification and regression models to identify and quantify hemolytic activity. These models train on 1926 peptides with experimentally determined HC50 against mammalian RBCs. Analysis indicates that hydrophobic and positively charged residues were associated with higher hemolytic activity. Among classification models, including machine learning (ML), quantum ML, and protein language models, a hybrid model combining random forest (RF) and a motif-based approach achieves the highest area under the receiver operating characteristic curve (AUROC) of 0.921. Regression models achieve a Pearson correlation coefficient (R) of 0.739 and a coefficient of determination (R²) of 0.543. These models outperform existing methods and are implemented in HemoPI2, a web-based platform and standalone software for designing peptides with desired HC50 values ( http://webs.iiitd.edu.in/raghava/hemopi2/ ).https://doi.org/10.1038/s42003-025-07615-w |
| spellingShingle | Anand Singh Rathore Nishant Kumar Shubham Choudhury Naman Kumar Mehta Gajendra P. S. Raghava Prediction of hemolytic peptides and their hemolytic concentration Communications Biology |
| title | Prediction of hemolytic peptides and their hemolytic concentration |
| title_full | Prediction of hemolytic peptides and their hemolytic concentration |
| title_fullStr | Prediction of hemolytic peptides and their hemolytic concentration |
| title_full_unstemmed | Prediction of hemolytic peptides and their hemolytic concentration |
| title_short | Prediction of hemolytic peptides and their hemolytic concentration |
| title_sort | prediction of hemolytic peptides and their hemolytic concentration |
| url | https://doi.org/10.1038/s42003-025-07615-w |
| work_keys_str_mv | AT anandsinghrathore predictionofhemolyticpeptidesandtheirhemolyticconcentration AT nishantkumar predictionofhemolyticpeptidesandtheirhemolyticconcentration AT shubhamchoudhury predictionofhemolyticpeptidesandtheirhemolyticconcentration AT namankumarmehta predictionofhemolyticpeptidesandtheirhemolyticconcentration AT gajendrapsraghava predictionofhemolyticpeptidesandtheirhemolyticconcentration |