Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning
Anticancer peptides (ACPs) are selective and toxic to cancer cells as new anticancer drugs. Identifying new ACPs is time-consuming and expensive to evaluate all candidates’ anticancer abilities. To reduce the cost of ACP drug development, we collected the most updated ACP data to train a convolution...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Pharmaceuticals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8247/15/4/422 |
| _version_ | 1827599645539303424 |
|---|---|
| author | Yih-Yun Sun Tzu-Tang Lin Wen-Chih Cheng I-Hsuan Lu Chung-Yen Lin Shu-Hwa Chen |
| author_facet | Yih-Yun Sun Tzu-Tang Lin Wen-Chih Cheng I-Hsuan Lu Chung-Yen Lin Shu-Hwa Chen |
| author_sort | Yih-Yun Sun |
| collection | DOAJ |
| description | Anticancer peptides (ACPs) are selective and toxic to cancer cells as new anticancer drugs. Identifying new ACPs is time-consuming and expensive to evaluate all candidates’ anticancer abilities. To reduce the cost of ACP drug development, we collected the most updated ACP data to train a convolutional neural network (CNN) with a peptide sequence encoding method for initial in silico evaluation. Here we introduced PC6, a novel protein-encoding method, to convert a peptide sequence into a computational matrix, representing six physicochemical properties of each amino acid. By integrating data, encoding method, and deep learning model, we developed AI4ACP, a user-friendly web-based ACP distinguisher that can predict the anticancer property of query peptides and promote the discovery of peptides with anticancer activity. The experimental results demonstrate that AI4ACP in CNN, trained using the new ACP collection, outperforms the existing ACP predictors. The 5-fold cross-validation of AI4ACP with the new collection also showed that the model could perform at a stable level on high accuracy around 0.89 without overfitting. Using AI4ACP, users can easily accomplish an early-stage evaluation of unknown peptides and select potential candidates to test their anticancer activities quickly. |
| first_indexed | 2024-03-09T04:18:57Z |
| format | Article |
| id | doaj.art-68648c10ca034501a63d44297d403b7a |
| institution | Directory Open Access Journal |
| issn | 1424-8247 |
| language | English |
| last_indexed | 2024-03-09T04:18:57Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pharmaceuticals |
| spelling | doaj.art-68648c10ca034501a63d44297d403b7a2023-12-03T13:49:31ZengMDPI AGPharmaceuticals1424-82472022-03-0115442210.3390/ph15040422Peptide-Based Drug Predictions for Cancer Therapy Using Deep LearningYih-Yun Sun0Tzu-Tang Lin1Wen-Chih Cheng2I-Hsuan Lu3Chung-Yen Lin4Shu-Hwa Chen5Graduate Institute of Biomedical Electronics and Bioinformatics, College of Electrical Engineering and Computer Science, National Taiwan University, Taipei 106, TaiwanInstitute of Information Science, Academia Sinica, Taipei 115, TaiwanInstitute of Information Science, Academia Sinica, Taipei 115, TaiwanInstitute of Information Science, Academia Sinica, Taipei 115, TaiwanInstitute of Information Science, Academia Sinica, Taipei 115, TaiwanResearch Center of Cancer Translational Medicine, Taipei Medical University, Taipei 110, TaiwanAnticancer peptides (ACPs) are selective and toxic to cancer cells as new anticancer drugs. Identifying new ACPs is time-consuming and expensive to evaluate all candidates’ anticancer abilities. To reduce the cost of ACP drug development, we collected the most updated ACP data to train a convolutional neural network (CNN) with a peptide sequence encoding method for initial in silico evaluation. Here we introduced PC6, a novel protein-encoding method, to convert a peptide sequence into a computational matrix, representing six physicochemical properties of each amino acid. By integrating data, encoding method, and deep learning model, we developed AI4ACP, a user-friendly web-based ACP distinguisher that can predict the anticancer property of query peptides and promote the discovery of peptides with anticancer activity. The experimental results demonstrate that AI4ACP in CNN, trained using the new ACP collection, outperforms the existing ACP predictors. The 5-fold cross-validation of AI4ACP with the new collection also showed that the model could perform at a stable level on high accuracy around 0.89 without overfitting. Using AI4ACP, users can easily accomplish an early-stage evaluation of unknown peptides and select potential candidates to test their anticancer activities quickly.https://www.mdpi.com/1424-8247/15/4/422anticancer peptides (ACPs)deep learningweb serviceprediction |
| spellingShingle | Yih-Yun Sun Tzu-Tang Lin Wen-Chih Cheng I-Hsuan Lu Chung-Yen Lin Shu-Hwa Chen Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning Pharmaceuticals anticancer peptides (ACPs) deep learning web service prediction |
| title | Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning |
| title_full | Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning |
| title_fullStr | Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning |
| title_full_unstemmed | Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning |
| title_short | Peptide-Based Drug Predictions for Cancer Therapy Using Deep Learning |
| title_sort | peptide based drug predictions for cancer therapy using deep learning |
| topic | anticancer peptides (ACPs) deep learning web service prediction |
| url | https://www.mdpi.com/1424-8247/15/4/422 |
| work_keys_str_mv | AT yihyunsun peptidebaseddrugpredictionsforcancertherapyusingdeeplearning AT tzutanglin peptidebaseddrugpredictionsforcancertherapyusingdeeplearning AT wenchihcheng peptidebaseddrugpredictionsforcancertherapyusingdeeplearning AT ihsuanlu peptidebaseddrugpredictionsforcancertherapyusingdeeplearning AT chungyenlin peptidebaseddrugpredictionsforcancertherapyusingdeeplearning AT shuhwachen peptidebaseddrugpredictionsforcancertherapyusingdeeplearning |